Professional Documents
Culture Documents
Mac ine
www.csi-india.org
Le rning
Contents
Chief Editor
S S AgRAwAl
KIIT Group, Gurgaon
Editor Cover Story
PRAShANT R. NAIR
Amrita University, Coimbatore Machine Learning: Messiah of 21st Century 6
Tawseef Ayoub Shaikh and Rashid Ali
Published by
A. K. NAYAK Technical Trends
Hony. Secretary
From Machine Learning to Deep Learning: Trends and Challenges 10
For Computer Society of India Apoorva Mishra and Anupam Shukla
Editorial Board:
Machine Learning and its application in Technology and Media industries 13
Arun B Samaddar, NIT, Sikkim Krishna Murthy
Bhabani Shankar Prasad Mishra,
KIIT University, Bhubanewar
Debajyoti Mukhopadhyay, MIT, Pune
Research Front
J. Yogapriya, Kongunadu Engg. College, Trichy Challenges of Theoretical Computer Science and Computing Systems 16
M Sasikumar, CDAC, Mumbai,
R. Ponnusamy
R Subburaj, SRM University, Chennai Fuzzy Based Machine Learning: A Promising Approach 21
Sujamol S., Sreeja Ashok and U Krishna Kumar
R K Samanta, SiliguriInst. of Tech., West Bengal
R N Behera, NIC, Bhubaneswar
Sudhakar A M, University of Mysore
Articles
Sunil Pandey, ITS, Ghaziabad Using statistical approach to Machine Translation for Indian languages 25
M. Sasikumar and Prakash B. Pimpale
Shailesh K Srivastava, NIC, Patna
Machine learning at the Edge of Internet of Things 28
Vishal Mehrotra, TCS
Mohammad Khalid Pandit, Roohie Naaz Mir and Mohammad Ahsan Chisthi
Security Corner
Design, Print and Dispatch by
Empirical Survey on Advances of Network Forensics in the Emerging Networks 31
gP OFFSET PvT. lTD. A. R. Jayakrishnan and V. Vasanthi
P l US
Meetings with Goa Chief Minister and Goa Chamber of commerce 2nd Cover
Please note: CSI Members win International recognition in SEARCC 12
CSI Communications is published by Computer
Society of India, a non-profit organization. Obituary - Dr. A. Shamugasundaram 12
Views and opinions expressed in the CSI
Communications are those of individual CSI Executive Committee (ExecCom) meeting at Nashik on 7 October 2017 20
authors, contributors and advertisers and they
may differ from policies and official statements Past President visit to Shambhunath Inst. of Engineering & Technology 24
of CSI. These should not be construed as legal
or professional advice. The CSI, the publisher,
“GeekExpo” - Project Exhibition 27
the editors and the contributors are not Report of ‘3rd IT Excellence Awards 2017’ by CSI Ghaziabad Chapter 37
responsible for any decisions taken by readers
on the basis of these views and opinions. CSI Young IT Professional (YITP) Awards 2017 – A Report 38
Although every care is being taken to ensure
genuineness of the writings in this publication,
Pilgrims in the Digital World – Book Review 41
CSI Communications does not attest to the CSI Reports 42
originality of the respective authors’ content.
© 2012 CSI. All rights reserved. Student Branches News 44
Instructors are permitted to photocopy isolated
articles for non-commercial classroom use
52nd Annual Convention of Computer Society of India 3rd Cover
without fee. For any other copying, reprint or Call for Papers-International Conference on Social Transformation - Digital Way Back Page
republication, permission must be obtained
in writing from the Society. Copying for other Printed and Published by Prof. A. K. Nayak on behalf of Computer Society of India, Printed at G.P. Offset Pvt. Ltd.
than personal use or internal reference, or of
articles or columns not owned by the Society
269 / A2, Shah & Nahar Industrial Estate, Dhanraj Mill Compound, Lower Parel (W), Mumbai 400 013 and published from
without explicit permission of the Society or Computer Society of India, Samruddhi Venture Park, Unit-3, 4th Floor, Marol Industrial Area, Andheri (East), Mumbai 400 093.
the copyright owner is strictly prohibited. Tel. : 022-2926 1700 • Fax : 022-2830 2133 • Email : hq@csi-india.org
3
CS I C o mm u n I Ca t I o n S | n o VE m B ER 2 0 1 7
Editorial
Dear Fellow CSI Members,
The theme for the Computer Society of India (CSI) Communications (The Knowledge Digest
for IT Community) November 2017 issue is Machine Learning
“The human condition is plagued with a labyrinth of shortcomings, frailties and limitations that
hinder man from reaching his fullest potential. Therefore, it only makes sense that we find
ourselves at the next phase in human evolution where restricted man merges with the infinite
possibilities of hyper-evolving technologies. This techno-human transmutation will prove to be
‘the’ quantum leap in human progression. The harmonization of technologically extending oneself,
Prof. (Dr.) S. S. Agrawal consciousness, artificial intelligence and machine learning will reverse the failures of genetic Prof. Prashant R. Nair
Chief Editor Editor
predisposition and limitation.”
James Scott, Senior Fellow, Institute for Critical Infrastructure Technology
After a series of thematic issues focusing on ICT in applications such as education, governance, agriculture and health, CSI
Communications is focusing on machine learning in this issue. Machine learning is a field of computer science that gives
computers the ability to learn without being explicitly programmed. Machine learning is employed in a range of computing tasks
where designing and programming explicit algorithms with good performance is difficult or infeasible; example applications
include email filtering, detection of network intruders and computer vision.
The Cover story in this issue is Machine Learning: Messiah of 21st Century by Tawseef Ayoub Shaikh and Rashid Ali. In this article,
the authors have traced the evolution of machine learning and also classified the same.
The technical trends showcased are “Machine Learning and its application in technology and media industries” by Krishna Murthy
and “From Machine Learning to Deep Learning: Trends and Challenges” by Apoorva Mishra & Anupam Shukla
In Research front, we have two contributions, One is “Fuzzy Based Machine Learning: A Promising Approach Towards Better
Decision Making” by Sujamol.S, Sreeja Ashok & U Krishna Kumar. The other one is “Challenges of Theoretical Computer Science
and Computing Systems” by R.Ponnusamy.
Other articles in this issue on machine learning provide us information on applications, of machine learning in healthcare, I ndian
languages, IoT and bioinformatics.
The articles are as follows:
¬ “Using statistical approach to Machine Translation for Indian languages” by M. Sasikumar & Prakash B. Pimpale
¬ “Machine learning at the Edge of Internet of Things” by Mohammad Khalid Pandit, Roohie Naaz Mir & Mohammad Ahsan
Chisthi
In Security front, A R Jayakrishnan & V.Vasanthi have performed an “Empirical Survey on Advances of Network Forensics in the
Emerging Networks”
This issue also contains reports of CSI Young IT Professional (YITP) Awards 2017 National Round Reports, Book Review and CSI
2017 convention notifications, CSI activity reports from chapters & student branches and calendar of events
We are thankful to entire ExecCom for their continuous support in bringing this issue successfully.
We wish to express our sincere gratitude to the CSI publications committee, editorial board, authors and reviewers for their
contributions and support to this issue.
We look forward to receive constructive feedback and suggestions from our esteemed members and readers at
csic@csi-india.org.
www.csi-india.org
4
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
Computer Society of India
TM
http://www.csi-india.org
Mr. Sanjay Mohapatra Shri.gautam Mahapatra Prof. A. K. Nayak Mr. Manas Ranjan Pattnaik Dr Anirban Basu
President Vice President Hon. Secretary Hon. Treasurer Immd. Past President
President’s Message
From : President, Computer Society of India
Date : 01 November, 2017
Email : president@csi-india.org / Cell : (91) 9861010656
5
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
COvER STORY CSI HIStory SerIeS
1. Introduction the other hand have got the inherent in T, as measured by P, improves with
“People worry that computers ability to remember the information for experience E”. Learning is used when a
will get too smart and take over
the world, but the real problem Machine Learning
is that they’re too stupid and
they’ve already taken over the
world.” -Pedro Domingos
Since the time humans landed their
feet on the earth, they have been always
trying to improve their life in one or the Suppervised Unsuppervised Reinforcement
other way around. Counting from the Machine Learning Machine Learning Learning
Active Learning Active Learning
earlier discoveries of the fire, clothing,
food, houses etc., the human civilization Fig 1: Machine learning (Ml) types
was always in effort to through light on
new innovative ideas which will make pattern exists in the given data which we
billions and billions of years and could
their lives comfortable and sustainable. can’t pin down manually. It is because
also perform any hard computational
In this phase of continues development of the Machine Learning that the
task in milliseconds. This made them
humanity has seen a revolution in present century has been witness to the
a perfect candidate to make them
industrial sector in the 18th century landmark discoveries like Autonomous
learn so that they can automatically
when they discovered the mechanical Helicopter, Handwriting Recognition,
perform the tasks which human brain
engine which later on took many shapes Natural Language Processing (NLP),
was lacking, thus outputting the most
and eased humanity in capturing the Computer Vision, Speech Recognition,
debatable topic of machine Learning
light year distances in few units of Recommendation Systems, Decision
(ML), nowadays.
time. This phase was the dramatic shift Support Systems (DSS), email filtering,
in which the muscular energy of the 2. Machine learning
Machine Learning (ML), a term detection of network intruders or
living beings were transformed into the malicious insiders working towards
machines which are doing many times coined by Arthur Samuel coined in 1959
at IBMisabranchof Artificial Intelligence a data breach, optical character
the amount of work the humans could recognition etc. Machine Learning is
do in very less amount of time. Be it the in which machine is trained so as to
impart it the ability to automatically at the root of the tree and has lots of
automobile engines, aero planes, ships branches and sub branches. Broadly
and other types of machines commonly learn and improve from the experience
without being explicitly programmed. speaking, this fantastic branch of
used in day to day life. From the time innovation is divided into following
man has landed in to the ocean of Its focus lies in the development of the
intelligent programs that can access a categories:
Information Technology sector, a new 1. Supervised Machine Learning
revolution has stepped in the human particular amount of the data (training
data) and is then used to automatically 2. Unsupervised Machine Learning
history and a rigorous effort is been 3. Reinforcement Learning
applied to impart the Intelligence inside work on the new data (test data)
which it has never met with. Machine 4. Active Learning
the hearts of the same machines. This 5. Online Learning
continues evolving effort has given rise Learning is a broad multi-disciplinary
to what is commonly known as Artificial filed which has its roots in Statistics, 1) Supervised Machine Learning:
Intelligence (AI). Machine Learning Algebra, Data Mining, Data Analytics This is the learning [2] under
(ML) being at the core of Artificial etc., which makes it difficult to come up a supervision that is why it is
Intelligence (AI) is the thrust and sexiest with a unique definition of it. According also known as learning from a
research area in the 21st century. Since to Tom M. Mitchell’s [1] definition of Teacher. Here the input data with
the human brain can’t remember the Machine Learning (ML) which defines its corresponding desired output is
information for large periods of time it as:, “ A computer program is said to provided to the computer program
and is computationally hard for them learn from experience E with respect to for the purpose of making it learn.
to perform any work on a large amount some class of tasks T and performance Dataset {(x1, y1), (x2, y2)….(xn, yn)} is
of data. Computers (Machines) on measure P if its performance at tasks inputted to the program and the
www.csi-india.org
6
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
COvER STORY
Classification Regression
7
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
COvER STORY
Supervised learning
condition is satisfied.
Monte Carlo Methods Online learning: recursive
ii(c) Gaussian Mixture Model: Each least squares
mixture component represents a Direct Policy Search
unique cluster specified by:{πk, μk,
Stochastic gradient descent
Online Ml
σk}, where ‘πk’ is the data inputted,
Temporal difference
‘μk’ is its mean and ‘σk’ is the
Methods
corresponding variance. Incremental stochastic
gradient descent
Singular Value
K-Means
Decomposition (SVD) Progressive learning
Hierarchical Clustering
etc. Online convex optimisation
Gaussian Mixture Models Fig. 7: Reinforcement Ml Approaches
(GMM) Follow the leader (FTL)
Singular Value Balance exploration and Below is a list of the machine learning
Decomposition (SVD) exploitation tools:
3.1) Some open Source tools/
etc. Query by committee
Software’s
Weka, CNTK, KNIME, RapidMiner,
Expected mode change Deeplearning4j, R, Mahout, H2O, GNU
Fig. 6 : Unsupervised Ml Approaches
Octave, MOA (Massive Online Analysis),
Exponentiated Gradient Tanagra, Orange, Python, Shogun,
iii) Reinforcement Learning: In it a Exploration for Active TensorFlow, Torch etc.
computer program [4] is given Learning
3.2) Some Proprietary software
access to a dynamic environment
MATLAB, Neural Designer,
in for performing a certain goal Fig. 8 : Active Ml Approaches
Mathematica, Google Prediction API,
(such as playing a game against
Oracle Data Mining, NeuroSolutions,
an opponent or driving a vehicle). v) Online Learning: Online machine Amazon Machine Learning,
Feedback in terms of rewards and learning [6] is a method of machine Microsoft Azure Machine Learning,
punishments is provided to the learning in which sequential order STATISTICA Data Miner, Splunk, SAS
program as it navigates its problem of data availability is followed and is Enterprise Miner etc.
www.csi-india.org
8
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
COvER STORY
Dr. Rashid Ali, Associate Professor at department of computer engineering, Zakir Hussain College of Engineering &
Technology (ZHCET), Aligarh Muslim University Aligarh India. Dr. Rashid Ali is a senior IEEE member in addition of having life
time membership of Computer Society of India. His interests are AI, Web Mining, and Soft Computing etc.
9
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
TEChNICAl TRENDS
www.csi-india.org
10
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
TEChNICAl TRENDS
punishment for the process of learning. LSTM. It is very useful for time-series learning techniques are CNN, RNN,
In this type of learning, the objective is data. LSTM, etc-. Although deep learning
to maximize the reward and minimize Applications of Deep learning techniques give far better results than
the punishment. Some of the broad application the shallow traditional machine learning
Emergence of Deep learning areas of the deep learning techniques algorithms, there are some issues
Deep learning has emerged as the are mentioned below. associated with them like: the need for
hottest area of Machine learning [8-11], huge amount of data for training, need
Medical image classification.
which is based on a group of algorithms for expensive hardware resources and
Pattern Recognition the requirement for very high running
in which high level abstractions of
the data are modeled by using deep Robot trajectory generation time. Despite these limitations, deep
graph having various processing learning algorithms are very useful and
Automatic Game Playing. are being widely used for solving various
layers and multiple non-linear and
linear transformations. Deep learning Patient monitoring in ICUs and problems related to different fields.
promises to replace hand-engineered their mortality prediction. References
features with feature extraction Automatic photograph description [1] Karpathy and L. Fei-Fei, Deep visual-
techniques that are hierarchical, semantic alignments for generating
unsupervised or semi-supervised [1]. Feature extraction image descriptions,” in Proceedings
of the IEEE Conference on Computer
In a deep neural network, there Intrusion detection
Vision and Pattern Recognition, pp.
are multiple hidden units between input
Prediction in Finance 3128-3137, 2015.
and output layers. With the advent of [2] Samuel, Arthur L. “Some studies in
big-data and powerful computational Autonomous driving of vehicles machine learning using the game of
resources, the use of deep learning Geological data analysis checkers. II—recent progress.” IBM
has become more widespread as Journal of research and development
the performance of deep learning Logistics 11.6 (1967): 601-617.
algorithms increases with the amount [3] Krizhevsky, I. Sutskever, and G. E.
