Professional Documents
Culture Documents
© IJCSI PUBLICATION
www.IJCSI.org
© IJCSI PUBLICATION 2009
www.IJCSI.org
EDITORIAL
Dr Tristan Vanrullen
Chief Editor
LPL, Laboratoire Parole et Langage - CNRS - Aix en Provence, France
LABRI, Laboratoire Bordelais de Recherche en Informatique - INRIA - Bordeaux,
France
LEEE, Laboratoire d'Esthétique et Expérimentations de l'Espace - Université d'auvergne,
France
Dr Mokhtar Beldjehem
Professor
Sainte-Anne University
Halifax, NS, Canada
Dr Pascal Chatonnay
Assistant Professor
Maître de Conférences
Université de Franche-Comté (University of French-County)
Laboratoire d'informatique de l'université de Franche-Comté (Computer Sience
Laboratory of University of French-County)
Prof N. Jaisankar
School of Computing Sciences, VIT University
Vellore, Tamilnadu, India
IJCSI REVIEWERS COMMITTEE
3 . Prototype System for Retrieval of Remote Sensing Images based on Color Moment and
Gray Level Co-Occurrence Matrix
Priti Maheshwary and Namita Sricastava, Deparment of Mathematics, Maulana Azad National
Institute of Technology, Bhopal, Madhya Pradesh, India
Kevin Yi-Lwern YAP1,2, Xuejin CHUANG2, Alvin Jun Ming LEE2, Raemarie Zejin LEE2, Lijuan LIM2, Jeanette Jiahui LIM2
and Ranasinghe NIMESHA2
1
Department of Pharmacy, Faculty of Science, National University of Singapore
Block S4, 18 Science Drive 4, Singapore 117543, Singapore
kevinyap.nus@gmail.com
2
NM5206 Project Team, Communications and New Media Programme, Faculty of Arts & Social Sciences, National University
of Singapore
IJCSI
2 IJCSI International Journal of Computer Science Issues, Vol. 3, 2009
use can affect their compliance to their medication, which strategy to portray some cancers as being more ‘favorable’
may consequently lead to the patients suffering from drug- since they were more photogenic and less offensive [11].
related problems (DRPs) such as under- or overdosing, or Furthermore, a recent trial also showed the usefulness of
potential drug-drug, drug-food or drug-herb interactions digital media in improving the knowledge and awareness
[2]
. of prostate cancer screening among African-American
Human-computer interaction (HCI) has become a norm men [12]. However, the two most pressing health-related
in society. The roles between patients and healthcare issues currently which involve the impact of digital media
professionals have evolved with the information age. are on its effects on the views and attitudes of sexuality [13]
Internet and informatics technologies brought about by the and smoking among youths [14,15].
cyber era have been critical in transforming the public’s In recent years, the internet has become a very popular
attitudes towards healthcare and medicine. The interface HCI tool in a person’s daily life. It is not uncommon
between HCI and health services has led to the birth of nowadays for patients to search for health-related
medical informatics, which aims to develop studies and information online. The World Wide Web Consortium
instruments to solve clinical issues in the practical setting (W3C) [16] and the Internet Engineering Task Force (IETF)
[3] [17]
. Its ultimate goal is to improve the healthcare of have not only provided common standards for data,
patients. As such, many issues from the genetics, social, information and software applications for the WWW, but
economic and environmental factors, cognitive, emotional also encouraged users to discuss about various internet-
and behavioral domains can also play a role [4]. The related operational and technical problems. Users can now
emergence of the World Wide Web (WWW) is one of the navigate through a vast and complex web of linked
most significant developments in the history of the internet computer documents through an inexpensive, easy-to-use,
[5]
. The internet is rapidly gaining importance not just for cross-platform, graphic interface which supports items like
healthcare professionals, but for patients as well. Although buttons, scroll lists, tables and pop-up menus for user
healthcare professionals access information on the internet interaction. However, the current hype in healthcare not
to help them make decisions regarding patient care, only embarks on the use of IT and the WWW, but also the
patients are also becoming more well-informed about their integration of interactive media technologies. Interactive
health and health-related issues through the information media not only establishes a two-way communication
which they can get over the internet. Patients are now just among its users, but allows active participation as well. An
as likely to be able to highlight the risks, various therapies opportunity exists for web users to gain information and
and available treatments to their healthcare providers [6]. knowledge in a more interesting manner. Internet
As traditional therapy is being translated to the internet, interactivity can exist in both digital and multimedia forms,
the layman is now more aware of his health and is able to and is most commonly represented by means of text, audio,
better understand the science behind the various illnesses video, graphics, images and animation [18]. As long as one
through information he gets from the WWW. Albeit the has the hardware, software, talent and skills for
uncertainty as to whether cybermedicine will ever be developing an interactive application, it can be mounted
comparable to non-cybermedicine [7], the WWW has on the WWW through inexpensive browsers.
nevertheless impacted the way healthcare is being
practiced today. The challenge is for both healthcare 1.2 Animation as an Interactive Tool in
professionals and patients to critically evaluate the vast Healthcare
amounts of available information so as to provide the best
care for the patients’ well-being. Animations have always been promoted as a way to
showcase the dynamics of user interface actions. People
1.1 The Roles of the Internet and Interactive encounter animations frequently since they have been used
Media in Healthcare for various purposes, particularly in web pages and online
advertisements. Animations are useful for presenting
The traditional role of media in healthcare has involved highly abstract or dynamic processes, or when the user is
the use of audio and video programs in public health involved in an action or process [19]. It is known that user
education, such as with psychiatric diseases, cancer and satisfaction with animations is usually quite high, unless
smoking. Film and photography were used as forms of they distract the user from focusing on key issues [20]. The
‘Edutainment’ – an Education-Entertainment strategy – to applications of animation are widespread, normally
address the stigma of people experiencing depression [8] involving the entertainment and advertising industries.
and schizophrenia [9]; while the American Cancer Society However, this form of interactivity is also getting more
leveraged the use of movies as an educational tool for the widely accepted in the healthcare world.
public on cancer in the 1920s [10]. In fact, popular There are many examples of animation applications in
Hollywood films in the 1930s to 1970s also used this the medical sciences, such as in medicine and dentistry [21],
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 3
orthopedics [22,23], and aesthetics surgery [24,25]. A virtual have recognized pharmacists as essential health care
human simulation using a 3D phantom was developed by providers [30]. The practice of pharmaceutical care forms
Oak Ridge National Laboratory and its collaborators [26] at the cornerstone of clinical pharmacy, and its concept
the beginning of the century as a computer representation revolves around identifying, solving and preventing drug-
of the human anatomy. Animated films can also be used in related problems (DRPs) with regards to a patient’s drug
the field of psychology for teaching purposes, such as therapy [31]. Although this area has significantly
characterizing personality types. An example can be contributed to new approaches in pharmacy education,
extracted from the animated film ‘Who Framed Roger several ‘driving forces’ that will impact the value of
Rabbit’ [27], in which Roger exhibits a whole range of pharmacists have been identified [30]. These include: (a)
personality traits from being extroverted and aggressive to improved care and protection for patients, especially the
being insecure and anxious. However, film animation is chronically ill or those with particular types of diseases
only one of animation techniques that can be used in the (e.g. acquired immune deficiency syndrome or AIDS); (b)
health sciences. training new pharmacy professionals to be more patient
Advancements in computer technology have orientated; and (c) the need for advanced pharmaceutical
revolutionized the way healthcare is practiced. As expertise and new skills to keep up with accelerated
computers become more affordable and newer information technology so as to be able to manage new
technologies emerge, traditional animation techniques of treatments.
tweening and morphing have transformed into Pharmaco-cybernetics is an upcoming area of pharmacy
computerized versions created by two- (2D) and three- which involves advanced skills and expertise to deal with
dimensional (3D) bitmap and vector graphics. The HCI concepts and technologies in relation to medicines
development of the WWW has led to the creation of many and drugs. The term ‘pharmaco’ is derived from the Greek
web publishing platforms, including HyperText Markup term ‘pharmakon’ meaning drugs or poisons [32], and
Language (HTML) and its variants, Java applets, Flash ‘cybernetics’ comes from the Greek term ‘kubernetes’,
and Shockwave, among others. Web technologies have which can be translated to mean ‘the art of steering’ [33,34].
also enabled the generation of other forms of web pages Originally defined by Norbert Wiener in his book of the
like Hypertext Preprocessor (PHP) and Active Server same title, he defined ‘cybernetics’ as the science or study
Pages (ASP). HTML has been the well-known standard of ‘control and communication in the animal and the
format for publishing content on the WWW, but its machine’ [33-35]. Aptly described by the American Society
limitation lies in the management of interactive and for Cybernetics (ASC) as the design, discovery and
animated content. However, the WWW has now managed application of principles of regulation and communication
[35]
to successfully integrate Flash technology for this purpose , this is a multi-disciplinary area which has been applied
due to its advantages of not having cross-platform and to many fields such as system theory, psychology,
cross-browser compatibility problems, and the ‘Flash anthropology, sociology, and more recently, biology,
everywhere’ phenomenon is getting very popular with engineering and computer science [34]. The single
website developers [28]. Websites can now be created using characteristic that defines a cybernetic system is the
a combination of HTML and Flash, or created entirely in relationship between endogenous goals and the external
Flash. A recent small-scale usability study done by environment [36]. In fact, this was not a new concept in
Piyasirivej reported that users generally enjoy Flash sites healthcare, and was already applied in the 1970s by Maltz
more than HTML sites [28]. Examples are the ‘Virtual Knee as a means of setting goals of positive outcomes for his
Surgery’ and ‘Choose the Prosthetic’ games developed by patients who were not satisfied by their plastic surgery
Edheads + COSI where the user takes on the role of a procedures [37]. However, the traditional concept of
virtual surgeon to diagnose knee replacement patients and cybernetics has evolved into a modern theory known as
carry out a total knee replacement surgery [29]. However, ‘new cybernetics’ or ‘second-order cybernetics’, in which
despite the attractiveness of such technologies in the information is viewed as construct and reconstructed by
various areas of healthcare, their progress in the individuals interacting with the environment [38,39]. This
pharmaceutical arena is still slow. means that the system is not only dependent on the
observer or person interacting with it, but it also links the
1.3 Pharmaco-Cybernetics as Part of Pharma- individual with the society as a whole.
Culture The science of cybernetics has further led to the term
‘cyberspace’ being coined by Gibson in his famous book
The objectives, roles and value-addedness of clinical Neuromancer, which identified a virtual representation of
pharmacists have always been in continuous debate. information in varying states of accessibility, linked to
Nevertheless, many organizations such as the World various people and organizations [40-42]. A similar concept
Health Organization (WHO) and the Nuffield Foundation was brought up in the movie ‘The Matrix’ and its sequels
IJCSI
4 IJCSI International Journal of Computer Science Issues, Vol. 3, 2009
in which Neo, a computer programmer, who lived in a their strengths, as well as know the drugs, herbs or foods
future world perceived by humans as reality, was actually that interact with warfarin in an interesting manner.
a simulated matrix created by sentient machines to subdue
the human race [43]. This term is now ubiquitously used to
describe anything which is associated with computers,
information technology, and the internet. It also
incorporates the elements of social experiences and
interaction of individuals through the exchange of ideas
and the sharing of information [44].