Speech processing
Hinton, “Imagenet classification with
of data that is available for training,
Image Caption Generation. deep convolutional neural networks,”
and they also require tremendous in Advances in neural information
computational power [7]. Handwritten digits and character processing systems, pp. 1097-1105,
The popular deep learning based recognition. 2012.
algorithms are as follows: Natural language processing. [4] H. Lee, P. Pham, Y. Largman, and A. Y.
Ng, “Unsupervised feature learning for
• Convolutional Neural Network
audio classification using convolutional
(CNN) Challenges in Deep learning
deep belief networks,” in Advances in
CNN is a variant of the feed-forward Requires tremendous amount of
neural information processing systems,
network that involves various layers data for proper training. pp. 1096-1104, 2009.
and deeply connected architecture [3]. Lack of generic intelligence, most [5] Y. Zheng, Q. Liu, E. Chen, Y. Ge, and J. L.
CNNs are trained with a modified form of the deep learning models work Zhao, “Time series classification using
of the back-propagation algorithm. They multi-channels deep convolutional
for the specific purpose only.
are capable of recognizing patterns with neural networks,” in International
a lot of variability and hence are widely Requires too many computational Conference on Web-Age Information
resources (like GPUs) Management, pp. 298-310, Springer,
used for this purpose. 2014.
• Recurrent Neural Network (RNN) Running time is very high varying [6] Yu, Dong, and Li Deng. “Deep learning
RNN is a special type of Artificial from hours to days. and its applications to signal and
Neural Network (ANN). It has directed information processing [exploratory
Lack of flexibility.
dsp].” IEEE Signal Processing Magazine
cycles between connections. The
28.1 (2011): 145-154.
dynamic temporal behavior is exhibited Conclusion
[7] Sharma A, Shukla A, Tiwari R, Mishra
by the internal state of the network. Machine learning algorithms have A. Mortality Prediction of ICU patients
Unlike ANN, arbitrary sequences can been playing a pivotal role for decades using Machine Leaning: A survey.
be processed by using the internal in almost every field like Finance, InProceedings of the International
state of RNN. There is a time-varying Weather forecasting, Medical science, Conference on Compute and Data
real-valued activation in every unit Engineering optimization problems, Analysis 2017 May 19 (pp. 49-53). ACM.
and modifiable real-valued weight in Software cost prediction, Pattern 10.1145/3093241.3093267
each connection. The Long short term matching etc-. With the improvement [8] Poria, Soujanya, Erik Cambria,
and Alexander Gelbukh. “Aspect
memory (LSTM) is an RNN based in hardware technology and availability
extraction for opinion mining with a
deep learning system that overcomes of huge amount of training data, deep deep convolutional neural network.”
the vanishing gradient problem of learning techniques have emerged as Knowledge-Based Systems, 108 (2016):
traditional RNN. The recurrent gates the most important machine learning 42-49.
called forget gates are augmented in algorithms. Some of the popular deep [9] Polson, Nicholas G., and Vadim O.
9
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
TEChNICAl TRENDS
Sokolov. “Deep learning for short-term [10] Affonso, Carlos, et al. “Deep learning [11] Evermann, Joerg, Jana-Rebecca Rehse,
traffic flow prediction.” Transportation for biological image classification.” and Peter Fettke. “Predicting process
Research Part C: Emerging Expert Systems with Applications 85 behaviour using deep learning.”
Technologies 79 (2017): 1-17. (2017): 114-122. Decision Support Systems (2017).
Prof. Anupam Shukla (Life Membership No. 01099955) is a Professor in the Department of Information and
Communication Technology (ICT) at ABV-Indian Institute of Information Technology and Management (ABV-
IIITM), Gwalior. He has 29 years of administrative, research, and teaching experience. He has been awarded
“Distinguished Professor” by Computer Society of India, Mumbai, 2017,“Dewang Mehta National Education
Award” for best Professor, 2016, ‘Prof. Rais Ahmed Memorial Award, Acoustical Society of India’ in 2015 and
has received many other awards and honors. He is the author of three patents, three books, published by
international publishers such as CRC Press, USA & Springer-Verlag, Berlin, 176 peer-reviewed publications,
editor of three books published by IGI Global Press, USA, and mentor of 18 doctorates and 116 postgraduate
theses. He is also an editorial board member and a reviewer of various international journals of repute.
9
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
TEChNICAl TRENDS
able to see recommendations for cat- processing and automation, as bots process.
related products. In the coming year, increasingly take on tasks for IT and In contrast, deep learning allows
e-commerce sites will be able to use business processes. us to feed data into an artificial neural
more buying trends and customer data Machine learning and Media: network—a computer system modeled
to provide nuanced recommendations Machine learning is being applied after the human brain—and use
that will accurately reflect products you in the media in a number of ways. One algorithms to help the computer learn
might like to buy. area that has seen huge growth is autonomously.
While online retail is already around the personalisation of content – For example, in 2012, a team at
experiencing the early stages of the analysis of data to make conclusions Google fed images from 10 million
machine learning deployment, one and predictions. YouTube videos into an artificial neural
of the most exciting things is the Imagine news articles that network. The system identified distinct
application of this technology in the write themselves. Envision bots that objects within the images, such as cats
physical store environment. identify fake news before it’s widely (apparently there are tons of cat videos
Retailers will be able to analyse disseminated. on YouTube).
customers as they walk in, and we These things will be possible Why was this such a big deal?
will start to see this analysis used because of deep learning, in which Because no one told the computer what
to help the customer find the right computers learn human-behavior a cat actually looks like. It learned on its
products and appropriate offers. With without being explicitly programmed. own.
the incorporation of video analytics, Prior to deep learning, computers The opportunities to leverage this
retailers will be able to analyse which had to be programmed to exhibit human technology within the media industry
products people are looking at, and even behavior. will be enormous. As publishers are
where they are looking on the product – For example, if you wanted a squeezed for ad dollars and face the
whether that’s the price, the features or computer to learn how to write a news duopoly that is Facebook and Google,
the picture on the box. article, you’d have to figure out the AI/Machine Learning will help them
By considering this data against behaviors of a journalist, and manually stay competitive in an era of dominant
customer purchases, retailers will be input those behaviors into the computer. social platforms.
able to make the best recommendations This was a painfully time-consuming To that end, here are a few
for other products that the customer
may want to consider.
Developments in technology
In order to support industries in
transformations, the big developmental
shift we will see in machine learning is
one of hardware upgrades rather than
software.
In order to support the speed of
insights that machine learning can
offer, machine learning processing is
increasingly moving from the cloud to
edge computing where time-sensitive
information can be processed as close
as possible to its origin.
Alongside this, we are seeing
increasing investment in multi-core
technologies and parallel computing
that can boost this speed further. 2017
is the year that hardware begins to
catch up with software in the wider
deployment of machine learning
technology e.g. enhancements in
GPU technologies coupled with hybrid
systems like CPU+FPGA.
Machine learning is beginning to
affect us both at work and at home,
and the possibilities for industries are
truly transformative. Enterprises will
soon find machine learning at the heart
of decision making in core business
www.csi-india.org
14
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
TEChNICAl TRENDS
applications of AI/Machine Learning serve up content to fit your mood. distribution strategy.
that media companies should consider. Sad? Here’s a ‘feel good’ movie. This reality, coupled with the fact
Automation in the newsroom Energized? Check out this action flick. that many publishers rely on these
This is all about making work more Silly? Maybe you’ll enjoy this comedy. platforms for over 40% of their traffic,
efficient.A computer system will be able Recommendations across content creates a problem in legitimate need of
to identify the contents of an image and types a solution.
write the caption. The opportunity to enhance Content management systems like
In fact, a recent study by AI recommendations extends beyond WordPress VIP and Drupal are fantastic,
researchers shows that humans prefer emotionally intelligent software. If but what if they could publish content
computer-generated captions 25% of you’ve been around the industry, you’ve across multiple platforms, and predict
the time they’re displayed. heard time spent being referred to as the when and where (i.e. what platform) to
The technology isn’t perfect, but new “currency” of advertising. publish in order to maximize referral
as its accuracy continues to improve, Ad buyers want to know how much traffic?
survey results will increasingly favor time people spend on your content, What if they could predict virality?
computer-generated outputs. what percentage of video ads they AI will make these things possible.
Similarly, AI can’t write nuanced, complete—that sort of thing. Cultivating a smarter workforce
eloquent news articles yet, but it’s getting One way to maximize time spent AI can also be leveraged to build a
close. For example, the Associated Press would be to suggest content across more knowledgeable workforce.
(AP) is already leveraging deep learning multiple formats. For example, Fortune Communications teams are
to automate news articles that have Magazine could recommend its Most commonly bogged down by the manual
structured data, such as corporate Powerful Women podcast series to users process of discovering and sharing
earnings reports and baseball game who read articles about women CEOs news with their employees. The ability
recaps. on Fortune.com. to share the right information at
Ultimately, automation will enable AI could discover similarities the right time, thus enabling better
media companies to shift resources to between text, video, and audio assets, business decisions, can be a difficult
higher value initiatives, and that will be and guide users through content that undertaking.
good for both consumers and editorial meets their interests across different It doesn’t have to be this way,
teams. formats. though. AI will be able to automate
Computer-Generated Earnings It’s something to consider as the this process and predict what type of
Report, Associated Press industry shifts to “video first,” and news and information will be most
Publishers that detect emotion experiences continued buzz in audio valuable to your employees at any given
We’ve known for some time that and podcasting. time—whether you’re a team of 50 or
technology can be cognitively intelligent. Smarter content management 50,000.
However, Affectiva—an AI company AI will improve our ability to We believe that information is only
born out of MIT’s Media Lab—is helping recommend content, but what about as valuable as the ability to access,
it become emotionally intelligent, too. our ability to distribute it? understand, and share it at scale, and
Powered by emotion recognition With numerous platforms to find we’re excited about using AI to make
software, a streaming service like audience at scale—including Facebook, that easier for media companies, and
Netflix could analyze the look on your YouTube, Twitter, and Snapchat—it can ultimately, the world at-large.
face to understand your feelings and be difficult to determine the optimal
15
C S I C o mm u n I C a t I o n S | noVEmBER 2017
R E S E A R C h FRONT
The existing challenges of theoretical computer science and computing systems were documented in
the order of importance. The issues were critically discussed and gaps in the research were portrayed.
The need for further research is emphasized. These problems are classified under polynomial, cognitive
science, bio-informatics, bio-medicine, application development and other new technologies.
Keywords: Theoretical computer science, computing systems, polynomial, cognitive science, bio-informatics, bio-medicine.
that is either it may be solved by best polynomial time algorithm is a big setups. But it is still unknown which
algorithms in a Polynomial (P) time challenge till date. does in optimal time.
or Non-deterministic Polynomial (NP) 3.5 Fourier transform 3.9 Big-data applications and
time [13, 7]. It is only a question of A Fast Fourier Transform Analysis
whether it is solvable in a deterministic calculation registers the Discrete The system should able to
or non-deterministic polynomial time Fourier change of a grouping, or its quickly analyze and process the semi
and resources. As of now the non- reverse. Fourier Transform changes structured and unstructured data using
deterministic polynomial (NP) problems over a signal domain from its area to machine learning[7] and patterning is
are classified as either complete or hard a frequency domain in the recurrence yet another challenge in the present era
problems. In case of complete problem space [17]. A FFT quickly registers such of computing.
the solutions are possible and in the changes by factorizing the DFT network
case of hard problems the solutions are 3.10 Artificial intelligence and robotics
into a result of inadequate elements. It is to make a computer to become
possible only by converting the problem Subsequently, it figures out how to
in to a complete problem by means intelligent one to perform efficient
diminish the many-sided quality of tasks, to make effective decisions like
of approximation or constrains. The registering the DFT, which in the event
computing world should find suitable humans. Self-driving cars and swarms
that one essentially applies the meaning of search-and-rescue robots are a
solutions for this. of DFT. Fast Fourier transforms are used good illustration [7]. The system needs
3.2 Cryptography for many applications in engineering some intelligence (common sense) to
A public key encryption method and science. Finding less complex and do the works and things automatically.
is used as a method of assuring efficient method is a big challenge till Designing such system is a challenging
the confidentiality, authenticity and today. one at present.
non-reproducibility of electronic 3.6 Tree rotation
communications [7]. It needs a private 3.11 Systems Biology
In discrete science, tree turn
key to decrypt the messages. Anybody In understanding modeling
is an operation on a parallel tree.
knows the private key can decrypt interactions of multiple systems in a
Progressions are made in the structure
messages sent over the public network living organism [7], including immune
without meddling with the request of
and this is a big challenge in the security systems and cancer development, to
the components [18]. A tree turn moves
world and it needs alternate solutions develop the suitable treatment therapy
one hub up in the tree and one hub down
to overcome this problem. is another challenge.
and it is utilized to change the state of
3.3 Integer factorization the tree, and specifically to reduce its 3.12 Computational Biophysics
In number theory, whole number tallness by moving smaller sub-trees The modeling and understanding
factorization is the disintegration of down and bigger sub-trees up, bringing mechanical, electrical, and molecular-
a composite number into a result of about enhanced execution of many tree level interactions inside an organism
littler whole numbers. In the event that operations. There exists an irregularity [7] is another big challenge for the
these whole numbers are additionally in various depictions with regards to the computer scientists.
limited to numbers, the procedure is meaning of the heading of turns; some 3.13 Computational Cognitive Science
called prime factorization [15]. When say that the course of revolution mirrors There is a very large gap between
the numbers are large, no efficient, the bearing that a hub is moving upon what is known about the understanding
non-quantum integer factorization pivot while others say that the bearing of brain structure and the functional
algorithm is known. So far it has not of revolution reflects which sub-tree capabilities of a living brain; closing
been demonstrated that no proficient is turning. It is another big issue for this gap is one of the big challenges in
algorithms exists; finding an efficient theoretical computer scientist. modern science and engineering [21].
algorithm for this problem is a big 3.7 Multiplication algorithm DNA analysis and genetics have also
challenge, till this time. A multiplication algorithm is an become computer-based in the last
3.4 Clustered Planner algorithm to multiply two numbers [16]. twenty years. Development of artificial
The clustering can be depicted Depending on the size of the numbers, brain neural system in understanding
combinatorially by a gathering of different algorithms are in use; efficient the nature is the big challenge for
subsets of the vertices with the end goal multiplication algorithms have existed computer scientist.