Thus, ‘pharmaco-cybernetics’ or ‘pharma-cybernetics’
aptly describes the science of dealing with medicines or
drugs through applications of HCI concepts and
technologies so as to reduce or prevent DRPs, and
ultimately, improve pharmaceutical care in patients. It
involves communication and feedback with the users, and
connects control (i.e. actions taken in the hope of
achieving goals) with communication (i.e. the flow of drug
information and knowledge between the user and the
cybernetic system or environment).
In this paper, we attempt to introduce the concept of
Fig. 1 Screenshots of the interaction tool which consists of 2 games: (a)
‘pharmaco-cybernetics’ through the creation of a simple Warfarin Game, and (b) Warfarin Hangman.
interactive tool aimed at improving the knowledge of users
on anticoagulation therapy. In particular, two prototype A pilot usability study was also carried out on a group
games which are targeted at students in the pharmaceutical of pharmaceutical science students at a local educational
sciences and patients on warfarin therapy will be institution to evaluate how well the interactive tool helped
discussed. Ten web animation principles [45], as well as in improving their knowledge of the anticoagulant drug.
user- (UCD), experience- (ECD) and activity-centered Participants were given 15 minutes to answer a
design (ACD) approaches which can be considered in the questionnaire which consisted of questions categorized
designing of pharmaco-cybenetic systems will also be into 3 parts: (a) user demographics, (b) general knowledge
elaborated through a critique of the tool based on a pilot and views on anticoagulation therapy and online
usability survey that was done. Due to space constraints, interaction tools, and (c) feedback and experiences on
only important concepts related to the design frameworks using the interactive tool (warfarin games). A fifth of the
will be discussed. The reader is referred to Appendices 1, time (3 minutes) was dedicated to playing the games. The
2 and 3 for more detailed application summaries. results were then evaluated based on descriptive statistics
and participants’ responses.
A total of 25 participants were recruited in the study,
2. Creation and Evaluation of WarfarINT with a response rate of 92%. Two responses were
excluded from analysis due to incomplete submissions.
The WarfarINT interactive tool was created as an The mean age of the respondents was 19.7+/-0.8 years,
information resource for patients, students and the general and majority were females (87%). All respondents had
public who are interested in learning about anticoagulation previously heard of warfarin before participating in the
therapy. WarfarINT stands for ‘Warfarin INTerative’, and study, but did not know about its tablet strengths and
consists of 2 games (Fig. 1) which provides the interactive interactions.
component for users.
The first is a pill-catching game in which users have to
catch different colored warfarin tablets dropping from the 3. Human-Computer Interaction Frameworks
top of the screen by moving a pill bag with their mouse in
in Pharmaco-Cybernetics
a horizontal direction. Their scores are correlated with the
strength of the tablets that are caught, which in turn are
reflected by the different colors. The second is a hangman 3.1 The User-Centered Design (UCD) Approach
game in which users are supposed to guess a drug, food or
herb that interacts with warfarin. The objectives of this User-centered design (UCD) is a broad term used to
tool are to enable users to correlate the tablet colors with describe design processes in which end-users play a role in
influencing how a product’s design takes shape. Users are
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 5
placed at the center of the design process throughout the “Collect as many warfarin tablets as you can! Move
planning, creation and development phases of the product. your mouse to shift the pill bag left and right. Each tablet
The concepts of visibility, mapping and feedback play color awards you points equivalent to its strength.” –
crucial roles in the UCD approach [46]. Instructions of the pill-catching game.
The principle of visibility states that the user should be “Choose a letter by clicking on it… The letter changes
able to figure out the use of a product based on the to green if your guess is correct, and red if your guess is
visibility of its components. In other words, the product’s wrong.” – Instructions of the hangman game.
parts or components should convey a correct message The use of ‘backup’ text to provide additional details can
regarding its usage [46]. This can be correlated to the help users understand the rationale of the animation better
animation principles proposed by Weir and Heeps provided it is used sparingly. Animations combined with
(Appendix 1) [45]. text and sound can reduce the likelihood of an ambiguity
The product, in this case is the tool consisting of the in interpretation by the user. However, when used
games, should not distract users’ attention from salient inappropriately, it may cause distractions and cognitive
information, but rather, convey its intended message overloads.
across. Users should be drawn to the essential features of Besides textual information, sounds can also support
the animation so that they can focus on the relevant ambiguity and provide feedback to the users regarding
aspects. The graphical user interfaces (GUIs) of the tool certain results. However, it should only be used to enhance
(Fig. 2) are located in the middle of the webpages so that the purpose of the animation. When used inappropriately,
the user’s attention will be focused on the games. The sounds can confuse the user instead of enhancing their
white backgrounds of the webpages are meant as contrasts information-retrieval experience. In the pill-catching game,
to the background of the games, and the titles of the games users would hear a ‘boing’ when they manage to catch a
are kept simple and self-explanatory so that first-time tablet, but if they miss, a ‘splash’ would be heard instead.
users would know what to expect of the tool. This enables the users to discriminate between a score and
a miss, which would be important since the users would
strive to hear more ‘boings’ than ‘splashes’ to gain higher
scores.
The use of appropriate colors and adherence to color
conventions are also important for visibility of the product.
Like sounds, irrelevant color differences can also distract
and mislead users of the product. Colors are more than just
a cosmetic effect. They do not only help convey messages
to users, but also affect the users’ perceptions of depth and
space. The colors of the animated tablets follow the actual
color convention of warfarin tablets in reality with regards
to their tablet strengths. A 3D aspect is also achieved in
the hangman animation through the use of different colors.
A brown surface with red diagonal lines gives the ground
a horizontal effect, and the pole and stool seem to be
situated on the ground. The background is green to
distinguish it from the other objects in the animation, and
to give a sense of calm to the user playing the game, since
green is often associated with safety (e.g. traffic lights) or
nature (e.g. trees).
Humans have limited visual processing capability.
When faced with a visually cluttered display, users tend to
ignore some components in their perceptual field, and this
often impedes the delivery of the intended message. To
avoid clutter of our online tool, the animation screens are
Fig. 2 Graphical user interfaces of the (a) warfarin pill-catching and (b) centralized in the middle of the webpages (Fig. 2). In the
hangman games.
pill-catching game, the title, instructions, and scores, are
In addition, visibility was demonstrated in the games placed on the top left and right corners respectively. The
through short and concise instructions to users on what the button to start and restart the game, indicated by ‘Play
games entail and how to play: Again’, is placed below the ‘Game Over’ message so that
users can click on it to play the game. Similarly, the title
IJCSI
6 IJCSI International Journal of Computer Science Issues, Vol. 3, 2009
and instructions of the hangman game occupy the top half information exposure cannot be determined, the common
of the screen, and the animation of the hangman is located rule of ‘too-much is better than too-little’ can be applied.
just beside the words that users are supposed to guess, so A principle that deserves special mention in this paper is
that they know how many wrong guesses they have made. that of complying with the Co-operative Maxims. Based
Clutter is also minimized as users are allowed to expand or originally on Grice’s Coorperative Principle, Weir and
collapse the categories of drug interactions as appropriate. Heeps have defined them with regards to animation in
Mapping [46], the second principle of UCD, describes the terms of (a) quality (the animator tells/ portrays the truth),
link between one’s intended actions (what one wants to do) (b) quantity (the intended message is adequately conveyed
to actual operations (what appears to be possible). In without use of excess animation), (c) relation (the
animated products, it is crucial for the designer to animations are organized in a meaningful order), and (d)
appreciate the insight of semiotics. Users will be able to manner (the animations are clear and natural, avoiding
play the games if the games can be mapped to processes or ambiguity and disorder). The warfarin tool follows these
objects that are known or familiar to them. The target principles in the form of simple instructions and
audiences of the games are pharmacy/ pharmaceutical information that is easily understood by the layman, with
science students and patients on warfarin therapy, who are the exception of drug names which cannot be simplified,
expected to be familiar with the drug. Furthermore, users so as to avoid misinterpretation and ambiguity. Similarly,
can guess the interactions based on their previous these principles can and should be applied in any tool/
experience of knowing how to play the hangman game. product that are designed for the purpose of providing
Proper positioning and organization of objects in the drug information. The explanations of these ‘Four
games can help users understand how to play the games. Pharmaco-cybernetic Maxims’ are provided in Table 1.
The tool uses natural mapping of the left-right clicks on
the mouse controls that are familiar to users. This leads to Table 1: The ‘Four Pharmaco-cybernetic Maxims’ for designing
pharmacy and/or pharmaceutical science tools.
an immediate understanding of how to use these controls Design Explanation of principle with regards to pharmacy
to play the games. Incorporating these controls in the principle and/or pharmaceutical sciences
games allows for easier manipulations of the various Drug information content provided by the informatics or
animated components such as moving the pill-bag to catch internet tool(s) should be accurate and follow appropriate
Quality
the dropping warfarin tablets, and selecting the alphabets resources for evidence-based therapies (e.g. research
articles, established databases or product information).
of the interacting drug. Gestalt’s law of proximity which
states that ‘related items should be placed closer together Adequate information about the drug or drug therapy is
provided so that users of the tool know enough to minimize
than non-related items’ also applies here. Similarly, Quantity
the likelihood of drug-related problems (e.g. underdose,
information deemed to be of greater importance should overdose, drug interactions).
appear in positions of greater importance on the screen Drug information provided by the tool(s) is/are relevant to
from the user’s perspective. Related items in the games are Relation what the target audience needs to know, and should clarify
grouped together in time, space and shape, such as with their doubts instead of making them more confused.
the warfarin tablets dropping in a vertical direction while Drug information provided by the tool(s) is/are conveyed
clearly in an appropriate manner which avoids ambiguity
the pill bag moves in the opposite horizontal direction; and Manner
and misinterpretation (e.g. layman language for the patient
the hangman animation being grouped side-by-side with and medical jargon for healthcare professionals).
the word of the interacting drug. Users who play the
games will then be able to better remember the warfarin In UCD of products, feedback is largely a crucial
interactions, as well as the tablet strengths. component as it reflects to the user about what action has
For animations, the duration of exposure to users also been done and what result is achieved [46]. Feedback is
affects their ability to interpret and understand the accomplished in the warfarin tool as the user seeing the
information about the product. Too short an exposure time pill bag move in response to his mouse movements, and
will leave the viewer confused, but too long a time can parts of the hangman animation or the letters appearing as
lead to boredom and fatigue. Both games provide an part of the word when he selects wrong or correct
adequate amount of exposure time to users – the pill- alphabets respectively.
catching game lasts less than a minute so that users do not Feedback in animated tools should also follow the
get bored, yet have enough time to learn and correlate the traditional features developed by Walt Disney Studios,
tablets’ colors with their strengths; while users are given which aims to make animations as realistic and
an option to end the hangman game in the middle of entertaining as possible. The ‘Squash and Stretch’ and
gameplay or if they give up guessing the word, or else, ‘Timing and Motion’ aspects are most commonly accepted
frustration will result and lead to the user not wanting to by the public. The former defines an object’s rigidity and
play the game again. Generally, if the correct amount of mass by distorting its shape during an action, and the latter
follows the natural motion of an object such as
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 7
acceleration and deceleration, moving in curved paths, or The results showed that although 75-85% of the
experiencing color and texture changes. Potentially respondents deemed the instructions of the games to be
‘unreal’ aspects of an animated object’s behavior could clear, one respondent actually commented to “Give some
hinder users from interpreting the correct message. instructions on playing the games” as a free-response
‘Squash and Stretch’ in the games (Fig. 3) is demonstrated feedback. This situation could not have been predicted or
by the distorting/ shrinking of the pill bag when the user detected if a usability study had not been carried out on
catches the tablet and the rope becoming taut when the the games. The participants in our pilot study had different
hangman is no longer supported by the stool. On the other requirements and experiences with the games, and this
hand, ‘Timing and Motion’ is seen through the proved to be one of the major limitations of UCD which
acceleration of the dropping tablets and the hangman and can be accounted for by experience-centered (ECD) and
his feet dropping lower when the stool topples. These give activity-centered designs (ACD), discussed in later
users the perceptions of gravity and friction in the sections. Thus, there is a need to involve potential users in
animations, which translates a sense of virtual reality when the environment in which the interactive tool would be
playing the games. used so as to increase its effectiveness, and consequently,
its acceptance and success.
IJCSI
8 IJCSI International Journal of Computer Science Issues, Vol. 3, 2009
and increasing the sizes and color intensities of the tablets The ‘spatio-temporal’ thread describes one entering a
with higher strengths. Providing the interaction effects of state of ‘flow’ as he becomes engrossed in his experience
[50]
the drug, herb or food will also allow the user to . Both games managed to keep the respondents
understand the need of knowing the drug interactions. engrossed in gameplay, with 55% and 70% of the
The reflective level [49] is related to the ‘emotional respondents indicating that their levels of concentration
thread of experience’ by McCarthy and Wright which increased during continuous gameplay of the pill-catching
describes personal meaning derived from use of a product and hangman games respectively. However, some
[50]
. Sixty-five percent of the survey respondents thought comments from the respondents also suggested to “make
that the interactive tool did help them learn about warfarin, the pill catching game more interesting.” This can be done
even though it took a while for the learning to be by splitting the game into varying difficulty levels and an
assimilated. The factors that could probably keep them animated storyline, for example, a virtual patient whose
motivated in playing the games are the high scores in the blood vessels become less blocked due to the blood-
pill-catching game, since they indicate the user’s level of thinning effect of warfarin, resulting in the patient
accomplishment, and he is motivated to better his scores improving from his medical condition. On the other hand,
and learn about the tablet strengths; and the congratulatory only users who have adequate drug vocabulary knowledge
message indicating “[the hangman] is alive!” when the of the warfarin interactions (e.g. pharmacy or medical
user guesses the word correctly. This gives meaning and students) are immersed in a state of flow when playing the
satisfaction to the user when he saves the hangman. hangman game. Patients who might not be as well-versed
However, if he loses, words of encouragement “Don’t give in the interactions might suffer from a ‘disruption of flow’
up!” appear to motivate him to play another round. due to frustration of not getting the correct word. Hints
The ‘sensual thread’ describes the involvement of the can be provided in this case to ease the current steep
human senses in shaping an experience [50]. Both games learning curve of the game.
currently focus on sight and utilize the user’s experience The designing of interactive systems require an
of moving and clicking the mouse to play. Sound effects understanding of how a person experiences the product
which provide feedback when the user catches (‘boing’) or from an interaction-centered viewpoint [51]. Cognitive
misses (‘splash’) a tablet cater to his sense of hearing. user-product interactions require users to focus on the
However, the user plays the hangman game in silence. product at hand, thus users of both games have to learn
Short midi, wav or mp3 files to indicate a win or loss in what their actions will lead to during gameplay. It was
the game can further enhance the user’s experience in this suggested in the survey that the warfarin tablets drop too
case. Mounting the games on other platforms such as quickly in the pill-catching game, and that users could not
personal digital assistants (PDAs) or iPhones can also keep track on their scores without comprising their
provide touch-alternatives and a completely different gameplay. Increasing tablet sizes and/or color intensities
experience to mouse-clicking. can improve the cognitive interaction as users will find it
The ‘compositional thread’ describes how one frames easier to relate the animated tablets to their strengths, since
the many parts that make up one’s whole experience [50]. bigger and more intensely-colored tablets would be worth
According to this principle, the games should be more points. Furthermore, the games currently do not
considered in relation to the rest of the WarfarINT website. account for the fact that users will gain competence over
A common feedback from the survey was the lack of time and probably stop playing. To improve users’
adequate information about the drug. Although this could scalability of experience, splitting the games into varying
be due to the limited time given in the pilot study to difficulty levels will continually challenge users and
explore the rest of the website, this was seen as a provide a different experience each time they play the
‘breakdown’ by the respondents as the games seemed to games. Additional features to allow for customization of
be relatively disjointed from the rest of the website. the backgrounds and interfaces to suit users’ preferences,
Questions such as “how do these things go together” and or mounting the games on a variety of platforms like
“I wonder what will happen if [action occurs]” could not PDAs, mobile phones, and social networking sites (e.g.
have been answered by the users. Thus, an improvement Facebook or MySpace) will not only facilitate expressive
would be to include the warfarin dosing information on interactions and co-experience, but also reinforce the
the same page as the pill-catching game instead of a reflective and emotional threads of users’ overall
separate page, as is the current case. Another suggestion experiences.
from the respondents was to “show image[s] of the food
interaction with the correct word” in the hangman game
for a more positive and added visceral feel to the
experience.
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 9
3.3 The Activity-Centered Design (ACD) through the course of internalization, and is related to the
Approach socio-cultural environment [52-54]. There is currently no
means of knowing whether the user has assimilated the
The ECD approach gives designers an insight to users’ learning objectives of the games. Feedback mechanisms
experiences of the interaction tool. However, it does not such as short quizzes on simple warfarin interactions or
explain how the activity of playing these games affects the doses of different colored tablet combinations can be
user. Activity Theory (AT) describes a framework for incorporated so that the user is able to ‘internalize’ the
understanding how people operate in the world, taking knowledge he has gained from the tool and ‘externalize’
‘activity’ rather than ‘person’ or ‘mind’ as the central unit this knowledge by correctly answering the questions.
of analysis [52-54]. Several other interpretations of AT exist, The principle of tool mediation is the most significant
but we will discuss the online tool based on the principles concept in AT, and it describes how a tool reflects the
described by Kaptelinin (Appendix 2) [53]. accumulation and transmission of social knowledge, and
The principle on unity of consciousness and activity experiences of others who have tried to solve similar
states that the human mind (consciousness) is inseparable problems before to make the tool more efficient [52-54].
from his interaction with the environment (activity) [52,53]. Improvements of the ‘tools’ in the games would also
Users of the online tool know that the tablet colors in the improve the users’ cognitive skills and knowledge on
pill-catching game are related to their strengths, and the warfarin. For example, a pill-box, cupped hand or a mouth
objective of the hangman game is to learn about the to simulate catching the warfarin tablets would better
warfarin drug interactions. However, they may not see the mediate the process of how a patient takes the medication
relevance of knowing the strengths and interactions. Thus, in reality. Similarly, an animated form of the traditional
providing a form of text or storyline would help make ‘pen-and-paper’ hangman can probably provide a more
users aware of the consequences of DRPs such as under- familiar and fun way of learning the warfarin drug
and overdosing, and the severity of a drug interaction with interactions.
warfarin. Lastly, the principle of development is used to
Object-orientedness, in this case, is to educate users on understand how tools are developed into their existing
the warfarin tablet strengths and drug interactions. In a form [52-54]. The underlying concepts of why the games
broad sense, the object in this principle need not be related were developed have been explained throughout the
to physical objects, but includes socially/ culturally various sections of this paper, but it can also be used to
defined properties as well [52,54]. Although the tool fulfils further develop and improve the games. Voice reporting of
its objectives, the significance of the activity itself can be the user’s score status can improve his gameplay so that he
enhanced through making explicit to the user why it is does not need to simultaneously focus on the rapidly
important to know about the tablet strengths and the changing scores and correlating the strengths of the
consequences of the drug interactions. different colored tablets. Similarly, having different
The hierarchical structure of activity is associated with a difficulty levels in the hangman game can also ease the
tri-level scheme describing activities, actions and user’s learning curve.
operations which are oriented towards the goals and
motive of the whole activity [52-54]. This hierarchy differs
in patients and students playing the games. Students would
want to know the tablet strengths and drug interactions to
better prepare for exams, instead of improving their health.