that for every two subsets, either both since the advent of the decimal system. 3.14 Computational neurobiology
are disjoint or one is contained in the But, still much better algorithms are It is another area of research to
other. It is not required that the grouping needed to reduce the number of basic understand how organisms process
is maximal [14] nor that each vertex has operations. incoming information and react to it,
a place with a bunch and it is obscure 3.8 Matrix multiplication algorithm control their bodies, store information,
whether it is conceivable to develop Many different algorithms do exist and think [7]. The existing connectionist
grouped planar drawings in polynomial for matrix multiplication [20]. They are neural models are not fully complying
time. There are many cases which have performed in different hardware setups with the requirements. It is another
polynomial time algorithms. Finding a like parallel, distributed and standalone modern research challenge for
23
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
R E S EA R Ch FRONT
computer scientists. Any multimedia-data analysis without damage. Such an electronic charge
3.15 Computer-assisted automated considering semantics will be a futile signaling route should help restore
education exercise. It is another challenge in the ordinary reminiscence capabilities to an
It essential to design a system future generation multimedia. impaired brain.
to teach a lesson spontaneously [11]. 3.20 Computerized Artificial Limbs and 3.23 Semantic Web
Cheat-proof automated support for Components The semantic net [8] is an extension
exams and testing, essay grading, Of late even extra ambitious of the contemporary net in which facts
generation of multiple-choice envisioning programs are underway are given properly-described, which
questions. Support for learning specific for systems to control Artificial Limbs. means, enabling computer systems and
skills, such as programming by giving Engineers envision automatic implants those to work in cooperation. Gap exists
immediate feedback and correction of capable of receiving the signals from between automated processing and
mistakes and giving suitable example hundreds of the brain’s nerve cells accessing of information in the present
narration are the challenging one in the and then wirelessly transmitting that web setup. The present challenges are
present era of computing. statistics to an interface tool that might (i) the availability of content, (ii) ontology
3.16 Automated Information decode the mind’s intentions [1]. The availability, development and evolution,
Processing Centers interface could then ship indicators to (iii) scalability, (iv) Multi-lingualism,
Automated collection, storing, an Artificial Limb, or maybe at once to (v) visualization to reduce information
indexing and retrieval are major issues nerves and muscular tissues, giving overload, and (vi) Stability of Semantic
[7] in the present days. Development of guidelines for imposing the preferred Web languages. If these things are
such systems will enable the designers actions. This could help the physically solved then the users will see a different
to handle huge set of unstructured data handicapped people to have better and kind of Internet tomorrow.
generated by the humans in different easy movements.
3.24 Advanced Technologies for
forms. 3.21 Automated Brain intension Hardware
3.17 Natural-Language Processing Identification Development of optical and
The system should understand Some brain studies have explored, quantum computing or optical
the human-generated documents and with some achievement, implants that computing [2, 3] hardware technology
should be able to communicate with could literally study the thoughts of will enable us to develop the three-
the humans in a normal manner [4]. immobilized sufferers and signal an dimensional circuits and chips. Even
This needs syntax, semantic, pragmatic external computer [1], giving human though the physicists are involved in
level of conversation and dialogs. This beings who are not able to talk a way that, the computer scientist has also
will also solve many other computer to communicate with the outside world. little things to do with this development.
interaction issues. Design of solutions This can have a substantial opportunity It will have a high-impact in increasing
for such problems is a greater. to have exclusive applications. the processing power.
3.18 Human-computer interaction 3.22 Brain Damage Recovery System 3.25 High-end Communication Devices
The current generation systems are Brain is the probably most Modeling and the usage of new
not able to understand tacit knowledge complicated system which has even styles of digital switches (Memristors,
available with the user. Moreover the greater impact on human health. devices using carbon nano-tubes,
user interaction is restricted with the The use of new AI insights can be etc), quantum communication [22,
keyboard and few selective devices. used for repairing broken brains [1]. 7] and improvement of high-stop
But, the future generation system Damage from injury or disease to the sensing devices to understand diverse
should understand the human mind hippocampus, a brain shape essential communications occurring around the
states such as emotion, intent[5], social for gaining knowledge of and memory device is the predominant challenge for
interactions and spontaneously give the can disrupt the proper electric signaling electronic scientist.
suitable answer on behalf of the user among nerve cells; this is needed for
as well as do the tasks. Design of such 3.26 Advanced Networking
forming and recalling recollections with
system is a challenging one. Ubiquitous networking by giving the
understanding of the right signaling
low cost service [7] to access multiple
3.19 Multimedia styles in wholesome brains, engineers
services is another important issue in
In the design of video or audio have begun to layout computer chips
the communication world.
or multi-media data the system is that mimic the brain’s very own verbal
not able to understand any semantic exchange abilities. Such chips may be 3.27 Space Communication and
structure associated (scene analysis, useful in cases where healthy brain Networking
comprehendingmovement, synthesizing tissues is starved for information due Days are not for behind for human
realistic multimedia) with it [7]. Most of to the barrier imposed via damaged to travel to the other planets. It is also
the time the designer is bothered about tissue in principle; indicators from essential to develop a new network
the quality of display data, rather than the healthy tissue can be recorded system for space communication [7].
semantic structure. At present people by an implantable chip, which might Development of such a network is
are doing it with the explicit annotation. then generate new signals to pass the another challenge.
www.csi-india.org
18
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
R E S EA R Ch FRONT
3.28 Automated programming the benefits and side consequences of solutions. The appropriate researchers
Environments capability treatments or treatments. should take-up the research on these
Complete Automated program “reverse-engineering” the mind, to issues for future computing system.
generation [12] is only a partial success decide how it plays its magic, should References:
in the age of programming. The provide the twin benefits of supporting [1] Grand Challenges For Engineering,
next generation programming must treat sicknesses at the same time as National Academy of Engineering of
support the automated programming, imparting clues for brand new methods the National Academics, http://www.
compilation, and debugging and system to computerized Artificial Intelligence. engineeringchallenges.org
development. Also, automated program Advanced computer intelligence, in flip, [2] Richard P. Feynman, Simulating
Physics with Computers, International
language conversion (converting the should allow computerized analysis and
Journal of Theoretical Physics, VoL 21,
code from one language to another) is prescriptions for remedy. Automatic Nos. 6/7, 1982.
another problem. It is the big deal for catalogs of fitness data should beautify [3] Nolte, D.D., Mind at Light Speed: A New
computer scientist. the clinical device’s ability to tune the Kind of Intelligence, ISBN 978-0-7432-
3.29 Internet Security System unfolding of sickness and analyze the 0501-6, 2001.
The security system development comparative effectiveness of various [4] Bates, M, Models of natural language
procedures to prevention and therapy. understanding, Proceedings of the
is another challenge in the Internet National Academy of Sciences of the
[23]. Even though security is provided at The engineering demanding situations
United States of America. 92 (22): 9977–
different levels the creation of trusted for enabling drug discovery replicate
9982, 1995.
secured environment in the public the ones needed to permit customized [5] https://www.interaction-design.org/
network is still a major issue. medicine: improvement of greater literature/book/the-encyclopedia-of-
effective tools and techniques for human-computer-interaction-2nd-ed/
3.30 Online Electronic Voting
speedy evaluation and prognosis in [6] Computing Research Association http://
All over the world big democracies order that a variety of medicine can cra.org/]
are moving towards electronic voting be fast screened and right remedies [7] 13 Of 2015’s Hottest Topics In Computer
system. Development of trusted state- may be promptly carried out. Modern Science Research - Forbes,2015 https://
of-art online electronic voting system capsules are frequently prescribed
www.forbes.com
[10] with foolproof security is a big [8] Jorge Cardoso, “The Semantic Web
incorrectly or unnecessarily, promoting Vision: Where Are We?”, IEEE Intelligent
challenge. the development of resistance without Systems, vol. 22, no. , pp. 84-88,
3.31 Automated Software Verification actual clinical benefits. Quicker, Extra September/October 2007, doi:10.1109/
and theorem proving precise diagnoses may additionally MIS.2007.97
Software verification in the dynamic lead to greater targeted and effective [9] http://www.indianspacestation.com/
environment [19] is another challenge therapies. Antibiotics that attack a huge research/general/575-challenges-in-
for the software developers. The logical deep-space-communication
range of bacteria have usually been
[10] https://www.scientificamerican.com/
entailment and formal reasoning is the sought, becausedoctorscouldn’tusually article/pogue-the-challenges-of-
another challenge in the computing make certain of the ideal bacterium digital-voting/
system. This system development inflicting an infection. Units which can [11] Wang Tiantian, et. al., AutoLEP: An
should enable us to solve the theorem determine the real wrongdoer right Automated Learning and Examination
proving and diagnostics system. away may want to cause using greater System for Programming and its
narrowly centered tablets, reducing the Application in Programming Course,
3.32 Automatic Personalized Medicine
risk of selling resistance. Developing First International Workshop on
System Education Technology and Computer
One goal of biomedical engineering organism-specific antibiotics should Science, 2009. ETCS ‘09,7-8 March
these days is fulfilling the promise of come to be one of the century’s most 2009, ISBN: 978-0-7695-3557-9,DOI:
personalized medicine [1]. Medical essential engineering challenges. 10.1109/ETCS.2009.18.
doctors have long identified that people 4. Conclusion [12] Alan W. Biermann, Automatic
vary in their susceptibility to ailment In general the engineers play vital programming : A tutorial on formal
and their reaction to treatments, but roles in creating the new products and methodologies, Journal of Symbolic
Computation, Volume 1, Issue 2, June
clinical technologies have generally systems in diverse fileds. The computer 1985, Pages 119-142.
been presented as “one length fits scientist is not exception for that. All [13] Gerhard J. Woeginger, Open problems
all.” Current cataloging of the human over the world the computer people around exact algorithms, Discrete
genetic endowment, and deeper know- create novel software and systems every Applied Mathematics 156 (2008) 397 –
how of the body’s complement of day. Hence, this article aims to review 405.
proteins and their biochemical inter- the major problems and an issue for the [14] Cortese, Pier Francesco; Di Battista,
actions, provide the prospect of figuring computer engineering scientist about Giuseppe, “Clustered planarity”, Proc.
21st Symp. Computational Geometry
out the specific factors that determine the different difficulties exists today. It
(SCG’05), New York: ACM, pp. 32–34,
illness and well being in any man or surveys a few hot issues and difficulties doi:10.1145/1064092.1064093, 2005.
woman. A critical manner of exploiting that need to understand in the field. A [15] Richard Crandall and Carl Pomerance.
such data would be the improvement of large portion of the issues anticipated Prime Numbers: A Computational
techniques that permit docs to forecast that would locate the fundamental novel Perspective. Springer. ISBN 0-387-
23
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
R E S EA R Ch FRONT
CSI Executive
Committee (ExecCom)
meeting at Nashik on
7th October, 2017
Dr. S S Agrawal
Chief Editor
www.csi-india.org
20
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
R E S EA R Ch FRONT
why Fuzzy Based learning is Table 1: Comparison between Traditional logic and Fuzzy logic
Important
Traditional Logic Fuzzy Logic
The real life application gives less
importance to boolean variables. They (x) = 1 if x A μA:x→[0,1]
mainly concentrate on linguistic variable 0 if x A
that have values as words or sentences.
Allows only two binary values : 0 Permitts a range of value between 0 and 1
For example, the area medical field,
and 1 where 0 represent no membership and 1
come across many levels of uncertainty
Where 0 stands for True and 1 for represent complete membership.
as there are different manifestation of a
False
single disease depending upon a patient
and occurrence of a single symptoms Based on models from differential Uses Knowledge generated through rules
in multiple disorders. All the entities equations
related with a disease are described Requires complete set of data Concentrates on incomplete and fuzzy data
using linguistic words and will have
Linear Non Linear
values in the range 0-1. The traditional
mathematics lies on precisely defined Table 2: Brief history of Fuzzy logic - Important Milestones
points, functions, sets and probability
measures. Here an element x either Year Invention
belongs to a particular set X or it 1965 Fuzzy Sets(Lofti Zadeh,Seminar)
doesn’t. They are purely dependent on 1966 Fuzzy Logic(P.Marinos,Bell Labs)
binary logic. A precise statement loses
its meaning and a meaningful statement 1972 Fuzzy Measure(M.Sugeno,TIT)
loses its precision when complexity is 1974 Fuzzy Logic Control(E.H.Mamdani)
increased. Even though human brain
1980 Control of Cementkiln(F.L.Smidt,Denmatk)
resembles a binary computer based
on exact information containing zeros 1987 Sendai Subway Train Experiment(Hitachi)
and ones, human heart is compared
1988 Stock Trading Expert System(Yamaichi)
with a chemical computer that uses
fuzzy logic for analyzing information 1989 LIFE(Lab for International Fuzzy Engineering)
that can’t be easily defines by zeros 2003 First class on fuzzy logic is held at Clarkson University
and ones. The task of decision making 2005 Studies in gene expression using Fuzzy Logic
has met with many difficulties when 2006- Successful implementation of fuzzy models in control theory, disease
dealing with real world problems. The 2016 prediction,Faurd detection etc
traditional crisp logic is based on binary
reasoning where everything is classified stands for false values and 1’s for true logic.
as Yes (True) or No (False). Fuzzy is values. Fuzzy set is a form of knowledge Basic Elements of a Fuzzy System
described as mathematics of words representation suitable for notions that Fuzzy system (Fig: 1) consist of
and was developed by Lofti.A.Zadeh in cannot be defined precisely, but which following 5 elements
1965. The fuzzy logic provides a work depend upon their contexts. They are an
space for computation with words and extension of crisp sets .A crisp set is a Rule Base
offers a hand in managing uncertainty traditional way where each element is
during the designing of expert systems. allowed with full membership or partial Fuzzification Defuzzification
It has now become an unavoidable part membership. It is denoted as (x) =1
of machine learning as it can handle when x belongs to set A and (x) =0, if
Knowledge Base
imprecise and uncertain situation. x doesn’t belong to A where (x) is the
Fuzzy logic can take value between membership function of x in A. Table
0 and 1 and these values represent 1 represents the difference between Crisp Input Crisp output
degrees of uncertainty and models traditional and fuzzy logic system and
human cognitive decision making. 0’s Table 2 details the brief history of fuzzy Fig. 1: Fuzzy System
23
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
R E S E A R C h FRONT
23
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
R E S E A R C h FRONT
Dr. Sreeja Ashok is currently working as an Assistant Professor in the Department of Computer Science, Amrita School
of Arts and Sciences, Amrita University, Kochi. She has blend experience in industry and academic fields. Her industrial
experience includes Data Analytics, Project Management, Software Development, and Quality Assurance (Wipro and Avenir).
Her research is broadly in the fields of computational biology, developing machine-learning algorithms for modeling
biological and clinical data; has a strong publication record to her credit.