Based on Leontiev’s principles [52], the relationship
between higher and lower objectives of a patient who
undergoes anticoagulant therapy and uses the online tool
is illustrated by Fig. 4. The smooth transition of conscious
actions to subconscious operations when playing the
games orients the user towards the objectives of learning
about warfarin. A breakdown, however, will disrupt the
user’s game playing activity, and may lead to
disorientation of the user or even frustration. An example
would be the shift in alphabet locations when the browser
is resized, resulting in the user trying to find out where to
click the alphabets.
The concept of internalization-externalization states that
our mental processes are derived from external actions Fig. 4 Hierarchy of objectives of a patient on anticoagulant therapy, and
how they are affected by socio-cultural factors.
IJCSI
10 IJCSI International Journal of Computer Science Issues, Vol. 3, 2009
3.4 Pharmaco-Cybernetics from an Ecological management of their health. This can potentially help them
Perspective to adapt to any changes in their dietary habits and
lifestyles, as well as improve compliance, and ultimately,
The Ecological Systems Theory by Urie Bronfenbrenner improve the pharmaceutical care of patients who are on
describes how users interact with their immediate anticoagulant therapy. Healthcare providers, patients and
environments (micro, meso, exo, macro, chrono), and how developers of health information systems should realize
these environments affect the user in a wider context [55]. the importance and know the concepts and related
From a pharmaco-cybernetics perspective, this theory can principles when designing for pharmaco-cybernetics
be applied in the context of users learning about applications. However, understanding how users structure
anticoagulant therapy from the interaction tool (Appendix their individual experiences, immediate environments, and
3). The bi-directional influences of each individual system tasks is just the beginning when designing such products.
on the others can help identify possible avenues for Designers should also take into account how external
improvement, as well as the pitfalls and disturbances in forces such as socio-cultural and inter-personal factors
the activity of using the tool. This warfarin tool also shape a user’s overall experience, attitude and goals in
allows the possibility of creating other larger-scale and using the applications, and through an ecological
more complex interactive tools that will not only perspective so as to cater the interactive tools for a wider
encompass the magnitude of influences across the various audience; as well as how they can be applied to the
environments, but also reduce DRPs by empowering designing of other pharmaco-cybernetics products
patients with the appropriate drug knowledge so that they involving medication therapies.
can better participate in their therapies and management
strategies with their healthcare professionals, and
ultimately improve their health.
4. Conclusion
Developers of healthcare interactive tools often
overlook relevant user characteristics, tasks, preferences
and usability issues, thus resulting in systems or tools that
decrease productivity or simply remain unusable [56].
Medical tools need to be robust and easy to use in a wide
variety of environments [57]. Thus, healthcare applications
must be carefully crafted to ensure that they meet the
standards and models outlined by their target users.
The integration of interactive media and informatics
technologies with the WWW has enabled computational
tools to play an important role in pharma-culture. In this
paper, the concept of ‘pharmaco-cybernetics’ is introduced
through the creation of an interactive tool on oral
anticoagulation therapy. Interactivity was developed in the
form of two games for users to learn about warfarin tablet
strengths and drug interactions. Currently, this tool is
largely based on the principles of UCD and ECD.
However, the potential of incorporating the ACD
approach in the designing of this tool is definitely
attractive, and can lead to better quality healthcare tools
for other chronic medication therapies. Prototype sketches
of how the games can be improved in future versions are
provided in Fig. 5. It is hoped that these improved
versions will not only cater towards enhancing the user’s
experience, but also his interactions with the tool. Fig. 5 Prototype sketches of improved versions of the interactive tool
In conclusion, pharmaco-cybernetics can empower consisting of (a) the warfarin pill-catching game and (b) the warfarin
patients with the appropriate knowledge regarding their hangman game.
therapy so that they can better participate in the
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 11
IJCSI
12 IJCSI International Journal of Computer Science Issues, Vol. 3, 2009
[30] H. Leufkens, Y. Hekster, and S. Hudson, “Scenario Love (or Hate) Everyday Things, pp. 63-98, New York,
analysis of the future of clinical pharmacy”, Pharmacy NY: Basic Books, 2004.
World and Science, Vol. 19, No. 4, 1997, pp. 182-185. [50] J. McCarthy, and P. Wright, “The threads of experience”,
[31] T. Westerlund, A. B. Almarsdóttir, and A. Melander, Technology as Experience, pp. 79-104, Cambridge, MA:
“Factors influencing the detection rate of drug-related MIT Press, 2004.
problems in community pharmacy”, Pharmacy World [51] J. Forlizzi, and K. Battarbee, “Understanding experience in
and Science, Vol. 21, No. 6, 1999, pp. 245-250. interactive systems”, Symposium on Designing
[32] T. L. Stedman, Stedman's Medical Dictionary, 28th ed., Interactive Systems. Proceedings of the 5th Conference
Baltimore, Maryland: Lippincott Williams & Wilkins, on Designing Interactive Systems: Processes, Practices,
2005. Methods, and Techniques. DIS '04, 2004, pp. 261-268;
[33] P. Pangaro, “"Getting started" guide to cybernetics”; http://doi.acm.org/10.1145/1013115.1013152 [accessed 3
http://pangaro.com/published/cyber-macmillan.html July 2009].
[accessed 3 July 2009]. [52] V. Kaptelinin, K. Kuutti, and L. Bannon, “Activity theory:
[34] Wikipedia, “Cybernetics”; basic concepts and applications. A summary of a tutorial
http://en.wikipedia.org/wiki/Cybernetics [accessed 3 July given at the east west HCI95 conference”, Lecture Notes
2009]. in Computer Science, Human-Computer Interaction,
[35] American Society for Cybernetics, “Foundations - the Vol. 1015, 1995, pp. 189-201.
subject of cybernetics: defining 'cybernetics'”; [53] V. Kaptelinin, “Activity theory: implications for human-
http://www.asc-cybernetics.org/foundations/definitions.htm computer interaction”, Context and Consciousness:
[accessed 3 July 2009]. Activity Theory and Human-Computer Interaction, B.
[36] P. A. Corning, “Synergy, cybernetics, and the evolution of A. Nardi, ed., pp. 103-116, Cambridge, MA: MIT Press,
politics”, International Political Science Review, Vol. 17, 1996.
No. 1, 1996, pp. 91-119. [54] V. Kaptelinin, and B. A. Nardi, “Activity theory in a
[37] 'Psycho-cybernetics' Author, “Plastic surgeon tries to heal nutshell”, Acting with Technology: Activity Theory and
'inner scars'”, Los Angeles TimesB5, 1973, pp. B5-1. Interaction Design, pp. 29-72, Cambridge, MA: MIT
[38] Wikipedia, “New cybernetics”; Press, 2006.
http://en.wikipedia.org/wiki/New_cybernetics [accessed 3 [55] D. Paquette, and J. Ryan, “Bronfenbrenner’s Ecological
July 2009]. Systems Theory”;
[39] F. Geyer, “The challenge of sociocybernetics”, http://pt3.nl.edu/paquetteryanwebquest.pdf [accessed 3
Kybernetes: The International Journal of Systems & July 2009].
Cybernetics, Vol. 24, No. 4, 1995, pp. 6-32. [56] C. M. Johnson, T. R. Johnson, and J. Zhang, “A user-
[40] P. C. Adams, “Cyberspace and virtual places”, centered framework for redesigning health care interfaces”,
Geographical Review, Vol. 87, No. 2, 1997, pp. 155-171. Journal of Biomedical Informatics, Vol. 38, No. 1, 2005,
[41] R. Trappl, “The cybernetics and systems revival”, in 14th pp. 75-87.
European Meeting on Cybernetics and Systems [57] R. Gagnier, “User centered design of medical devices:
Research (EMCSR'98), University of Vienna, Austrian managing use related hazards”, Macadamian White
Society for Cybernetic Studies, February 1998, p. Preface. Papers, n.d.; http://www.macadamian-
[42] W. Gibson, Neuromancer (Special 20th Anniversary usability.com/resources/whitepapers/Maskery-
Edition), Hardcover ed.: Ace Books, 2004. designing_medical_devices.pdf [accessed 10 November
[43] Wikipedia, “The Matrix”; 2008].
http://en.wikipedia.org/wiki/Matrix_movie [accessed 3 July
2009]. Kevin Y.-L. Yap (B.Sc. in Pharmacy (Hons), M.Eng., Sp. Dip.
[44] Wikipedia, “Cyberspace”; Digital Media Creation) is currently a Ph.D. candidate in the
http://en.wikipedia.org/wiki/Cyberspace [accessed 3 July Department of Pharmacy, National University of Singapore, and a
registered pharmacist in Singapore. He has worked as a
2009]. pharmacist in the hospital and community settings, as well as an
[45] G. R. S. Weir, and S. Heeps, “Getting the message across: academic facilitator in the biomedical sciences, based on the
ten principles for web animation. ”; problem-based learning pedagogy. His research interests lie in the
http://eprints.cdlr.strath.ac.uk/2513/ [accessed 3 July application of informatics, digital media, interactive and web
2009]. technologies in clinical pharmacy practice, particularly with regards
[46] D. A. Norman, “The psychopathology of everyday things”, to pharmaceutical care and the solving of drug-related problems;
and he has presented in various international conferences and
The Design of Everyday Things, pp. 1-33, USA: Perseus
published several papers in this area. He is a member of the
Publishing, 2002. Pharmaceutical Society of Singapore, American Association for
[47] J. Preece, Y. Rogers, and H. Sharp, Interaction design: the Advancement of Science, and the Healthcare Information and
beyond human-computer interaction, 1st ed., New York, Management Systems Society. He has also been featured in
th
NY: John Wiley & Sons Inc., 2002. Marquis Who’s Who in Science and Engineering (10 ed.), and in
th
[48] D. A. Norman, “Emotion and design: attractive things work Medicine and Healthcare (7 ed.).
better”, Interactions, Vol. 9, No. 4, 2002, pp. 36-42. Xuejin Chuang, Alvin J.M. Lee, Raemarie Z. Lee, Lijuan Lim
[49] D. A. Norman, “Three levels of design: visceral, and Jeanette J. Lim were undergraduates, while R. Nimesha and
behavioral, and reflective”, Emotional Design: Why We Kevin Yap were postgraduates in the National University of
Singapore during the time in which the pilot usability study was
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 13
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 14
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 15
Faramarz Valafar [4] has discussed pattern recognition Fig. 1 Inbound link of page A.
techniques in data analysis. Clustering is one of the most A set of five web pages is assumed: A, B, C, D, E. The
commonly used recognition techniques. Data are grouped initial probability is distributed evenly among these pages.
into clusters or groups in clustering. K-means clustering Therefore, each of the pages will get a PageRank of 1.0/5.
[2] is a widely used algorithm for data clustering. In k- It means,
means similar algorithm patterns are partitioned into the PR(A) = PR(B) = PR(C) = PR(D) = PR(E) = 0.2
same group. All the data are classified into any of the k (i)
clusters or classes. Then the mean inter and intra-class
distances are determined. The last step is to maximize the Now suppose the scenario as depicted in figure 1:
intra-class distance and minimize the inter-class distance.
Page A has inbound links from Page C, D and E. Thus, the
This is an iterative procedure where data is moved from
PageRank of page A
one cluster to another. This process continues until
optimized distances of intra-class and inter-class are
found. PR(A) =PR(C) + PR(D) + PR(E) (ii)
In pattern recognition different techniques are applied for Page C has other outbound links to page E, page D has
similarity matching. For this work it is necessary to other outbound links to B, C and E as depicted in figure 2.
discover optimized techniques and algorithms for
similarity matching, fault classifying and fault cause E
detecting.
D
C E C
4. Ranking Algorithms
A PR ( j )
PR (i) =∑
C E
(v)
jεS i Nj
Where,
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 16
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
PR(i ) = PageRank of page i with. If Levenshtein Distance is applied to find out the
similarity of faults it would not give a meaningful result as
PR( j ) = PageRank of any other pages except the positions of the strings should not have importance.
page i. That is why this technique will not be used in this study.
N j = Number of pages in the set
Damerau-Levenshtein Distance
jεS i = Inbound pages linking to page i
Damerau-Levenshtein distance comes from Levenshtein
distance that counts transposition as a single edit
PageRank algorithm is mainly used for internet operation. The Damerau-Levenshtein distance is equal to
applications to find the rank of a page. The basis of the the minimal number of insertions, deletions, substitutions
algorithm is that the rank of a page depends on the and transpositions needed to transform one string into the
inbound links of the other pages. To apply this technique other.
we need to compare links among the pages with the links
among the features of the fault. But this study requires the Kukich [5] described several edit distance algorithms
ranking of features according to their importance. This which use Damerau-Levenshtein distance. It has been
makes PageRank algorithm inappropriate for this project. proved that the use of Damerau-Levenshtein metric to
calculate the similarity between two words is a slow
5. Similarity Matching process. For this reason this method is not well-suited for
similarity matching in this project.
This chapter describes the similarity matching techniques
for strings. Using these techniques, a concept is proposed Needleman – Wunsch Distance
to search similar faults when the symptoms of a fault are
provided. The Levenshtein distance algorithm assumes that the cost
of all insertions, deletions, substitutions or conversions is
equal. However, in some scenarios this may not be
Edit distance is a common term in matching algorithms.
desirable and may mask the acceptable distances between
The word distance is used to compare different data for
inputs.
similarity. Edit distance is a measure to estimate
differences between input elements. Different methods to Needleman-Wunsch has modified Levenshtein distance
calculate edit distance exist: algorithm to add cost matrix as an extra input. This matrix
Levenshtein Distance structure contains two cost matrics for each pair of
characters to convert from and to. The cost of inserting
Levenshtein distance is named after the Russian scientist
this character and converting between characters is listed
Vladimir Levenshtein, who devised the algorithm in 1965.
in this matrix.
The Levenshtein distance between two strings is given by
the minimum number of operations needed to transform This approach is not appropriate for use in this study’s
one string into the other, where an operation is an similarity matching for the same reason stated in
insertion, deletion, or substitution of a single character. Levenshtein approach.
Levenshtein distance (LD) is a measure of the similarity Hamming Distance
between two inputs: the source s and the target input t.
The distance is the number of deletions, insertions, or The Hamming distance [6] H is defined for the same
substitutions required to transform s into t. For example, length inputs. For two inputs s and t, H(s, t) is the
If s is "math" and t is "math", then LD(s,t) = 0, because no number of places in which the two strings differ, i.e., have
transformations are needed. different characters.
If s is "math" and t is "mats", then LD(s,t) = 1, because
one substitution (change "h" to "s") is sufficient to Hamming Distance is used in information theory. This
transform s into t. method can not be applied in similarity matching for
The more different the inputs are, the greater the automotive faults since Hamming Distance only considers
Levenshtein distance is. the differences among the two inputs.
Insertion, deletion and substitution are the main criteria for Weighted Edit Distance
determining Levenshtein Distance. The position of a
character plays an important role to determine the
distance. In this study, the description of a fault is dealt
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 17
6. Similarity Determination
Input Database:
The aim of this section is to propose an algorithm to use This is the database which is already stored in the system.
for similarity matching in text queries. The procedures of This is compared with the user provided fault symptoms.
this algorithm are as following
Attachment Defect ID Fault Characteristics
A text (query) T is represented by multidimensional 32 Display ON Signal will be
vector: sent, but Display remains dark
Y 40 Preconditions: radio hu
F(T) = (F1(T), F2(T), …Fk(T)) (occurrence vector) message
k = no. of distinct term occurring in database (non-stop 41 radio: radio. message;
word) audio hu radio message message
42 Preconditions: message->
hu -> audio
Function of frequency of the i-th term in T, Y 44 preconditions: hu sds sdars
1⎛ ⎞
T message message radio radio
tf i
Fi (T ) = ⎜⎜1 + ⎟ log N 45 radio hu message message
2 ⎝ max tf i T ⎟ ni
⎠ message
46 radio hu no message
where, message
T 47 radio no hu message
tf i message no sds
= frequency of the i-th term in T
T
48 radio hu message message
max tf i no message sds
= no. of database documents where the most 49 radio hu
frequent term of T occurs 50 radio
N = no. of database entries 51 radio radio
52 radio radio radio
ni = no. of entries where the i-th term occurs
53 radio does not receive
message from headunit
The cosine similarity measure between a query (A) and a Result Analysis:
stored document (B) is defined as:
Below is the graphical representation of outputs for
determining fault similarities corresponding to user
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 18
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
similarity
matching is shown in figure 3. 60
40
20
radio hu
0
40 41 42 44 45 46 47 48 49 50 51 52 53
100
fault id
80
similarity %
60
40 Fig. 5 Fault similarities with symptom radio dvd message.
20
The similarities of fault symptom radio dvd message are
0
61% (id 41) with the database fault radio: radio. message;
40 41 42 44 45 46 47 48 49 50 51 52 53
audio hu radio message message and 56% (id 45) with the
fault id database fault radio hu message message message. The
result of this fault matching is shown in figure 5.
Fig. 3 Fault similarities with symptom radio hu. The similarities of fault symptom radio dvd are 58% with
database faults radio (id 50) and radio radio(id 51) and
The similarities of fault symptom radio hu message are radio radio radio (id 52). The result of this fault matching
100% (id 40) with database fault radio hu and 84% (id 41) is shown in figure 6.
with database fault radio: radio. message; audio hu radio
message message and 84% (id 45) with database fault
radio hu message message messaeg. The result of this fault radio dvd
matching is shown in figure 4.
100
80
similarity %
radio hu message
60
100 40
80 20
similarity %
60 0
40 40 41 44 45 46 47 48 49 50 51 52 53
20 fault id
0
40 41 42 44 45 46 47 48 49 50 51 52 53
Fig. 6 Fault similarities with symptom radio dvd.
fault id
Based on the above result analysis it can be concluded that
the similarity of a user provided fault is higher if the
Fig. 4 Fault similarities with symptom radio hu message. symptom of the fault matches more closely with any
database fault. It satisfies the requirement of finding
similar faults for a fault symptom.