Dr. U Krishna Kumar, a Life Member of CSI, is Director, Amrita School of Arts and Sciences and Dean (Arts,
Media and Commerce) of Amrita Vishwa Vidyapeetham University. He has more than three decades of
experience in teaching and research. Areas of interest include Data Mining, Medical Informatics, Media and
Science Communication. Has published research papers in various national and international journals.
www.csi-india.org
24
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
ARTIClE
Introduction disambiguation. Ambiguity can even much higher, and where such large
Machine Translation (MT), i.e., happen at sentence level as in the corpora is available, there have been
translation of content from one sentence, “I saw the man on the hill attempts to use NMT.
language to another language using the with a telescope”, which has multiple A translation problem can be
help of computers, is a necessity for a meanings depending on where ‘with a construed as figuring out what patterns
country like India. Being a multilingual telescope’ is attached. As MT involves in the source language correspond to
country with 22 official languages two languages, problems like these get what patterns in the target language. For
and only small share of population amplified. The involved languages may a new sentence, these correspondence
speaking English, communication have completely different morphology rules can be used to replace the source
of information is a major challenge. and syntax, i.e., it may happen that, a patterns to the corresponding target
Human translators try to bridge this word in one language has no equivalent patterns to produce a sentence in
information gap, but the inherent word in another language (and so has the target language. In RBMT, these
limitations of manually performing a to translated into multiple words), or patterns are manually identified and
complex knowledge intensive task like may be one language uses different coded into the system. SMT, as the
translation restricts the height one can grammatical structure than the other. name suggests, relies on statistical
reach. As the information technology These are just a few snapshots to techniques to address this problem.
is reaching masses, we will be seeing demonstrate the source of complexity Main components of any SMT system are
more focus on Indian languages. for MT. Translation Model (TM) and Language
Making all these people understand In this paper, we discuss the Model (LM). Translation Model basically
each other at run time, is a task beyond Statistical Machine Translation (SMT) captures the pattern replacement rules
human capabilities. MT systems apart approach to tackle the problem of and is learnt by an SMT system from
from automating and speeding up the translation and how we at C-DAC a bilingual parallel corpus. This is a
task, also offers confidentiality, i.e., you Mumbai have used the same in our MT probabilistic process and consequently
don’t have to expose your content to an system, Anuvad, for Indian languages. for a given pattern comes up more than
unintended (human) user just for the Statistical Machine Translation one target pattern. A language model
sake of translation. The techniques for MT are being (LM) is used to select the right target
MT has been an important field continuously improved and researchers pattern, looking at how sentences are
of research in computer science for have moved from the traditional Rule constructed in the target language.
many decades. Though it’s still work Based MT (RBMT) to Statistical MT Language Model is learnt using a
in progress, quality of translation is (SMT) and recently to Neural MT (NMT/ target language corpus. The language
improving day by day with the emerging DeepMT). Major factors which fostered model scores the sentences generated
techniques. Despite the long gestation this movement were the hope of a more by TM, based on their fluency in the
period, the complexity of natural accurate translation and lesser human target language which is represented
languages has still not allowed us to involvement in creating the knowledge by the aggregate probability of word
solve the problem completely. The structures required for RBMT. Now sequences in that language.
major source of complexity in natural the problem of MT has moved from There are variants of the SMT
language is ambiguity, in many different structural and morphological transfer model. We have used phrase based
forms. One word in a language may of one language sentence into SMT approach in Anuvad. Though
have multiple meanings; for example, another, to transfer of one pattern into SMT can save the effort of manually
word ‘bank’ in the sentence “I lost another. For SMT, the languages are generating transformation rules, going
my wallet at the bank”, may mean considered as patterns and learning to a fully statistical model raises many
that, you lost your wallet at a financial the transfer model from one pattern challenges. In practice, we need a
bank while withdrawing money or you to another became the translation hybrid model, where other knowledge
lost your wallet at a river bank while system. Availability of huge sentence sources are used to make the job of
having bath. This is called word sense aligned parallel corpora accelerated SMT less error prone. Keeping this
ambiguity and sense of such words in the development of machine-learning in mind, along with the use of core
the given sentence needs to be decided based MT systems, paving way for SMT. phrase based SMT, we have developed
using a technique called word sense For NMT, the corpora requirement is and incorporated various techniques to
25
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
ARTIClE
handle complexities involved in MT for Transliteration apart from the core SMT richness; a word takes many different
Indian languages. These are described training and decoding modules. These forms depending on the context it is
in the next section. are the improvements we worked on, as used in. keÀjsiee, keÀjsbies,keÀjesies, keÀ©biee etc. for
Anuvad - An English to Indian mentioned above. These are discussed the word kar (do). By default, these
language SMT system in more detail below. The block diagram words are treated as independent
Development of Anuvad was started shows English as the source language words, and makes the pattern detection
with focus on English to Hindi and and Hindi as the target language. problem harder. Further, even if we
Marathi translation. Further we have know karoonga-kartha hai (keÀ©biee –
tried to extend the approach for other keÀjlee nw) combination, we are unable to
major Indian languages, basically from convert jaoonga (peeTbiee) to jaatha hai
Indo-Aryan and Dravidian language (peelee nw). To alleviate this problem, at
families and were able to achieve some the preprocessing stage we also apply
Fig 2 : Reordering Example
improvements there also. If you like stemming and compound word splitting
to read more details about our work, to handle morphological difference
please refer our publications openly As we know, structure of an English in the source and target languages.
available at http://kbcs.in . sentence is Subject – Verb – Object (SVO), Stemming, splitting and any other
We have developed systems for whereas for those Indian languages we preprocessing, for that matter, are
English to Hindi, Marathi, Punjabi, were looking at, primarily it’s Subject – applied as per the need and nature of
Bengali, Tamil, Gujarati, Telugu, Object – Verb (SOV) and we sometimes languages involved in translation.
Konkani and Malayalam. Size of observe free word order also. For There can be situations when
the parallel corpus available is example, the English sentence ‘Ram some of the words from new sentences,
significantly important in determining Killed Ravan.’ (SVO) can be translated mostly names of entities like person,
the performance of SMT systems, and to Hindi as ‘Raamne Raavanko maaraa.’ place, etc, may not get translated by our
in most cases, large aligned corpus (SVO); translation ‘Raavanko Raamne trained system. Such words are then
is not available for Indian languages. maaraa.’ is also frequently seen. In passed to the transliteration system,
More work in this area is very important the presence of adjectives, phrases, Xlit also developed by C-DAC Mumbai,
to produce good quality translation and sub-ordinate clauses, this re- which essentially does an intelligent
systems in our languages. ordering can mean movement across script conversion. The final output is
An MT system, like any other very many words. Such movements are presented to the user as translation
Machine Learning system, has two hard to capture statistically. To ease this which he can choose to use as it is or
phases, the training phase and testing/ difference of word order, we reorder edit.
usage phase. In the training phase, the the English sentence to Hindi structure Performance of Anuvad
models are created, and these are used in an approximate fashion. After It’s important to know the accuracy
to produce translations in the testing reordering, the above English sentence of a system before relying on it for the
phase. Fig 1 shows block diagram of will become ‘Ram Ravan Killed’. Fig 2 purpose of translations. MT accuracy is
Anuvad System at an abstract level. has a complete example. mostly measured using BLEU (Bilingual
We can see that, Anuvad makes use Another characteristic typical of Evaluation Understudy) score. Many
of Reordering, Stemming, Splitting and many Indian languages is morphological times translations are also evaluated
manually, but are time consuming and
costly.
Though BLEU scores are used
widely, averages over multiple human
scores is the best way to judge accuracy
of system for deployment in the field.
In table 1, we detail the manual scores
of Anuvad for some language pairs.
This evaluation is done by an external
agency (MTIL17) and translations were
manually evaluated by three different
language experts and then averaged. In
manual evaluation, the translations are
scored for adequacy and fluency. Thats
is, this evaluation looks at how much
information from the source sentence
is carried into the target (adequacy) and
how native/fluent the translation is in
the target language. The final score is
Fig. 1 : Anuvad Block Diagram
average of these two scores.
www.csi-india.org
26
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
ARTIClE
27
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
ARTIClE
INTRODUCTION forwarding and all the analysis happens discusses the problem of high latency
Internet of Things (IoT) has recently at the cloud which makes decisions of over 100’s of ms associated with the
emerged as one of the buzzwords in based on current and historical data. cloud.
the IT world. It serves as a catalyst for These decisions are then transported There has been a tremendous
rapidly growing smart networks with the back to the edge of network for actions. increase in the computing power and
deployment of sensors, communication storage capabilities of the personalized
and control infrastructure at a rapid devices (smart phones, IoT gateways).
pace. IoT envisions the concept in Smartphones today are million times
which all the physical objects, generally more powerful than all of NASA’s
referred to as “things” get connected combined computing in 1969. Popular
to each other and the internet for IoT gateway Raspberry pi has a 64 bit
information sharing. IoT goes beyond quad core ARM processor, each of
the classical machine to machine which offers one third of computational
paradigm whereas later only focuses capabilities of Intel xeon processor
on the communication infrastructure core over the cloud [4]. With such
(protocols), IoT envisions not only computing capabilities around us in
communication infrastructure but an form of IoT edge we feel there is an
intelligent network that can be sensed opportunity in exploiting this compute
and programmed using state of art capability & storage power of modern
techniques from machine learning and personal devices. This shift gives rise to
neural networks. It enables new kind Fig 1. Big Data Statistics [11] a new computing paradigm called Edge
of applications ranging from smart computing. This new paradigm will help
homes, smart body implants to self- For the dream of IoT to be in de-centralizing the computing from
driving cars and much more. It enables successful, the enormous data that it cloud towards the edge of IoT. Edge
new kind of applications ranging from generates has to be processed in real computing will complement the cloud
smart homes, smart body implants to time and classified into actionable as more computationally intensive
self-driving cars and much more. These information. Currently cloud is the tasks will be delegated to the cloud for
devices generate huge amounts of data, natural choice for large machine final outcome.
according to IBM 2.5 exabytes (EB) - learning algorithms to run and process why Intelligent Edge?
that’s 2.5 billion gigabytes (GB) - of data data. The presence of huge compute Delegating more powers to the
was generated every day in 2012 [1]. power of cloud coupled with modern edge than we have in the traditional
Estimates suggest that 90% of total data Graphics Processing Units (GPU’s) lend centralized approach requires that
has been produced in last 2 years, and naturally towards processing these some of the computation on the data
current data production output is almost huge amounts of data. generated by IoT sensors to be done
2.5 quintillion bytes per day. Currently However with continuous incoming on edge itself. The reasons for edge
we have almost 20 billion connected data from sensors, cloud being the computing becoming necessary are:
devices and IHS Markit projects 30.7 only analytical engine introduces many Data generation at the edge: most
billion IoT devices by the end of 2020 extra complications. For example. of the data for analytics is produced at
[2]. In order to create a truly smart IoT connection is always required to the the edge of network. Natural and easier
application the massive data that gets cloud, unilateral trust between client way is to process that data at the edge
generated from the sensors needs to be and cloud service. It can also incur loss itself, with the exception of historical
processed and analysed into actionable of privacy by releasing the personal data that lies in the cloud.
information. information to the centralized service Network and energy constraints:
The traditional approach of using like cloud. Security remains the prime the issue of latency becomes
centralized architecture of cloud, concern of cloud computing as the raw unacceptable for some of the mission
wherein the devices (end points in IoT) data generated by the sensors is being critical applications. Edge devices
are only used for data sensing, data send to the cloud servers. Reiter et al [3] are not always connected through
www.csi-india.org
28
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
ARTIClE
low latency network; instead they use edge as computing resource will have but multiple output layers are trained
UMTS and LTE connections. Reiter et an advantage of using cloud as support for each hidden layer. It runs the part
al [3] shows that UMTS connections are infrastructure but puts decision related of network locally and part of it over
subject to large variations of round trip to trust and control back to edge and the cloud. Only those samples can be
times (RTT) of more than 100ms during is well suited for human centered classified locally which are processed
peak traffic hours. computing. with sufficient confidence (above
Transferring 1 bit of data over Machine learning at the Edge threshold). The remaining samples
cellular network requires about 500 Machine learning especially are send to the cloud for further
micro joules (µj) of energy. With the artificial neural networks are the processing. LeCun et al [6] performed
amount of data that is being generated, natural solutions to process such the experiments on MNIST data set
the energy consumption for transferring huge data that gets generated in (fig 4) which is the repository of over
the data will be huge and beyond our IoT environment. It can be used for 70000 images of handwritten digits. The
imagination. classification, object recognition, experiments showed that the neural
natural language processing, speech network with just two layers (i.e one
30 FB recognition etc. currently cloud is the hidden layer) is able to achieve 4.7%
only choice for training and evaluating error rate, i.e. 95.3% of the samples of
deep neural networks due to its power MNIST data set are classified by only one
Data Usage
3.7 EB and scalability. As we have already hidden layer with sufficient confidence.
discussed the short comings using
cloud only solution. Therefore, the
1 PB goal is to distribute the neural network
10 GB
among the local compute power (fig 3)
present in the IoT scenario (devices,
gateways, embedded GPU’s).
2000 2005 2015 2020
29
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
ARTIClE
of cloud on the device (edge) through energy and performance issues. It will Edge and Cloud Platforms.” IEEE
snapdragon 820 System on Chip (SoC). be compliment to the cloud paradigm Internet of Things, May 2017.
Elias et al [7] proposed a big little whereby the ML algorithms will run [5] Kumar, Ashish, Saurabh Goyal, and
Manik Varma. “Resource-efficient
architecture for distributed neural on the small scale devices driving the
Machine Learning in 2 KB RAM for
networks for internet of things. The localised decision making. With the the Internet of Things.” International
neural network is partitioned into big amount of data being generated and IoT Conference on Machine Learning. 2017.
and small (little) networks. The little device population surpassing human [6] LeCun, Yann, et al. “Gradient-
network is housed in the edge device population, the energy requirements based learning applied to document
itself and the big network is put in the highlighted makes it imperative to do recognition.” Proceedings of the
cloud. The aim here is to use the local a lot more with the data at the edge IEEE 86.11 (1998): 2278-2324.
compute power first (little network) itself and sending far less data into the [7] De Coninck, Elias, et al. “Distributed
neural networks for Internet of Things:
before turning up to the cloud. This will network.
the Big-Little approach.” Internet of
drastically save the network, energy and There is a need for investigating the Things. IoT Infrastructures: Second
cost requirements. [7] proposes the use opportunities of distributing the deep International Summit, IoT 360° 2015,
of one vs. all or one vs. one classifiers to neural networks and other machine Rome, Italy, October 27-29, 2015,
speed up the execution of small neural learning algorithms across the edge, Revised Selected Papers, Part II.
network which is distributed among the fog and cloud devices. This seems Springer International Publishing, 2016.
local compute power. the only way by which we can actually [8] Leroux, Sam, et al. “Resource-
Microsoft researchers [5] proposed realise the dream of IoT, making devices constrained classification using
a cascade of neural network
the use of tree based learning truly smart.
layers.” Neural Networks (IJCNN),
procedure ‘Bonsai’ for resource References 2015 International Joint Conference on.
constrained devices which are typical to [1] IBM Annual Report 2013 https://www. IEEE, 2015.