7. Conclusion
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 19
References
[1] Eric Brill, Jimmy Lin, Michele Banko, Susan Dumais,
Andrew Ng. Data-Intensive Question-Answering. In the
proceedings of the Tenth Text Retrieval Conference (TREC
2001), Maryland,November 2001.
[2] Tapas Kanungoy, David Mountz, Nathan Netanyahu,
Christine Piatko, Ruth Silverman, Angela Wu. A Local Search
Approximation Algorithm for k-Means Clustering. 18th Annual
ACM Symposium on Computational Geometry (SoCG’02),
Barcelona, Spain, June 2002.
[3] Shmuel Brody. Cluster-Based Pattern Recognition in Natural
Language Test. Master Thesis. August 2005.
[4] Faramarz Valafar. Pattern Recognition Techniques in
Microarray Data Analysis: A Survey. Special issue of Annals of
New York Academy of Sciences, Techniques in
Bioinformatics and Medical Informatics. (980) 41-64,
December 2002.
[5] Karen Kukich. Techniques for automatically correcting
words in text. ACM Computing Surveys, 24(4):377–439,
December 1992.
[6] Yu Tao; Muthukkumarasamy, V.; Verma, B.; Blumenstein,
M. A texture extraction technique using 2D-DFT and Hamming
distance. Fifth International Conference on Computational
Intelligence and Multimedia Applications, 2003. ICCIMA
2003.
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 20
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 21
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 22
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
Now for the retrieval purpose the user select the query
patch and on the basis of its class number the distance Figure 2: Water bodies
between the query patch with the other images of that
class is calculated and images are retrieved.
3. Experimental Plan
For our experiments, we use 3 LISS III + multi-spectral
satellite images with 23.5m resolution. We choose to
support 4 semantic categories in our experimental system,
namely mountain, water bodies, vegetation, and residential
area. In consultation with an expert in satellite image
analysis, we choose near-IR (infra-red), red and green
bands as the three spectral channels for classification as
well as display. The reasons for this choice are as follows. Figure 3: Open Land with vegetation
Near-IR band is selected over blue band because of a
somewhat inverse relationship between a healthy plant’s
reflectivity in near-IR and red, i.e., healthy vegetation
reflects high in near-IR and low in red. Near-IR and red
bands are key to differentiating between vegetation types
and states. Blue light is very abundant in the atmosphere
and is diffracted all over the place. It therefore is very
noisy. Hence use of blue band is often avoided. Visible
green is used because it is less noisy and provides unique
information compared to Near IR and red. The pixel
dimensions of each satellite image are used in our
experiments are 720x540, with geographic dimensions
being approximately 51.84Km× 38.88Km. The choice
patch size is critical. A patch should be large enough to
encapsulate the visual features of a semantic category,
while being small enough to include only one semantic Figure 4: Buildings
category in most cases. We choose patch size 100×100
pixels. We obtain 80 patches from all the images in this
manner. These patches are stored in a database along with
the identity of their parent images and the relative location
within them. Ground truth categorization is not available
readily for our patches.
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 23
5. References
[1] Li, J., Wang, J. Z. and Wiederhold, G., “Integrated
Region Matching for Image Retrieval,” ACM Multimedia,
2000, pp. 147-156.
[2] Flickner, M., Sawhney, H., Niblack, W., Ashley, J.,
Huang, Q., Dom, B., Gorkani, M., Hafner, J., Lee, D.,
Petkovic, D., Steele, D. and Yanker, P., “Query by image
Figure 5: Vegetation and Mountain and video content: The QBIC system,” IEEE Computer,
28(9), 1995, pp. 23-32
[3] Pentland, A., Picard, R. and Sclaroff S., “Photobook:
Contentbased manipulation of image databases”,
International Journal of Computer Vision, 18(3), 1996,
pp. 233–254
[4] Smith, J.R., and Chang, S.F., “Single color extraction
and image query,” In Proceeding IEEE International
Conference on Image Processing, 1997, pp. 528–531
[5]Gupta, A., and Jain, R., “Visual information retrieval,”
Comm. Assoc. Comp. Mach., 40(5), 1997, pp. 70–79
[6]Eka Aulia, “Heirarchical Indexing for Region based
image retrieval”, A thesis Submitted to the Graduate
Faculty of the Louisiana State University and Agricultural
and Mechanical College.
[7]Shi, J., and Malik, J., “Normalized Cuts and Image
Segmentation,” Proceedings Computer Vision and Pattern
Recognition, June, 1997, pp. 731-737
Figure 6: CBIR System [8]Smith, J., “Color for Image Retrieval”, Image
Databases: Search and Retrieval of Digital Imagery, John
Wiley & Sons, New York, 2001, pp. 285-311
[9]Zhang, R. and Zhang, Z., (2002), “A Clustering Based
Approach to Efficient Image Retrieval,” Proceedings of
the 14th IEEE International Conference on Tools with
Artificial Intelligence, pp. 339
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 24
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 25
the customer with a set of alternative solutions for each • Recommendation: this is a list of N items Ir (Ir is a
requested transaction. These solutions are constructed subset of I) that the user will like most (the
through the use of a specially developed algorithm for recommended list must contain items not already
retrieving optimal and sub-optimal solutions. Moreover, selected by the user). This outcome of CF algorithms
through a dedicated recommender agent [9, 22], which is also known as Top-N recommendation [20].
builds on Web Services concepts [26], the system assists
On the other hand, KBR attempts to suggest objects
the customer further towards making the appropriate
based on inferences about a user’s needs and preferences.
decisions.
In some sense, all recommendation techniques could be
The remainder of this paper is structured as follows:
Section 2 reports on background issues from the area of described as doing some kind of inference. Knowledge-
recommender systems, paying particular attention to based approaches are distinguished in that they utilize
recommendation approaches. Section 3 describes the basic functional knowledge; in other words, they have
aspects of our approach, which concern the selection of knowledge about how a particular item meets a particular
transportation plans and the evaluation of alternative user need and can therefore reason about the relationship
solutions. Section 4 focuses on issues raised during the between a need and a possible recommendation. The user
integration of the recommendation module, the profile can be any knowledge structure that supports this
formulation of the recommendation policy, and the
inference. In the simplest case, as in Google, it may simply
exploitation of software agents and Web Services
technologies. Finally, Section 5 concludes the paper and be the query that the user has formulated. The Entrée
highlights future work directions. system and several other recent systems [23], employ
techniques from case-based reasoning for knowledge-
based recommendations.
2. Related Work The knowledge used by a knowledge-based
recommender system can take many forms. Google uses
The most widely adopted recommendation techniques are information about the links between web pages to infer
Collaborative Filtering (CF) and Knowledge Based popularity and authoritative value [1]. Entrée uses
Recommendation (KBR), each one possessing its own knowledge of cuisines to infer similarity between
strengths and weaknesses. Collaborative Filtering (CF) restaurants. Utility-based approaches calculate a utility
[17, 18] is the most commonly used recommendation value for objects to be recommended; in principle, such
technique to date. The basic idea of CF-based algorithms calculations could be based on functional knowledge.
is to provide item recommendations or predictions, based However, existing systems do not use such inference
on the opinion of other like-minded users. In a typical CF mechanisms, thus requiring users to do their own mapping
scenario, there is a list of m users U = {u1, u2, …, um} and between their needs and the features of products, either in
a list of n items I = {i1, i2, …, in}. Each user ui is associated the form of preference functions for each feature, as in the
with a list of items Iui, for which the user has expressed case of Tête-à-Tête, or answers to a detailed questionnaire,
his/her opinion. Opinions can be explicitly given by the as in the case of PersonaLogic [2]. Knowledge-based
user as a rating score (within a certain numerical scale), or recommender systems are prone to the drawback of all
implicitly derived from transaction records (by analyzing knowledge-based systems: the need for knowledge
timing logs, mining web hyperlinks and so on). For a acquisition. More specifically, there are three types of
particular user ua, the task of a collaborative filtering knowledge that are involved in such systems:
algorithm is to find an item likeness that can be of two
forms: • Catalog knowledge: Knowledge about the objects
being recommended and their features. For example,
• Prediction: this is a numerical value, Pi, expressing the system should know that “Gasoline” is a type of
the predicted likeness of item i (i does not belong to “Fuel”.
Iua) for the user. The predicted value is within the • Functional knowledge: The system must be able to
same scale (e.g. from 1 to 5) as the opinion values match the user’s needs with the object that might
provided by ua [19]. satisfy those needs. For example, a recommendation
module should know that the transportation of toxics
to the above customer’s request is to involve both X and Y and fragment
require a higher safety level.
the intended overall itinerary to the related sub-routes. It is also noted that
these carriers may be associated with diverse transportation means, such • User knowledge: To provide good recommendations,
as trains, trucks, ships and airplanes. the system must have some knowledge about the user.
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 26
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
This might take the form of general demographic offers the possibility for a user-customized plan definition.
information or specific information about the need for Such a plan may combine parameters from all the above
which a recommendation is sought. four plans. The selection of one of these plans will
Of these knowledge types, the last one is the most influence the recommendation process of our approach for
challenging, as it is an instance of the general user- the particular user.
modelling problem [25]. Despite this drawback,
knowledge-based recommendation has some beneficial
characteristics. First of all, it is appropriate for casual
exploration, because it demands less from the user
(compared to the utility-based recommendation).
Moreover, it does not involve a start-up period during
which its suggestions are of low quality. On the other
hand, a knowledge-based recommender cannot “discover”
user niches, the way collaborative systems can. However,
it can make recommendations as wide-ranging as its
knowledge base allows.
Alternative techniques have been proposed in the
literature in order to handle the above issues [11]. Having Figure 1: Transaction’s request interface
thoroughly considered their pros and cons, our approach
follows a hybrid recommendation technique. Generally As shown in Figure 1, which depicts the system’s interface
speaking, CF and KBR techniques can be combined in for handling a user’s request, the user provides input about
hybrid recommendation systems in order to improve their the loading and delivery terminals, the quantity to be
performance. Most commonly, CF is combined with some transported, expresses his/her preferences concerning
other technique in an attempt to minimize or avoid the maximum cost and duration of the transaction, and selects
ramp-up problem [3]. the desired transportation plan. By selecting the “user-
defined” plan, a new window appears, allowing the user to
adjust the criteria (cost, duration, safety, dependability) of
3. The Proposed System his/her transportation request.
3.1 Transportation plans and evaluation of alternative Table 1: Selection criteria for the alternative transportation plans
solutions (safety and dependability take values from the set {very low, low,
average, high, very high}).
• Express
• Economic Economic Min Any Any Any
• Safe
• Dependable
• User Defined Safe Any Any >Average ≥Low
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 27
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 28
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
100%
90%
80%
Coefficients'
Significance
70%
60%
50%
40%
30% Figure 4: Solutions produced by the system.
20%
10%
0%
1 2 3 4 5 6 7 8 9 10 11
Number of Iteration
Duration Coef
Cost Coef
4. Integrating a Recommendation Module
4.1 A Hybrid Recommendation Methodology
Figure 3: Weight coefficients’ variation.
The recommendation procedure begins immediately after
This process is described in pseudo-code as follows: the abovementioned construction of the alternative
{ solutions. It is a complex process which is carried out in
costCoef Å 0.0; three basic phases, which are:
durationCoef Å 1.0; • the evaluation of the carriers and the transactions
step Å 0.0; data;
while step ≤ 1.0 calculate • the exploitation of transaction data through a data
{ mining process, and
costCoef Å step; • the recommendation methodology selection or
durationCoef Å 1-step; synthesis.
weight[i][j] Å costCoef*Wcost + At the beginning of the process, the system stores all
durationCoef*Wduration; the appropriate data that are submitted by the user and are
perform shortest path algorithm; related with pending or completed transportation
step Å step + 0.1; transactions. These data are of significant importance and
} will be further exploited by the data mining process.
} Moreover, in this phase the user evaluates (i.e. assigns a
score to) the carrier(s) involved in a transaction through an
The outcome of the above process is then presented to appropriate interface.
user. As shown in Figure 4 (which depicts an instance of The second phase of recommendation concerns the
the related system interface), the optimal routes for a data mining process. Data mining is a useful decision
transportation request from Athens to Patra have been support technique, which can be used to find trends and
retrieved (after a related request). The basic characteristics regularities in big volumes of data. At this phase,
of each route are presented in the main table of the web transactions data are gathered through knowledge
interface. By selecting the “View Details” option, the user construction processes. In our case, the data mining
is able to receive an analytical description of the sub- process constructs a model from the recommendation
routes contained in each itinerary, as well as their module’s database that may produce well defined
corresponding characteristics. Solutions at this phase are knowledge rules. This procedure is performed through
ranked by default according to the cost; in any case, users SQL queries performed on the transactions’ tables. After
may request alternative rankings by clicking on the the completion of this process, the constructed knowledge-
corresponding column header. based rules participate in the production of knowledge-
based recommendation data that will be evaluated and
synthesized in the last phase of recommendation.
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 29
The last phase of recommendation refers to the Table 2: Recommendation Module’s Database Model
selection or synthesis of the appropriate recommendation
technique. This objective will be reached through the Table Name Description
definition of well structured rules that will be applied for
each transaction. The Recommender Agent of our system
Transactions Transactions in progress
takes the initiative to select the most appropriate
recommendation technique. For example, for a particular
Transaction’s Subroutes Transactions sub-routes in progress
itinerary from point i to point j, taking into consideration
that the customer has selected a certain plan, a rule for the
specific itinerary could lead to the recommendation of a Transactions _Rating Completed Transactions’ evaluation
carrier that is different than the one suggested by the CF
technique, based on the carriers’ evaluation process Carriers_Rating Carrier evaluation with completed
described earlier in this section. The recommendation
methodology described above is graphically presented in Users_Reliability Customers reliability evaluation
Figure 5, through a data flow diagram.
Temp_Transactions Proposed transaction itineraries
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 30
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
procedure, basically due to the fact that a modular solution Ci,t j = The carrier’s score according to time, for the
may involve two or more carriers. It is obvious that a transportation from point i to j.
transaction can receive an overall negative evaluation,
C si, j = The carrier’s score according to safety, for the
while - at the same time - a specific part could have been
transportation from point i to j.
completed quite satisfactorily. The evaluation of a
transaction is based on a set of criteria such as cost, Ci,r j = The carrier’s score according to dependability, for
duration, safety, dependability, average score of a carrier, the transportation from point i to j.
itinerary’s popularity and number of transloadings [15]. Tt = The transaction’s score according to time.
Taking into consideration all the above issues, we define
the calculation formula of the overall score Oi, j of each
total
( ) Ts = The transaction’s score according to safety.
transaction from point i to point j (for each sub-route of Tr = The transaction’s score according to dependability.
the itinerary). It is:
Oi,total
j = Oi,t j + Oi,s j + Oi,r j (5) The expression avg(x) refers to the average value of the
element x in the database, and the variables a,b,c are
∑
j
O i, j =
final
(6) to time, safety and dependability respectively. Having
i, j = 1 f S, E
defined the detailed scores for each sub-route, we
where Oi , j , Oi , j , Oi , j represent the score of the time,
(O )
t s r
total
safety and dependability, respectively, for the calculate the overall score S, E for the proposed
transportation from point i to point j . The variable itinerary from point S (start) to point E (end).
fS,E represents the number of transloadings of each
proposed solution and is considered as a negative factor,
n
⎧ O i,t j + O i,s j + O i,r j ⎫
assuming that a large number of transloadings could evoke
O to ta l
S,E = ∑ ⎨ ⎬ (11)
i, j = 1 ⎩ (a + b + c ) * n ⎭
damage in the product and increase the transaction’s
completion time. The number of transloadings is related to
the number of sub-routes (n) of each itinerary. It is:
For the calculation of ( O ) we
total
S,E do not take into
consideration the proposed cost of a transaction, due to the
fS, E = n - 1, n > 1 (7) fact that the system evaluates it through its normalization.
The evaluation of the cost is performed through the
Each one of the detailed scores is calculated according to formula:
the score that has been assigned to the carrier and each
cost i, j
sub-route. It is: Oi,cost
j =
(
min cost i, j ) (12)
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 31
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 32
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
services it performs are visible and accessible to other the future (it will constitute a services repository). It is
software applications. A Web Service can be discovered noted that it is not necessary for all these services to be
and leveraged by other Web Services, applications, clients, provided through a single server; multiple servers, located
or agents. In other words, Web Services can request in distinct providers, may be used. Finally, our system’s
services from other Web Services, and they can expect to Web Services are message-based. Interaction via message
receive the results or responses from those requests. exchange means that instead of a client invoking
Moreover, Web Services communicate using an easy-to- functionality exposed as a Web Service, it sends a request
implement standard protocol (SOAP). Web Services may to the Web Service to have the functionality invoked [7,
interoperate in a loosely-coupled manner; they can request 8]. In other words, what a Web Service exposes is the
services across Internet and wait for a response [5]. Due to functionality of receiving a message. We have adopted a
the fact that external applications could exploit the generic message interchange, which means that delivery of
proposed recommendation services, the implementation of message content is independent of its format.
the FTMarket’s recommendation module was performed
according to Web Services concepts and standards.
5. Conclusions
This paper has elaborated a series of issues related to the
integration of hybrid recommendation techniques into an
agent–based transportation transactions management
platform. We proposed a hybrid recommendation module
that combines different recommendation techniques in
order to provide the user with more accurate and efficient
suggestions. The overall recommendation process is
coordinated by a software agent, which is responsible for
carrying out multiple tasks, such as coordination of the
recommendation module, selection of alternatives and
knowledge synthesis through the exploitation of different
recommendation techniques and algorithms. The presence
of the Recommender Agent guarantees that the user will be
provided with continuous recommendations, which are
Figure 7: The recommendation module architecture. dynamically updated. Finally, we have exploited concepts
related to Web Services in order to make the proposed
The overall architecture of the FTMarket’s recommendation functionalities accessible from external
recommendation module is illustrated in Figure 7. As applications.
shown, the module is appropriately wrapped in order to Future work plans mainly concern the consideration of
describe the kind of service to be provided. To be easily additional recommendation techniques, such as content–
located by users, such descriptions of services are placed based or model–based techniques and the exploitation of
in a shared public registry. It is through this registry that data mining algorithms in order to enhance the overall
users may look up for the services they need each time (in quality of the recommendations provided. The
any case, a Web Service can be directly accessed if one development of additional (local or remote) Web Services,
knows its URL and WSDL). The correspondent agent that which will be capable of carrying out more complex
needs functions provided by the specific Web Service requests for recommendation techniques synthesis, is
sends the appropriate request as an XML document in a another major concern.
SOAP envelope. This protocol can work across a variety
of mechanisms, either asynchronously or synchronously.
Web Services may make requests of multiple services in References
parallel and wait for their responses. The set of services to [1] S. Brin, L. Page, The anatomy of a large-scale hyper textual
Web search engine, Computer Networks and ISDN Systems
be provided in the FTMarket platform will be increased in
30(1-7) (1998) , pp. 107-117.
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 33
[2] R. Burke, Hybrid Recommender Systems: Survey and Symposium on Mining Answers from Texts and Knowledge
Experiments, User Modelling and User-Adapted Interaction Bases (2002), Stanford, pp. 60-68.
12 (2002), pp. 331-370. [17] M. O’Mahony, N. Hurley, C. Silvestre, Promoting
[3] R. Burke, Integrating Knowledge-Based and Collaborative- Recommendations: An attack on Collaborative Filtering,
Filtering Recommender Systems, Artificial Intelligence for Proceedings of DEXA 2002 Conference, Springer-Verlag
Electronic Commerce, AAAI Technical Report WS-99-01 (2002), Berlin, pp. 494-503.