IoT scenario. Bonsai aims at providing ibm.com/annualreport/2013. [9] Monroe, Don. “Neuromorphic
the alternative paradigm where in IoT [2] https://spectrum.ieee.org/tech-talk/ computing gets ready for the (really) big
devices can make decisions locally telecom/internet/popular-internet-of- time.” Communications of the ACM 57.6
without the compulsory connection things-forecast-of-50-billion-devices- (2014): 13-15.
to the cloud. Also sometimes the by-2020-is-outdated [10] David Brooks “Hubweek Symposium
[3] Reiter, Andreas, Bernd Prünster, 09/30, David Brooks: Taking
energy requirements for executing the
and Thomas Zefferer. “Hybrid Mobile Machine Learning to Edge Devices”
instruction may be much lower than Edge Computing: Unleashing the Full 6-october-2016.
the energy required to transmit the data Potential of Edge Computing in Mobile [11] Data Never Sleeps 3.0 https://
thereby extending the battery life. Device Use Cases.” Proceedings of www.domo.com/blog/data -never-
Conclusion the 17th IEEE/ACM International sleeps-3-0/.
Symposium on Cluster, Cloud and Grid [12] MNIST data set http://csc.lsu.
This article outlines the need for
Computing. IEEE Press, 2017. edu/~saikat/n-mnist/.
the computing at the edge to solve the [4] Yogesh Simmhan, “IOT Analytics Across
www.csi-india.org
30
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
S E CU R IT Y C OR N ER
In the modern world, where most of the population is connected to the internet via smart devices,
the surface for committing crimes and being attacked by hackers have been increased drastically.
Number of cybercrimes keep increasing and may ramp up when IoT, M2M, 5g and other new network
technologies become more popular in coming years. The electronic crimes that involve the use of
computer networks are considered the most complex category. After an attack is identified on a
network, there is a necessity for computer forensics to investigate and gather digital evidence to bring
to justice. Network forensics is dealt with the dynamic and volatile information instead of static/stored
data. hence, highly sophisticated techniques are required for instantaneously tracing down criminals
network activities. A honeypot tool can be used to trap intruders and collect essential information on
the crime activities. Classification of network forensics, reviews on emerging network areas, intrusion
and prevention methods, attack detection process, network forensic process, reviews on various
NFATs, survey on network forensic approaches are incorporated in this paper.
Keywords: Cyber Forensics, Network Forensics, Digital Security, Live Forensics Mechanisms, NFAT, Honeypot
1. Introduction
Computer forensic experts take place or have occurred within an analysis shall also be analyzed to
often face difficulties during data information technology system. The compile the study. Questions of network
collection from a network to aid in major components of network forensics security issues and attacks and the
forensic investigation. The crime scene include intrusion detection through investigation mechanisms used in a
constantly changes and as the traditional logging and correlating with the process. network security accident will also be
crimes reduce in number, the cyber Network forensics plays a primary role discussed in the study. Concerns as
crimes incidents are occurring more in the provision of sufficient evidence whether network forensic mechanisms
frequently. To comprehensively solve the to allow the perpetrators of crime to can be used in eliminating network
emerging network problems through be successfully persecuted. Practical security issues and attacks will also be
network forensics, understanding the application of network forensics in considered in the research.
context of forensic investigation and the emerging networks could be present 2. Background
general nature of emerging networks is in areas such as email investigation, The word computer crime was first
the key issue. hacking, insurance companies, fraud used in 1976 by Donn Parker in a book
Network forensics is a scientific detection, drug trafficking, software “crime in computer” [12], [13] that it is
field that deals with the collection, piracy, credit card cloning, electoral law, referred as dealing with unauthorized
recovering and the examinations of discrimination and sexual harassment modification or deletion of data in a
network events for the purposes of [2]. computer system [14]. Nevertheless, FBI
establishing sources of security attacks. This study aims at conducting was established first actual computer
This phenomenon is useful in the a literature survey to ascertain the analysis and response team in 1984
identification of unauthorized access emerging network forensic areas to conduct advanced digital forensic
to computer network systems and is and identify effective architectures investigation of the crime scenes [15].
an investigative tool in case of such for maintaining network security. The It was in 1986 the first complicated
occurrences. According to Alzaabin [1], process for network attacks detection, digital forensic investigation case was
network forensics plays an investigative network forensic process and the executed, chasing a hacker named
role at network level, the issues that essential tools for network forensic Markus Hess [16]. Mr Hess had
33
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
S E CU R IT Y C OR N ER
intruded to the LBL, the Lawrence- criminals behind it. From the existing networked technologies, fast advancing
Berkeley-National-Laboratory. It was network security products and tools, networking technologies and the need
detected and investigated by Mr. Clifford network log data are collected, analyzed to deal with volatile and dynamic live
Stoll. There wasn’t any standard digital for attack classification and investigated data, complicates the efforts to identify,
forensic investigation framework in to trace through the perpetuators. This collect and preserve evidence data in a
place at the time of the incident, so process can bring out deficiencies in timely fashion.
Stoll had to carry out the investigation security products which can be utilized In order to keep up to the pace
on his own. As Stoll’s objective was to guide deployment and improvement with the modern changing face of
discovering the identity of the intruder, of these security tools as well. The scope criminal activities and its growth, It is
he didn’t alter anything in the system of network related incidents should be important for the forensic research
and only collected the possible traces. quickly determined and also be able and practitioner communities to have
He finally managed to discover the to rewind the breach by the forensics an in-depth understanding of the types
identity and location of the attacker by investigator so that they can detect of artefacts that are likely to remain on
tracking the hacker for many months where to look for the potential evidence. network and on networked devices as
using alarms which send notification Network forensic investigator will well as the capability to undertake data
when the attacker was active with the require the same thought process and collection and acquisition in well-paced
cooperation of FBI and Telco Company. skill set as hackers in order to detect and in a forensically sound manner.
The case became a big issue since it why and what has happened and also Network security is not another
was involved academic and individual to identify the motivation for the crime. term for network forensics. Network
bodies in U.S, Germany and military Different networks may be spanned forensics is an extended phase of
bodies [17]. Day by day improvement across multiple geographical zones and network security. Network security
of digital devices makes digital crime various jurisdiction, which demands protects systems against attacks
more complicated than it was in 1986. the use of absolute trusted timestamps whereas network forensics focuses
Our augmented dependency on latest to make sure the integrity and on capturing evidences of the attacks.
networked technologies and the authentication of timestamps for each Network forensics is considered as
prevalent inter-connectivity of systems portion of network evidence ensuring an extension of computer forensics.
used in our networked modern world that all jurisdictions collaborate. The Monitoring is a continuous process.
are potentially be exploited for criminal network data will be available in both However, network forensics involves
purposes (e.g. malware, hacking, real time and off line modes, the former post mortem investigation of the attack
phishing, theft of trade secrets & requiring the ability to pick and analyze and is initiated post crime notification.
intellectual properties etc.). There are data on the fly. The amount of data could It is case specific since each crime
basically two approaches for network be massive due to the increasing size of development is different and the
protection. Defensive Mechanism is used network bandwidth and also it could process is time sensitive.
to defend from intruders by blocking involve various different protocols. A 2.2 Classification
malicious communications on network. protocol could in turn involve multiple Network forensics can be classified
Tools like Firewall, IDS are used by layers of signals. The current available into two types: “Catch-it-as-you-can”
this method. Firewalls control network set of forensics tools may not be able systems, whereby all the packets that
traffic according to the rules set, but has to handle the real-time and huge data are passing a specific traffic point are
many limitations. IDS is primarily a real volume. Various techniques are required captured and analyzed subsequently in
time system for detecting and reporting for instantaneously tracing criminal’s batch mode. This method requires lots
attacks as it happens on the fly, however network activities on computers and for of storage space as it captures volumes
it has no evidence gathering capability. mapping the networks topology. of data. Also, searching and finding
Preventive Mechanism will not block For any cyber-attack, an evidence required information from the stored
the network attack, but tries to prevent trajectory would be left in IDS - intrusion data is a big overhead. “Stop, look and
it by access control or authentication. detection systems, firewalls, proxies, listen” is another network forensics
Reliable and comprehensive network routers and within the network traffic. system that analyzes information in a
security and forensics architecture are Hence, there is an increasing need rudimentary manner in memory and
essential in maintaining security of the for investigators to analyze network only certain information is saved for
emerging networks. traffic, events, logs, netflow and digital future analysis [3]. Fig. 1 depicts the
2.1 Definition device log, in order to discover how an classification of forensics.
Network forensics is a science that attack was carried out. Such activities
monitors and analyzes network traffic, could lead in reconstruction of a
Network Forensics
aiming at detecting malicious network crime and eventually the identification
activities and preserving the trace to of the criminal(s). Rigorous
produce as legal evidence at court. It methodology and set of procedures
deals with capturing, recording and for conducting network forensics and Catch-it-as-you-can Stop, look and listen
analyzing of network traffic in order to investigations are very much required
discover the source of attack and the in place. However, the increasing use of Fig. 1 : Classification of forensics
www.csi-india.org
32
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
S E CU R IT Y C OR N ER
It is often a long and tedious important role in the emerging network traditional model of forensics does
process that requires standard areas such as Machine-to-machine not adequately address the recent IoT
operational procedures for the (M2M), 5G and Internet of Things (IoT). environment [19].
management. In order to come up M2M - The Internet in achieving 3.2 Preliminaries of Network Security
with a standard operating procedure intelligent interactions between and Forensics.
for network forensics in emerging machines having different terminals Intrusion detection and prevention
networks, it is recommended to have uses the Machine-to-Machine networks. systems are used to monitor network
a standard investigation image for This emerging network is composed traffic and activities of the network
system. This image should not be of equipments, back-end systems, system for any malicious activities.
of a bit stream and do not contain transmission links and front-end Intrusion prevention system takes
all the standard applications used. sensors. The front end sensors helps in action by sending an alarm, resetting
When an intrusion incident occurs, the collection and transmission data to connection, dropping malicious packets
the vulnerability of the system should the back end systems that is overhauled or blocking traffic from any offensive
be fixed to prevent any chances of and the back end nodes transmits IP addresses. Intrusion prevention
attacks. All the volatile data should be information to back end control system. System (IPS) is also essential in
acquired through live acquisition before When the M2M networks are attacked, cyclic redundancy check (CRC) errors
the system is switched off during the the terminals it is associated with correction, eliminating extra features
development of the standard procedure becomes affected and the network and network layer options as well as
for network forensics [5]. Additionally, a is eventually paralyzed and cannot unnecessary packet streams [18].
compromised drive should be acquired function. The security issues of M2M Honeypots and Forensics - With
and an image of it is taken. Comparison are attracting many concerns as the the rise of cyber-attacks, Honeypots
of forensic images should be done encounter of several attacks, hence, the have been considered one of the best in
and hash values properly checked to need for an elaborate forensic expertise network crime forensics, warm attack
ascertain if there are any changes in arises. Network security architectures detection and other aspects of active
them [5]. and protocols are evolving to counteract defense methods. A honey pot is a trap
Traditional vs Live - Live forensics the challenges experienced by emerging network that is static and is effective
(forensics on a system that cannot be networks. This evolution is key in the for attackers who are reckless. When
switched off, as in the critical systems) unauthorized access prevention leading the attackers are however aware of
and the attribution root question (linking to security improvement [18]. the existence of the honey pot, their
the criminal activities to the convicts 5G – Even though, the specifications functionality becomes degraded. In
behind it) are examples of issues that of the 5G is still not finalized, but order to increase the functionality and
requires additional research. The the technology is expected to be the persuasiveness of the Honeypots, the
traditional forensics and Live forensics fastest speed as high as 10Gbps. The behaviors of the attackers need to be
have common features, where both of new technology would lead to ultra- collected and stored in a safe place [11].
them are looking for similar artifacts low latency applications, high volume Honeypots are copies of the real
on a system. However, the differentiator data rate applications, network of servers and are often used to simulate
with live response is that the artifacts network applications. Real time threat real service through the coordination
are discovered on a live running system detection and network isolation are of various modules. These modules
against an active adversary. With going to be a big challenge for 5G include data acquisition module,
traditional forensics, images are taken networks. Interoperability and diversity remote storage module, detection
of volatile memory and hard disks before in networks increase attack surface module and implementation module.
being analyzed. Imaging alone can take and motivation of attacks. Forensics Data acquisition module captures
many hours and then the images should of such a superfast network would be and collects the activities of intruders
get processed and indexed to allow for a nightmare for the experts in coming or attackers. The remote storage
keyword searches. Obtaining and then years. [31] module in the other hand backs up the
processing the image could take a day IoT - The development and network system remotely and captures
or longer with large capacity disks. advancement of the Internet and other data to the log servers and keeps
With live response, there won’t be any smart electronic systems have led to the information without any further
scope for imaging or processing that the emergence of computing prototypes modification. Detection module protects
has to occur, everything will be real such the Internet of Things (IoT). The the host and records the invasion
time. This would dramatically improve IoT has been considered as the future process. Implementation module on
the response time in identifying and of Internet works with other emerging the other hand is used in the simulation
quantifying a threat. The quicker the networks such as M2M communication and protection of the host and prevents
threat is identified, the quicker it can be and Radio Frequency Identification attacks from any intruders.
contained and remediated. (RFID). IoT has the primary mandate Surveillance and Vulnerability
3. literature Review of adequately securing data exchange Scanning - During a forensic event,
between real world applications the surveillance and vulnerability
3.1 Emerging Network Forensic and devices. The paradigm of digital
Areas scanning systems are usually not stored
forensics in line of Internet of Things through the SIEM system. Surveillance
Network forensics plays an is challenging and diverse and the
33
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
S E CU R IT Y C OR N ER
& vulnerability systems are potential information for network forensics. and outside network attack detection,
parameters in attacks minimization via Another module that can be data recovery, risk analysis, attack
firewall rule adaptations or alterations. designed is the data analysis layer. It patterns detection, future attacks
The above mentioned preliminaries of analyzes network contents from the prediction and detection of anomalies
network security and forensics helps in content crawling layer. It extracts and in the network system. The main
the detection of all network anomalies displays information that is useful and properties of network forensics analysis
and are useful in the identification of all related to the attackers and finally tools include collection of information
the attackers. After the attackers have helps in the compilation of a report of [6].
been traced by these systems network evidence. Forensics implementation Some of the network forensics
forensics then follows. This process layer is an additional module that analysis tools include but are not limited
experiences challenges such as the loss is significant in the adjustment of to NetIntercept, which collects and
lag of network forensics and to some the evidence collection stability and analyzes bundles of traffic, Iris, which
extent even loss of evidence. Attack flexibility and it modifies the acquisition collects data from the Internet, then
detection needs to be integrated with of information and filters them in order reassembles them and reconstructs
network forensics in order to improve to simulate the login rules [7]. the actual text from the session.
the timeliness of forensics after the During network forensics process, NetDetector is another NFATs that
detection of attackers. after the design and compilation of capture the attack, integrates signature
Attack Detection Process - During the layers in the forensics analysis anomalies and reconstructs the actual
the attack, the network defense system modules, the network forensic analysis text from the session [10]. NetDetector
sends out attack alerts. Such alert needs to finish the collection of data, also supports network interfaces and
information needs to be collected in collection of information, analysis of analyzes report on network traffic.
order to identify the exact location. the collected data and ultimately and Silent Runner is a network forensic tool
Access authority is then sought and most importantly the implementation that primarily focuses on inside threats
the behaviors of the attackers analyzed of the forensics process [8]. A waterfall and analyzes the threats in a three
according to their path and finally model which has been commonly dimension on the network in order to
their operations intercepted and the followed in forensics has various steps monitor all the packets passing through
information of the attackers recorded. – Preparation, Detection, Collection, a specific network. Other network
The main attack detection process Preservation, Examination, Analysis, forensic tools include NetWitness,
includes sending a request to the URL Investigation, Presentation and Incident NetworkMinor, and NetStumbler etc [9].
that has been accessed to request the response. Feedback from steps 3.5 Literature survey evaluation on
collection of data information, recording examination, analysis and presentation Network Forensic approaches
the results of traffic anomalies and the can be used for improvement of network Evidence Graphs for Network
actual suspicious traffic, analysis of the security, tools used etc. Fig. 2 depicts Forensics Analysis [21], is a technique
obtained suspicious traffic and then the process of network forensics. for network forensics analysis which
accessing the relevant static resources. Preparation includes manipulation, effective
The behaviors of the attackers are then
Improvement of Security Tools
frameworks to form a reasonably requires more tools to conduct network reduction and organization), and
complete framework that groups forensic analysis in order to provide post analysis (report and resolution).
all the existing processes into three accurate results in investigation phase. Standard methods of detecting and
stages - preparation, investigation and Two-dimensional evidence collecting evidence doesn’t exist, which
presentation. They are implemented reliability amplification process produces insignificant evidence and
as guidelines in network forensics. The model [24], it consists of sixteen sub- it affects the accuracy of the incident
aim of the framework is to establish phases and they are then grouped in response as well.
guideline of what steps should be to five main phases namely initializing, Digital forensics investigation
followed in a forensic process. However, evidence collection, evidence procedure model [25], it consists of ten
it looks to be difficult in understanding examination or analysis, presentation phases with investigation preparation,
how the Forensics Zachman (FORZA) and case termination. All phases of classifying cybercrime & deciding
[23] depicts a framework that focuses the model are explained in detail by investigation priority, investigating
on the legal rules and participants in identifying the roles of the inspector damaged (victims) digital crime
the organization rather than technical and manager in each phase. The model scene, criminal profiling consultant
procedures. The framework tries to aims to provide answers to common and analysis, tracking suspects,
solve complex problems by integrating cybercrime queries, however it doesn’t investigating injurer digital crime scene,
answers for the queries why (the focus on intention and strategic analysis beckoning suspect, writing criminal
motivation), what (the data attributes), (why and how questions). It has much profiling and reporting. Model presents
who (the people involved), where (the similarity with incident response and block diagram without any technical
location), how (the procedures) and computer forensics. Both presents a details or process to manipulate with
when (the time) questions. Framework common process model for incident all these phases. Main focus was on
also includes eight rules namely case response and computer forensics to the number and the type of the network
leader, legal advisor, system or business improve the investigation phase. The forensics phase rather than how they
owner, security or system architect model includes steps grouped into three works and how they conduct outcomes.
or auditor, digital forensic specialist, main phases consisting of pre analysis Categorization of investigation
digital forensic analyst, digital forensic (detection of incidents, initial response procedure was done [26] to group and
investigator or system administrator and formulation of response strategy), merge the similar processes in five
or operator and legal prosecutor. analysis (live response, data recovery, phases that provide the same outcome.
Framework is human dependent and forensic duplication, harvesting, The phases lists: Phase-1 (preparation),
Table 1: literature survey on Network Forensic approaches
33
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
S E CU R IT Y C OR N ER
Phase-2 (collection & preservation), Notes in Computer Science, vol. 3391, Communications of the ACM, vol. 31,
Phase-3 (analysis & examination), pp.62–71, Jan. 2005. no. 5, pp. 484–497, May 1988
Phase-4 (presentation & reporting) [3] Anchit, Bijalwan, and Wazid, [18] Kun Wang, Miao Du, Yanfei Sun, Alexey
Mohammad, Emmmanuel S.Pilli. Vinel, and Yan Zhang, “Attack Detection
and Phase-5 (publishing the case).
“Forensics Of Random-UDP Flooding and Distributed Forensics in Machine-
Also proposes a mapping process of to-Machine Networks”, IEEE Network •
Attacks”, published in Journal of
digital forensic investigation process November/December 2016
Networks, vol:10, 2015, pp.287-293.
model to eradicate the redundancy of [4] Cato Networks: Global Industry Report, [19] Javeria Ambareen, Pritam Gajkumar
the process involved in the model and Top Networking and Security Challenges Shah and M. Prabhakar, “A Survey
standardize the terms used in achieving in the Enterprise, November 2016 of Security in Internet of Things –
the investigation goal. [5] Changwei, Liu, Anoop Singhal and Importance and Solutions”, Indian
Duminda Wijesekera: A Logic Based Journal of Science and Technology, Vol
4. Conclusion 9(45), December 2016
Network Forensics Model for Evidence
Network forensics is the scientific Analysis. IFIP Int. Conf. Digital [20] Joseph, Jane and Peter, “A Proactive
process that ensures investigation of Forensics, 2015. Approach in Network Forensic
attacks that are performed in network [6] Dhishan, Dhammearatchi. ‘Use Investigation Process” International
or network devices. The significantly of Network Forensic Mechanisms Journal of Computer Applications
surfacing problem in emerging To Formulate Network Security’, Technology and Research Vol 5– Issue
5, pp 304 - 311, 2016
networks is the constant change of International Journal of Managing
Information , NoTechnology (IIJMIT) [21] Wei, R, “Modeling the network forensics
the crime scene. An increase in the behaviors” In Security and Privacy for
Vol.7 No.4, November 2015
advancement of technology attracts Emerging Areas in Communication
[7] Shrivastava, Gulshan and B. B. Gupta.
network revolution that calls for “An Encapsulated Approach of Forensic Networks. Workshop of the 1st
effective methods for monitoring Model for Digital Investigation.”, International Conference in 2005.
and control of security and forensics. Consumer Electronics (GCCE), 2014 IEEE [22] Kohn, M. J, “Framework for a digital
This paper effectively addressed how 3rd Global Conference on, pp. 280-284. forensic investigation”, Information
network forensic mechanisms can be IEEE, 2014. Security South Africa (ISSA). South
[8] Nik, Mariza, Nik Abdull Malik, Saadiah Africa: Insight to Foresight, 2006
used to eradicate network security
Yahya and Mohd Taufik Abdullah, [23] Stephenson, “A Comprehensive
attacks. The researches failed to Approach to Digital Incident
“Critical Phases in Network Forensic-
deal with the concerns raised by the Investigation”, Information Security
A Review”, International Conference On
emergence of new networks such as Digital Security And Forensic, pp 68-75, Technical Report,E.A. Technology,
M2M and IoT as per the advancement of 2014. Editor pp 42-54, 2003
improved network forensics essential in [9] Pilli, S.E., R. Joshi and R. Niyogi, [24] Khatir, M. S, “Two-Dimensional
handling the situation of attacks. It is of “Network Forensic Frameworks: Survey Evidence Reliability Amplification
essence to comprehensively analyze the And Research Challenges,” Digital Process Model for Digital Forensics”. In
Investigation, pp. 14-27, 2010. Digital Forensics and Incident Analysis.
emerging networks to help with forensic
[10] Saad, Sam and Iven Traore, “Method WDFIA ‘08. Third International Annual
investigation. Network forensics plays Workshop in 2008.
a crucial role in new and developing Ontology for Intelligent Network
Forensics Analysis”, Eighth Annual [25] Yong-Dal, “New Digital Forensics
areas of network and those related to International Conference on Privacy Investigation Procedure Model”. In
data mining, social networking, data Security and Trust (PST), pp. 7 – 14, 2010. Networked Computing and Advanced
visualization and data imaging. [11] Wei, Wang and Thomas E. Daniels, Information Management,.NCM - 2008.
Future Work - With the empirical ”Network Forensics Analysis with [26] Rahayu Selamat, “Mapping Process
survey on advances of network Evidence Graphs”, Digital Forensic of Digital Forensic Investigation
Research Workshop, 2005. Framework”. IJCSNS International
forensics in emerging networks like IoT,
[12] M. Pollitt, “A History of Digital Journal of Computer Science and
5G, it has been identified that there is Network Security, Vol.8(No. 10): pp 163-
Forensics,” in Advances in Digital
a need in research to be conducted on 169, 2008.
Forensics VI, vol. 337, K.-P. Chow and
the upcoming IoT (Internet of Things) S. Shenoi, Eds. Berlin, Heidelberg: [27] Sherri Davidoff, Jonathan Ham,
forensics, to capture the network Springer Berlin Heidelberg, 2010, pp. “Network Forensics – tracking hackers
attacks and identify attack patterns 3–15. through cyberspace” Prentice Hall
using honeypots. [13] D. B. Parker, Crime by computer. publications ISBN-13 978-0-13-
Scribner, 1976. 256471-7, 2012
5. References [28] Charles Pfleeger, Shari Lawrence,
[14] E. Casey, Digital Evidence and Computer
[1] Alzaabin, Marc. “CISRI: a Crime “Security in Computing” fourth edition,
Crime. Academic Press, 2004.
Investigation System Using the Relative ISBN 978-81-317-2725-6, 2013
[15] P. Sommer, “The future for the policing
Importance of Information Spreads [29] Ankit Fadia, “Network Security, a
of cybercrime,” Computer Fraud &
in Network Depicting Criminals hackers perspective” second edition,
Security, vol. 2004, no. 1, pp. 8–12, Jan.
Communications” published in ISBN 1403-93088-0, 2009
2004.
Information Forensics and Security, IEEE [30] William Stallings, “Cryptography and
[16] S. L. Garfinkel, “Digital forensics
Transaction, vol. (10), pp. 2196-2211, Network Security – Principles and
research: The next 10 years,” Digital
2015. practice” sixth edition, ISBN 978-93-
Investigation, vol. 7, Supplement, pp.
[2] Almulhem, John and Iven Traore. 325-1877-3, 2014
S64 – S73, 2010.
“Experience with Engineering a [31] IEEE 5G Summit Trivandrum – “IoT &
Network Forensics System”, Lecture [17] C. Stoll, “Stalking the wily hacker,”
Cyber security” 2017.
www.csi-india.org
36
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
S E CU R IT Y C OR N ER
Dr. (Mrs.) v. vasanthi pursued M.Sc(CS), M.Phil, and Ph.D Computer Science from Karpagam University,
Coimbatore in 2014. She is currently working as a Professor in Department of Computer Science at Rathinam
College of Arts and Science, Coimbatore since 2015. She has published many research papers in reputed
international journals including Thomson Reuters (SCI & impact factor) and conferences including IEEE &
Springer. Her main research work focuses on Adhoc and Sensor Networking. She can be reached at vasanthi.
cs@rathinam.in
37
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
A REPORT
TM
Computer Society of India
CSI Young IT Professional (YITP) Awards 2017
Final Round at Nashik on 7th Oct. 2017
Back row – SB Bagal, Principal GN Sapkal college of Engg., person as mentioned above.
Manas Ranjan Pattnaik CSI treasurer, Shri.Gautam Mahapatra Motivate upcoming professionals and enhance the
CSI Vice President, Prof. A K Nayak Hon Secretary CSI, prestige of the profession by enabling them to exercise
Sanjay Mohapatra CSI President, Ravindra Sapkal CMD their skills and competencies in the best possible and
Sapkal Knowledge Hub, Prof. E. Vayunandan VC YCMOU, innovative manner
Nitin Mahajan GM BSNL, Dr. Anirban Basu CSI IPP, Jury Mr. Directly or indirectly contribute towards the improvement
Hussain Dahodwala, Shri SR Karode, Dr. RS Tiwari of professional effectiveness in different spheres of life
Motivate young men and women to imbibe the
Front row – Prabhakar & team, Shreyasi Datta winner, Dr.
entrepreneurial spirit and thereby encourage more and
SS Sane RVP region VI & YITP convener, Jury Rohit Kulkarni,
more people to venture into entrepreneurship
Sandeep Karkhanis Chairman CSI Nashik Chapter
Encourage contribution in boosting the economy of the
CSI had announced “CSI Young IT Professional (YITP) country and promote research
Awards” competition for Individual IT Professionals and the IT
The Criteria:
Professional Teams below 35 Years Age, with objectives to:
The most outstanding technology project related to any
Recognize the significant contribution(s) made by a
theme mentioned below & completed during the year 2016/
The regional winners:
Region Competition Winner Winner’s Project Runner-up Runner’s Project
Location
I Lucknow Mr. Ashutosh Kumar Route Finder and Communicator Mr. Manish Kumar Design and Development of a
for Blind, Deaf and Dumb Web Crawler for Hidden Web
II Kolkata Ms. Shreyasi Datta Detection of AF and Other Mr. Purnendu Debnath Smart BIO Secure Server Login
Arrhythmia Using Single Lead
ECG
III Vadodara Ms. (Dr.) Deepshikha Fire Detection in Visible Spectral Mr. Rushi Trivedi Modem Trace Tool & Automation
(Baroda) Tiwari Range of Carrier Acceptance Testing
IV Bhubaneswar Mr. Sanjaya Kumar Dynamic Data Normalization in Mr. Santosh Kumar Online Query Tracking System
Panda Cloud Computing Satapathy
V Bengaluru Mr. Shanmuga Vehicle Clutch Health Ms. Shresta Anatha Xcelerator - Education, Project
prognostics and Vehicle Fuel and Career Guidance Portal
Consumption calculation
VI Pune Mr. Prabhakar My Robot – Personal Assistant Mr. Sudhir Gorade, & Bandhan / MahaBandhan – A
Gadupuddi Team Self-Help-Group of Women
VII Kovai / Mr. S. Sathish “Vibo” - An Artificial Mr. V. Gokula An Intelligent Smart Energy
Kovanputhur Kumar, & Team Intelligence based Machine Krishanan, & Team Saver
(Coimbatore) Learning ROBOT for Assisting
Physiotherapists
www.csi-india.org
38
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
A REPORT
2017 (project duration could be of 2-3 years from the start well achieved in this research. The innovative Sensing is the
date) within an organization were judged for following criteria Low-Cost “Single Lead” but at the same time, recognizing and
by the selection committee: accepting that “Every irregularity in the pattern is NOT noise!!”
Criticality of IT Usage, Improvement of Customer Service, Therefore, the Noise in the Signal cleaning (removing) and the
Innovation, Return on Investment, Quality of Management, Marker Detection utilized the Spectrogram Method of Digital
Impact on Organization and/or Society & Presentation Skills Signal Processing which is analyzing the Signal Frequency
The completion was carried first at each of the 7 Regions Components in Hz with respect to time in Seconds (Time
of CSI at the following Centers where the Winners and Runners Domain) for the Frequency band of 0 to 150 Hz (higher power
up of the regional contest from each region were selected for at higher frequency means noisy window, to be rejected) in the
the Final Round Competition at Nashik. time frame of 0 to 30 Seconds. Traditional systems generally
The winners of the regional contest were qualified for record a longer duration of ECG (more than 1 Hour) using
competing in the final national round. 12-Leads Medical-Grade Device.
Each Participant / Team Leader at the Final Round
was given 30 Minutes for the presentation, followed by the The automated feature extraction techniques made the
questions by the Juries & the Audience. Invisible features, visible to the doctors!
However, all 14 Regional Winning Teams, 2 from each of More than 200 ECG Features can be extracted which are
the 7 Regions, could not appear for the Final Round due to domain specific which are impossible for the doctors to do.
various reasons. So, the Computers catch them fast and accurately.
The 4 Juries appointed for the evaluation of the Final Round
Teams were eminent & very well experienced IT Professionals The Arrhythmia Screening Process Block Diagram showed a
from Nashik who cross-questioned the contestants to really Patient / Person using the Single-Lead Sensor for his left-hand
judge them and bring-out on the front their IT Skills. & right-hand fingers. The Sensor provided an Ultra-Sound
The Jury team comprising of 1] Shri. S. R. Karode, 2] Electro-Acoustic Coupling to a side-by Mobile Microphone.
Dr. Anand Tiwari, 3] Mr. Rohit Kulkarni and 4] Mr. Hussain The ECG acquired in the Mobile Memory is transmitted to a
Dahodwala were keen to understand from the participants Server (Cloud). The Signal Processing done on the Server are
about their contributions. Noise Cleaning from the ECG waveform, Feature Extraction,
The Program started off with introduction speeches, and the Classification based on the Inputs from Pre-trained Models.
inauguration of the function by performing puja of goddess This Project Team has obtained a Patent for this project. The
of knowledge, Ma Saraswati Devi, followed by the dignitaries Team won an International Competition of the Physionet
on the dais lighting the traditional oil lamp, symbolizing the Challenge in 2017. The Team has excellent support from the
removal of the darkness of ignorance and lighting-up the medical doctors.
knowledge.
Overall, involvement, enthusiasm and the devotion noted
The competition was rightly set for - on this project was the highest and highly technical and
thoroughly professional. This IT Professional would continue
Category Final Round - to demonstrate even brighter results in time to come.
National Awards (`)
Winner 25,000/- The second prize was bagged by team lead by Ms. Shresta
Anatha on their Team’s development & Implementation of the
1st Runner-up 15,000/-
Education, Project and Career Guidance Portal (Excelerator).
Special mention 10,000/-
She highlighted the gap between the Industry Requirements
All teams presented their creative and innovative solutions and the Academic Output, addressing the serious problems
and product developed by them for their organisations. This of large number of Un-employable professionals with un-
difficult task of selecting the final Winner, the 1st Runner-up adequate skills which are demanded by the Industry.
and the Special mention was ably performed by the jury team.
The Industry needs, apart from the basic knowledge & the
The winner Ms. Shreyasi Datta on her domain knowledge, soft-skills, ability to analyze the problems,
project - Detection of Atrial Fibrillation and the problem solving approaches. She stated that formal
(AF) and Other Arrhythmia Using Single learning constitutes only 10% where as 20% is the informal
Lead Electro-Cardio-Gram (ECG). learning and the most significant part, that is 70% is by way of
The subject itself was highly technical, the on-the-job experience.
combining the technologies of Sensor, So, the 3 Buckets of making the potential candidate employable
Electronic Signal Processing, Medical are: Education, Exposure to Industry and Hands-on Experience
Electronics / Diagnosis, Machine Learning, and Intelligent from 2 Weeks up to the required duration.
Algorithms & Validation Schemes etc.
To address the situation, her team cleverly came-up with the
The motivation behind this project is to enable continuous Solution, “Xcelerator” as a Conceptual Architecture which
monitoring of cardiac conditions of the elderly through a holistically considers the Recommendations, the Skills
simple, easy to use, smart-phone based attachment by Framework, and helps in building the Candidate’s Digital
constant analysis of ECG data by doctors remotely, which is Portfolio suitable for Recruitment.
39
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
A REPORT
A Recruitment Dashboard on the Portal provides for Job Scope of the solution as presented has the high level features
Description, going in details of Use Case, Recommendations, as Personal assistant, IT Assets management and Device
Clarity on the Job Role, Skills Frames covering all aspects of management.
Education, Exposure and Experience. The Portal Technology
This project realized well their goal of providing a single
Stack was explained in terms of layered & robust architecture
application which automates IT assets management, Personal
in terms of Top Layer as Presentation Layer utilizing the
assistant, Device management as well as it helps individuals
ReactJS & NginX (both acting as the web server) and Sub-
to simplify their daily routine tasks.
Layers as Navigational Feeds, the Application Layer based
on Phoenix Web Development Framework written in Elixir, Features/ Functionality successfully lively demonstrated
deriving it’s strength from Erlang (concurrent, fault-tolerant were Voice enabled features for E-mail integration, Device(s)
and real-time system – A Virtual Machine); the Data Layer of management, Artificial intelligence enabled Chat-bot
Redis (mainly used for caching and to manage job queues) & integration, IT Assets/ compliance management, and Personal
Postgres (it runs Relational DB and NoSql DB in the same assistance.
server); and Infrastructural Layer of Docker (to manage the The Project’s Software and hardware requirements for 25 users
whole application stack by containers being run), AWS (Cloud are, Cloud Server (Hard Disk 80 GB, RAM 2 GB); Software:
Server). Android V 6.0+, Python required libraries Version 2.7+, MySQL
The Candidate’s Attitudinal Problems too are attending DB v5.0+, TensorFlow -, Google Speech recognizer – Natural
including a Blogger Forum. Language Tool Kit (NLTK); Mobile application – Android
application V6.0+
The Return on Investments were discussed on 4 Revenue
Streams of Workshops, platform subscriptions, mentoring and The Development tools and technologies utilized were, Front
guidance fees, recruitment service fees, affiliate agreements, end – Android layout model (XML); Back end – MySQL DB,
etc. Rest APIs and the Development environment – Android Studio
/ Eclipse environment (Java)
Finally, Impact on Society was presented in detail as the Team
want to give students pursuing a degree, a sense of purpose, The System Implantation Level Block Diagram showed the
to help them choose a goal, make a plan to achieve the goal, Mobile as a Voice Input & Output Device which sends digital
and help them stick to the plan to achieve their goal. The information to the Gateway which includes IMEI Operation and
platform empowers students to articulate and pursue their Model Token. The Services APIs are Loader, Main, Audit, Device,
aspirations and ambitions. The Teams’ Future Plans as Services, Chatbot, Remind. The Request generated is filtered
explained include expansion to an even wider college base and bundled. The cloud Storage provides the databases.
– more students on the platform will help them make their This project showed effectively how “Time is Money!!” and
recommendation algorithms more robust. how this application reduces the Total Cycle Time. A Physical
A similar effort on the industry side to expand the number Method which would take say about 14 Minutes, the “My Robot”
of companies on the platform is also underway. Their URL: can do the same in just 2 Seconds.
https://www.xcelerator.ninja On the whole, the entire presentation was most attentively
The special mention prize was awarded to Mr. Prabhakar watched by the audience and for the Non-IT personnel; it
Gadupuddi and his Team on the Project - My Robot – Personal would have given the feel of a Sci-Fi Movie. The Juries queries
Assistant. were most successfully fielded by the presenters.
The Project summary explained “My Robot – Personal It was enjoying moments as to watch and experience what
Assistant” as a mobile application and end user(s) can talk to today’s Information & Communication Technologies can do for
their mobile phones using natural language and assign the the mankind.
task for automation. Users can talk to their mobile phone and
mobile phones will control/ monitor user’s daily activities,
meetings, reminders, personal computers and IT assets, The event got overwhelming response from IT professionals
virtual machines and etc. from Nashik, Academia, Students and was appreciated
by participants, guest and executive committee of CSI for
In this application, artificial intelligence module is enabled. arrangements done by Nashik Chapter & Sapkal Knowledge
Mobile phones virtual think and respond to users for the Hub under guidance of Prof. Shirish Sane, RVP region VI and
task completion. All devices (computers, servers, mobiles) YITP 2017 convener.
are inter connected for sharing the device status and info for
n
monitoring/ controlling.
www.csi-india.org
40
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
Pilgrims in the Digital World Book Review
By Sandeep godbole
41
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
F ROM C h AP TERS & DI v I S I O NS
www.csi-india.org
42
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
F ROM C h AP TERS & DI v I S I O NS
Manmit Desai, Business Development Manager (India), Retrieval using Opinion Mining, Machine Learning and
Professional Graphics for AMD. Ajay presented on AMD Data Analytics in Multimedia IR and Information Retrieval
processors, which mainly include, AMD Godavari, AMD – Research Perspective. There were 113 participants who
Kaveri, AMD Bristol Ridge, & New Processor Ryzen, Server have registered for the seminar, out of which 54 members
platform EPYC. He explained AMD presence and stake were from the various colleges in Tamil Nadu. The speakers
in India as well as global. Manmit explained about AMD were leading researchers and academicians in the field of
graphics. Bahubali movie on AMD pro graphics. Radeon Information Retrieval from top engineering institutions and
Pro Graphics and applicable industry. Testimony given industry. The session speakers were Dr S Swaminathan,
by M/s Minitek and AMD core architecture was explained Anna University, Chennai, Dr Janet, NIT, Tiruchirappalli, Prof
by Shri. Jaykrushna Puranik committee member and J Naveen, Christ University, Bangalore, Dr E Kirubhakaran
experienced in microprocessor based controllers and , BHEL, Tiruchirappalli, Dr U Srinivasalu Reddy, Assistant
systems development. Session was interactive and followed Professor and Associate Dean, NIT, Tiruchirappalli and Dr
by technical Q and A. The participants expressed that the S Nicolas, NIT, Tiruchirappalli. Dr S Ravimaran, Principal
session was indeed a nice and informative one. & Chairman of CSI Tirchirappalli chapter rendered the
welcome address and explain the objectives of this two days
RAIPUR ChAPTER seminar to the participants. He congratulated the faculty
members for their support and stated how the two-days
seminar will be helpful for the academicians and research
scholars.
vADODARA ChAPTER
43
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
F ROM C h AP TERS & DI v I S I O NS
vEllORE ChAPTER
FR OM S T U D E N T B R A N C h ES
REgION-I
Maharaja Agrasen Institute of Technology, Delhi Jaypee University of Information Technology, Solan
31-8-2017 - CSI Orientation programme 15-9-2017 - workshop on Massive Open Online Courses
(MOOCS) by Prof Mangala Sunder Krishnan, IIT Madras
www.csi-india.org
44
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
FR OM S T U D E N T B R A N C h ES
REgION-I
Dronacharya College of Engineering, gurgaon
27-9-2017 - Expert Lecture on Data Warehousing and 7-10-2017 - Expert Lecture on C/C++ : An Expert’s View
Business Intelligence by Mr. Tarang Gupta
Jaypee University of Engineering & Technology, guna
20-9-2017 & 21-9-2017 - Event on QRIOSITY’ 17 23-9-2017 Workshop on Introduction to Python Programming
- A quizzing contest
45
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
FR OM S T U D E N T B R A N C h ES
REgION-III
The lNM Institute of Information Technology, Jaipur
4-8-2017 - Introduction of CSI to the freshers & short quiz 4-9-2017 - SIP (Summer Internship Project)
REgION-v
Scient Institute of Technology, hyderabad
29-9-2017 - Guest Lecture on Education Counselling 5-10-2017 –Seminar on Full Stack Development by Mr. Rohit
by Mr. Amarnath Goud
www.csi-india.org
46
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
FR OM S T U D E N T B R A N C h ES
REgION-v
geethanjali Institute of Science & Technology, Nellore vasavi College of Engineering (Autonomous), hyderabad
15-9-2017 to 17-9-2017 - Short Term Training program on 12-10-2017 - Orientation Program about CSI by Mr Mohan
Ruby on Rails by Mr Pavan Manne Raidu, Chairman, CSI Hyderabad Chapter
REvA UNIvERSITY, Bengaluru
1-9-2017 – Event on Best Idea Competition 7-10-2017 - Inauguration of CSI Student Branch
by Dr. Anirban Basu, IPP, CSI
St Joseph Engineering College, Mangaluru JSS Academy of Technical Education, Bangalore
18-9-2017 - CSI Student Branch Inauguration 23-9-2017 - Technical talk on Information and storage issues in
Modern Intelligent environments by Mr Hanu Ramasanjeeva
47
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
FR OM S T U D E N T B R A N C h ES
REgION-v
K S Institute of Technology, Bangalore
22-9-2017 National Level Coding Competition : 16-9-2017 - Technical Talk on Cloud Computing and Mobile
CODE IGNITER – 2017 Computing by Mr Manu Kamath
REgION-vI
Yeshwantrao Chavan College of Engineering, Nagpur Pillai hOC College of Engineering and Technology, Rasayani
16-8-2017 & 17-8-2017 - Two Days National Level Technical 16-9-2017 - Workshop on Web Application Development
Fest on iTECHROOTS 8.0 Using MVC & SERVLET
late g. N. Sapkal College of Engineering, Nashik
www.csi-india.org
48
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
FR OM S T U D E N T B R A N C h ES
REgION-vII
Panimalar Institute of Technology, Chennai
23-9-2017 to 7-10-2017 – Training Program on SQL 2016 and C# 24-9-2017 - Runner up team with the organizers in the CSI
.NET by Mr Joel S Davis Young IT Professional (YITP) Award 2017
Rajalakshmi Engineering College (Autonomous), Chennai
11-9-2017 - Workshop on Web Application Development 13-9-2017 - Seminar on Bootstrapping in Mobile Application
Using Hibernate with Spring MVC by Mrs Banu Manoharan Development by Mr Ashwin Irudayarajan
Nehru Institute of Engineering and Technology, Coimbatore Avinashilingam Institute for home Science and
higher Education for women, Coimbatore
21-9-2017 – Dr. Sundaresan, RVP-VII, 22-9-2017 - Workshop on Arduino Controller and its
CSI Inaugurated CSI Student Branch Applications by Mr. Madhan Kumar
Toc h Institute of Science & Technology, Ernakulam vIT University, vellore
18-8-2017 – Dr Rajesh Maliyeckal, Past Chairman, CSI Cochin 30-9-2017 - Workshop on coding “Send CodeZ”
Chapter Inaugurated CSI Student Branch
49
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
FR OM S T U D E N T B R A N C hES
REgION-vII
Jeppiaar Institute of Technology, Sriperumpudur
CSI CA l EN D AR 2 0 1 7 - 1 8
NOvEMBER State Level Student Convention for Andhra Pradesh organized by CSI Student Branch of GITAM Inst. of Tech., GITAM
24-25, 2017 University, Visakhapatnam. Contact : Prof. R Sireesha, 9848503365, sireesha.rodda@gitam.edu
DECEMBER Regional Level Student Convention for Region-VI organized by CSI Student Branch of Bansilal Ramnath Agarawal
19-20, 2017 Cheritable Trust’s Vishwakarma Institute of Information Technology, Pune. Contact : Prof Snehal Rathi, 9850604785,
snehal.rathi@viit.ac.in
21-23, 2017 State Level Student Convention for Tamil Nadu by Karpagam College of Engineering, Coimbatore. Contact : Dr. S. Angel
Latha Mary, 9842242882, angellathamary.s@kce.ac.in
28-29, 2017 Regional Level Student Convention for Region-V “Malwares in Social Media” organized by CSI Student Branch of
NBKR Institute of Science and Technology (Autonomous), Nellore. Contact : Dr. S. Maruthuperumal, 9848772088,
maruthumail@gmail.com
2018 Regional Level Student Convention for Region-VII organized by CSI Student Branch of Jeppiaar Engineering College,
JANUARY Chennai. Contact : Dr P Jesu Jayarin, 9444053102, jjayarin@gmail.com
23-24, 2018
24-25, 2018 State Level Student Convention for Maharashtra State organized by CSI Student Branch of St.Vincent Pallotti College of
Engineering & Technology, Nagpur. Contact : Prof. Abhishek D. Pathak, 9890919330, abhishekpathak81@rediffmail.com
FEBRUARY State Level Student Convention for Gujarat State organized by CSI Student Branch of G H Patel College of Engineering &
09, 2018 Technology, Vallabh Vidyanagar. Contact : Dr Moulika S Patel, 9428488563, maulikapatel@gcet.ac.in
www.csi-india.org
50
C S I C o mm u n I C a t I o n S | n o V E m B ER 2 0 1 7
52nd Annual Convention of Computer Society of India
In Technical Collaboration with
(CSI 2017)
host: Kolkata Chapter | venue: Science City
19-21 January, 2018
On enormous request the last Date of Submission has been extended up to 15th November 2017
Theme: Social Transformation - Digital way
Proceedings will be published by Springer Nature Singapore in CCIS Series indexed by SCImago, Scopus, DBlP
52nd Annual Convention of Computer Society of India (CSI 2017) will be held at Science City, Kolkata during 19th January to
21st January 2018. The CSI Annual Conventions are held in different cities across India. The CSI Annual Conventions, usually
attracting 2000 plus participants have been held since 1965. Apart from technical sessions, tutorials, panel discussions and
Exhibition are main features of the convention. The Conventions held at Kolkata include CSI 66 (First Convention), CSI 78, CSI
86, CSI 90, CSI 94, CSI 2001, CSI 2006, CSI 2012.
The theme of the CSI 2017 is “Social Transformation - Digital Way”. It will cover all aspects of digital technology and machine learning in
computer science and engineering, general science, educational research and management science. This convention will provide a platform
to the participants to share their views and ideas on latest technological developments in an inter - and intradisciplinary perspective. There
are total eight tracks in the call for papers. Tracks of the international Conference are (but not limited to): Signal Processing, Microwave and
Communication Engineering; Electronic Devices, Circuits and Systems; Data Science and Data Analytics; Security and Forensics; Digital
Mapping in Environment; Bio Computing and Biomedical Engineering; Mobile, Nano and Quantum Computing; e-Governance, e-Learning
and confidence based Learning.
Participations in the 52nd Annual Convention of Computer Society of India (CSI 2017) are solicited from Industry Houses, Acad emicians,
Corporate Houses, Exhibitors, Faculty Members, Researchers and Students.
Submission guidelines:
The publication for the International Conference will be in SCI Mago, Scopus DBLP Indexed CCIS Series of Springer (Confirmed) and the
article should be within 15 pages in the Springer CCIS one-column format. All submissions are subject to screening for plagiarism by
iThenticate®. Double blind review system will be followed and each paper will be reviewed by at least three reviewers. Formatting style is
available in http://www.springer.com/computer/lncs?SGWID=0-164-6-793341-0. Each paper should be registered separately with at least
one full registration fee and papers only of student authors are eligible for student registrations (proof needed). Research scholars will not
be considered as any category of student.
Submission Link: https://easychair.org/conferences/?conf=csi20170
Contact Details
Organizing Chair: Dr. Phalguni Muherjee (+91 9433477369) Exhibition Chair: Mr. Sib Daspal (+91 9830333781)
(phalguni.mukherjee@gmail.com) (sibdaspal@gmail.com)
Organizing Co-Chair: Mr. Subir Lahiri (+91 9432284548) Exhibition Co-Chair: Mr. Gautam Hajra (+91 7980739842)
(subirlahiri49@gmail.com) (computerhom@gmail.com)
Technical Program Committee Chairs: Event Chair: Dr. Samir K. Bandopadhyay (+91 9831030823)
Dr. Kalyanmoy Deb, Michigan State University, USA (1954samir@gmail.com>)
Dr. J. K. Mandal (+91 8240323373) (jkm.cse@gmail.com) Event Co-Chair: Dr. A. K. Mukhopadhyay(+919434385282 )
Program Co-Chair: Dr. Devadatta Sinha (+91 9830269278) (askm55@gmail.com)
(devadatta.sinha@gmail.com) Registration Chair: Mr. Aniruddha Nag (+91 9830876463)
Tutorial Chair: Dr. Amlan Chakrabarti (+91 9831129520) (ani_nag123@rediffmail.com)
(achakra12@yahoo.com) Registration Co-Chair: Mr Abhijit Sarkar(+919831611033)
Tutorial Co-Chair: Dr. Debasis De(+918617256060) (abhijit_sarkar_1@rediffmail.com)
(dr.debashis.de@gmail.com) Publicity Chair: Mr. Subhobrata Roy Chaudhuri
Tutorial Convener: Dr. Somnath Mukhopadhyay (+919475413463) (sabsrc@yahoo.co.in)
(som.cse@live.com) Publicity Co-Chair: Dr. Kaushik Roy (+919432841740)
Finance Chair: Mrs. Alakananda Rao (+91-98300-58313) (kaushik.mrg@gmail.com)
(alka.rao@alvarisys.com) Hospitality Chair: Dr Manas Kumar Sanyal(+919434451520)
Finance Co-Chair: Mr. Sourav Chakraborty (sourav_ch@rediffmail.com) (manas_sanyal@rediffmail.com)
Convener: Mr. Devaprasanna Sinha (+91 9830129551) Hospitality Co-Chair: Mr Subhranshu Roy(+919051377068)
Subhranshu_81@yahoo.com
Interested persons are requested to contact the respective Chair/Co-chair for further details for participating in this mega event to be held
at the City of Joy, Kolkata. The weather during January at Kolkata will be very much conducive for this mega event. All are requested for wide
publicity of the event so that the information about the event can reach to each corner of the globe at the earliest for their comprehensive
planning to visit Kolkata during the event.
Convention Secretariat
Computer Society of India, Kolkata Chapter, 5, Lala Lajpat Rai Sarani (Elgin Road), 4th Floor, Kolkata - 700 020
E-mail : csical@gmail.com, chairoccsi2017@gmail.com, csi2017kolkata@gmail.com
Registered with Registrar of News Papers for India - RNI 31668/1978 If undelivered return to :
Regd. No. MCN/222/20l5-2017 Samruddhi Venture Park, Unit No.3,
Posting Date: 10 & 11 every month. Posted at Patrika Channel Mumbai-I 4th floor, MIDC, Andheri (E). Mumbai-400 093
Date of Publication: 10th of every month
Conference Chair: Dr. Goutam Mahapatra, DRDO,GOI, VP,CSI Computer Society of India
Convenor: Mr. D. P. Sinha, RVP-II, CSI
The Springer Nature Sponsored International Conference on Social Transformation - Digital Way, is being organized by the CSI
Organising Chair: Dr. Phalguni Mukherjee, CSI
Kolkata Chapter at the Science City during 19th-21st January 2018. Proceedings will be published by the Springer in CCIS Series
Organising Co-Chair: Mr. Subir Lahiri, CSI
(approved) indexed by SCImago, Scopus, DBLP etc. Extended versions of presented papers will be submitted for publication in S CI
Technical Programme Chairs: and Scopus indexed journals.
Dr. Kalyanmoy Deb, Michigan State University, USA The event is also technically sponsored by the IEEE Young Professionals, IEEE Computational Intelligence Society, BCC & I etc.
Dr. J. K. Mandal, University of Kalyani, India
Technical Programme Co-Chair: Dr. D. D. Sinha, Calcutta University The articles for the International Conference should be within 15 pages in the Springer CCIS one-column format. All submissions
Finance Chair: Ms. Alakananda Rao, Alvari Systems are subject to screening for plagiarism by iThenticate®. Double blind review system will be followed and each paper will be reviewed
Finance Co-Chair: Mr. Sourav Chakraborty, CSI by at least three reviewers.
Exhibition Chair: Mr. Sib Daspal, The Bengal Chamber & Sasha Important Dates :
Group Last date of submission: 15.11.2017; Date of Notification:15.12.2017; Camera Ready Submission and Registration: 31.12.2017.
Exhibition Co-Chair: Mr. Gautam Hajra, CSI
Registration Chair :Mr. Aniruddha Nag, CSI Submission link: https://easychair.org/conferences/?conf=csi20170
Registration Co-Chair: Mr. Abhijit Sarkar, JOBexo Call for Papers
Event Chair: Dr. Samir K Bandopadhyay, CU The theme of the CSI 2017 is “Social Transformation - Digital way”. It will cover all aspects of digital technology and machine
Event Co-Chair: Dr. A K Mukhopadhyay,CSI learning in computer science and engineering, general science, educational research and management science. This convention
Publicity Chair: Dr. Subhobrata Roychaudhuri, Techno University will provide a platform to the participants to share their views and ideas on latest technological developments in an inter- and intra-
Publicity Co-Chair: Dr. Kaushik Roy, WBSU disciplinary perspective. There will be total eight tracks for the international conferences.
Hospitality Chair:Dr. Manas Kumar Sanyal, KU
Tracks of the Conference (not limited to) • Digital Mapping in Environment
Hospitality Co-Chair: Mr. Subhranshu Roy, KU
Tutorial Chair: Dr. Amlan Chakrabarti, CU • Mobile and Wireless Communication • Intelligent Bio Computing
Tutorial Co-Chair: Dr. Debasish Dey, MAKAUT • Nano Device Modelling • Digital Judiciary
Tutorial Convenor: Dr. Somnath Mukhopadhyay, Hijli College
• Data Analytics • e-Learning and confidence based Learning
& RSC II
• Security and Forensics • Intelligent Data Mining
Advisory Committee(Partial)
Mr. Snajay Mahapatra, President, CSI Conference highlights
Dr. Anirban Basu, Immd. Past President, CSI Keynote/Invited/Banquet Talks, Technical Paper Sessions, Student Research Forum, Panel Discussions, Demos & Exhibits,
Dr. A. K. Nayak, Secretary, CSI Mentoring Sessions
Mr. Manas Ranjan Pattnaik, Tresurer, CSI Important Dates :
Dr. Aditya Bagchi, RKM University, India Formatting Guidelines: http://www.springer.com/computer/lncs?SGWID=0-164-6-793341-0
Dr. S Bandopadhyay, Calcutta University Submission link: https://easychair.org/conferences/?conf=csi20170
Mr. R. N. Lahiri, CSI WikiCFP Link: http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=66231
Dr. Kalyanmoy Deb, MSU, USA
Dr. Aynur Unal, Stanford University, USA Registration Fees :
Dr. Prith Banerjee, Schneider Electric, USA
Category of Delegates/ Authors Early Bird (On or before 10th After 10th October,2017 Spot Registration(Only in
Dr. Shikharesh Majumdar, CU, Canada October, 2017) Cash)
Dr. Amiya Nayak, OU, Canada
Dr. Sajal Das, UTA, USA Indian Authors & Delegates(in INR) including GST
Dr. Santosh Mohanty, TCS, India CSI Members General CSI Members General CSI Members General
Dr. Zbigniew Michalewicz, UA, Australia
Full time Students 1,800/-* 2,000/-* 2,300/-* 2,500/-* 2,300/-* 2,500/-*
Dr. Y Narahari, IISC Bengaluru, India
Dr. Hyeona Lim, MSU, USA Academician/Research Scholar 6,500/- 7,000/- 7,000/- 7,500/- 8,000/- 8,500/-
Dr. Rajkumar Buyya, UM, Australia
Industry/Govt./PSU 7,000/- 7,500/- 7,500/- 8,000/- 8,500/- 9,000/-
Dr. Somnath Mukhopadhay TU, USA
Dr. A. Kaykobad, BUET, Bangladesh One Day Registration 3,000/- 3,500/- 3,500/- 4,000/- 4,000/- 4,500/-
Dr. B. B. Chaudhuri, ISI Kolkata, India Pre-convention Tutorial INR 1,000 for authors and INR 1,500 for others
Dr. S. Satapathy, PVPSIT, India
Foreign Delegates $300 for Registration and $ 100 for Tutorial
Dr. Atulya Nagar, LHU, UK
Dr. B. K. Panigrahi, IIT Delhi, India *Including Tutorial Sessions
Dr. Basabi Chakraborty, IPU, Japan
Dr. Subarna Shakya, TU, Nepal Sponsorship Platinum Gold Silver Knowledge Partner Academic Conference Kit Conference Cultural Program
Dr. Girijasankar Mallik UWS, Australia Partner Dinner
Technical Program Committee Members: Amount (`) 15 Lakh 10 Lakh 5 Lakh 2.5 Lakh 1 Lakh 2 Lakh 2 Lakh 1 Lakh
Dr. S. K. Basu, BHU, India
(I) Each paper should be registered separately with at least one full registration fee.
Dr. P. K. Jana, ISM Dhanbad, India
Dr. A. Damodaram, TU, India (II) Papers only of student authors are eligible for Student registrations (proof needed).
Dr. Subir Sarkar, JU, India (III) Research scholars will not be considered as any category of student.
Dr. S. P. Maity, IIEST, India
Email: csi2017kolkata@gmail.com Accommodation: To be made on payment basis Convention Website: www.csi2017.in
Dr. Vipin Tyagi, CSI
Dr. Durgesh Nandi, CSI Group Registrations:
Dr. Paramartha Dutta, Viswa Bharti University, India Student Author Delegate
Dr. P. K. Roy, APIIT, India
Group of 4 or 5 Group of 6 or more Group of 4 or 5 Group of 6 or more Group of 4 or 5 Group of 6 or more
Dr. D. K. Pratihar, Indian Inst. of Technology Kharagpur, India
Dr. B. B. Pal, University of Kalyani, India ` 1,800 Per Head ` 1,600 Per Head ` 6,500 Per Head ` 6,000 Per Head ` 7,000 Per Head ` 6,500 Per Head
Dr. Dhananjay Bhattacharyya, SINP, Kolkata, India