(1999), pp. 69-72. [18] P. Resnick, N. Iacovou, M. Suchak, P. Bergstrom, J. Riedl,
[4] A. Crauser, K. Mehlhorn, U. Meyer, P. Sanders, A GroupLens: An Open Architecture for Collaborative
Parallelization of Dijkstra's Shortest Path Algorithm, Filtering of Netnews. In Proceedings of CSCW (1994),
Proceedings of 23rd International Symposium, MFCS'98 Chapel Hill, NC.
(1998), Brno, Czech Republic. [19] B.M. Sarwar, G. Karypis, J.A. Konstan, J. Riedl, Analysis of
[5] G. Fox, W. Wu, A. Uyar, H. Bulut, A Web services Recommender Algorithms for E-Commerce, Proceedings of
framework for collaboration and audio videoconferencing, the ACM Conference on e-Commerce, Minneapolis, ACM
International Multiconference in Computer Science and Press (2000), pp. 158-167.
Computer Engineering, Internet Computing (2002), Las [20] B.M. Sarwar, G. Karypis, J.A. Konstan, J. Riedl, Item-Based
Vegas, USA. Collaborative Filtering Recommendation Algorithms,
[6] G. Froehlich, H. J. Hoover, W. Liew, P. Sorenson, Proceedings of the 10th International World Wide Web
Application Framework Issues when Evolving Business Conference (2001), Hong Kong, ACM Press.
Applications for Electronic Commerce, Information Systems [21] J.B. Schafer, J. Konstan, J. Riedl, Electronic Commerce
24(6) (1999), pp. 457-473. Recommender Applications, Journal of Data Mining and
[7] D. Greenwood, M. Calisti, Engineering Web Service - Agent Knowledge Discovery, 5 (1-2) (2000), pp. 115-152.
Integration, IEEE Conference of Systems, Man and [22] W. Shen, D.H. Norrie, An Agent-Based Approach for
Cybernetics (2004), The Hague. Dynamic Manufacturing Scheduling, Proceedings of
[8] E. Hanson, P. Nandi, D. Levine, Conversation Enabled Web Autonomous Agents'98 Workshop on Agent-Based
Services for Agents and e-Business, Proceedings of Manufacturing, Minneapolis (1998), pp. 117-128.
International Conference of Internet Computing, Computer [23] S. Schmitt, R. Bergmann, Applying case-based reasoning
Science Research, Education and Applications (CSREA) technology for product selection and customization in
Press (2002), pp. 791-796. electronic commerce environments, 12th Bled Electronic
[9] N. Jennings, P. Faratin, T.J. Norman, P. O'Brien, B. Odgers, Commerce Conference (1999), Bled, Slovenia.
Autonomous Agents for Business Process Management, [24] K. Sycara, D. Zeng, Coordination of Multiple Intelligent
International Journal of Applied Artificial Intelligence 14(2) Software Agents, International Journal of Cooperative
(2000), pp. 145-189. Information Systems, 5(2-3) (1996), pp 546-563.
[10] N. Karacapilidis, A. Lazanas, G. Megalokonomos, P. [25] B. Towle, C. Quinn, Knowledge Based Recommender
Moraitis, On the Development of a Web-based System for Systems Using Explicit User Models, Knowledge-Based
Transportation Services, Information Sciences, 176(13) Electronic Markets, AAAI Technical Report WS-00-04,
(2006), pp. 1801-1828. AAAI Press (2000), pp. 74 -77.
[11] N. Karacapilidis, L. Hatzieleftheriou, A hybrid framework [26] H. Wang, J. Huang, Y. Qu, J. Xie, Web services: problems
for similarity-based recommendations, Business Intelligence and future directions, Journal of Web Semantics, 1 (2004),
and Data Mining, 1(1) (2005), pp. 107-121. pp. 309–320.
[12] N. Karacapilidis, P. Moraitis, Building an Agent-Mediated [27] A. Lazanas, G. Megalokonomos, Optimizing Alternative
Electronic Commerce System with Decision Analysis Routes Retrieval in an Agent–based Transportation
Features, Decision Support Systems 32(1) (2001), pp. 53-69. Management System. Proceedings of the International
[13] M. Klusch, K. Sycara, Brokering and Matchmaking for Conference on Service Systems and Service Management
Coordination of Agent Societies: A Survey, A. Omicini et al. (ICSSSM 2006), Troyes, France, pp. 1525-1530.
(eds.), Coordination of Internet Agents, Springer (2001), pp.
197-224.
[14] A. Lazanas, C Evangelou N. Karacapilidis, Ontology-Driven Dr. Alexis Lazanas studied Applied Informatics in Athens
Decision Making in Transportation Transactions University of Economic and Business (B.Sc. 1996) and received
his Ph.D. from University of Patras (Greece) in the field of
Management, Witold Abramowicz (ed.), Proceedings of the Recommender Systems, Data Mining and Intermodal
8th International Conference on Business Information Transportation (2008). He worked in Technological Educational
Systems (2005), Poznan, Poland, pp. 228-241. Institute (T.E.I.) of Patras as Scientific Collaborator and as
[15] A. Lazanas, N. Karacapilidis Y. Pirovolakis, Providing Software Developer – Special Analyst in various major companies.
Recommendations in an Agent-Based Transportation Currently he is working as Teacher of Informatics in Greek Public
Education. His research interests are on the areas of Agent-based
Transactions Management Platform, Proceedings of the 8th Information Systems, Data Mining, Web Technologies, Hybrid
International Conference on Enterprise Information Systems Recommender Systems and Intermodal Transportation
(2006), Paphos, Cyprus. Management.
[16] U. Nahm, R. Mooney, Text Mining with Information
Extraction, Proceedings of the AAAI Spring 2002
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 35
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
1. Introduction
2. GEOMETRIC CRITERIA
The world population is currently growing which
implies a remarkable increase in buildings and The evolution of the IEEE 802.11 standard fulfil more
skyscrapers. These are obstacles for Global Navigation and more the constraints allowing the improvement of
Satellite Systems (GNSS) such as the Global Positioning its efficiency in large and more complex environments.
System (GPS). New networks have emerged (UMTS,
GSM, ...) which does not help to reduce the impact of The efficiency of such networks is measured by different
interferences. These factors among others contribute to criteria. Some of those criteria are focused on the
the GPS [1] up to 20 meter loss in accuracy especially network geometry, others on the throughput [7] or on
in urban and peri-urban environments. the interference [8].
During the last ten years the number of users of the A. Gondran and al. [9] provide a geometric indicator for
IEEE 802.11x community has known a remarkable WLAN planning. This indicator is based on the study of
growth and a new positioning solution based on Wi-Fi the covered area by a Basic Service Set (BSS), where a
was born. Some positioning algorithms guaranty an cell relative to one antenna is a set of pixels associated
accuracy of 5 meters such as RADAR[2], Viterbi-like to a given base station. The cell C is defined by:
algorithm [3], Friis and Reference Based Hybrid Model
[4] (FRBHM) [5]. c= {bi , j / F i , j q } (1)
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 44
3.1 FRIIS
A. Gondran and al. adapted this formula to 3-D space
which can be indoor environment such as buildings. The Friis [11] equation is:
(5)
(3) where :
• P R and P T are respectively the Signal Strength
(SS) received and the SS emitted;
Where k presents the floor.
• G R and G T are respectively the receiver and
The geometric indicator regrouping all floor-indicators transmitter antenna gains;
is defined by the following equation:
• is the carrier wavelength;
• d is the distance between the receiver and the
(4 transmitter.
)
(6)
where :
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 43
Y. Wang proves in the paper [15] the possibility to 1- The first step consists in the constitution of a set
approximate the target position by measuring the signal of all visible access points (Fig. 1). The number of
strength. In fact, the signal attenuation between the
transmitter and the receiver allows to determine the visible access points is one of the decisive
mobile position. However, the Friis equation enables to elements on the accuracy of a positioning system.
estimate the distance between the receiver and the
Our needs in the number of visible access points
transmitter in an environment without any obstacles.
Thus, Y. Wang suggest an empirical model based on depend on the dimension of the positioning system.
regression. By comparing the residual among different
At least three APs for a two dimension positioning
degrees polynomials, he decide that a cubic regressive
equation would be adequate for the empirical system and at least four APs for a three dimension
2
model EM : one. If the number of AP is not sufficient, we set
d i = 0.000198 S 3i − 0.025 S 2i 1.14 S i − 14.8 ( automatically the value of the precision of dilution
7) coefficient as infinite. The optimal value is equal to
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 44
We obtain:
(9)
PT ,i G RGT ,i
d i= (10)
4 P R ,i
Where :
Let us suppose S AP = N AP the number of visible P R , i , P T , i ,G R and G T , i are respectively the receiver
Where AP i are the visible access points. The distance d i can be approximated by a Taylor
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 43
(12)
Where and :
X c ,i − X u Y c ,i − Y u
bi , x = , bi , y = ,
ri ri
Z c , i− Z u We obtain:
b i , z= and C P R= H X (16)
ri
2 2 2
ri= X c , i− X u Y c , i− Y u Z c ,i− Z u Where C is a known matrix equal to:
We obtain:
(13) P T ,i G T , i G R
and ci =
4
Where :
1 1
P R , i= −
We suppose that P T , i ,G R and G T , i are fixed P R,i P R,i
parameters. Only P R , i the Signal Strength (SS) received
The G matrix is defined by:
from the AP i is unknown and then estimated. −1
G= H T H (17)
Thus from the equation (5), we obtain:
The Wi-Fi GDOP follows the equation bellow:
PT , i G T , i G R 1 1
d i= − (15)
4 P R,i P R,i DOP = Tr [ G ] (18)
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 44
(19) S= H X (20)
and
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 43
5.3 Analysis
Fig. 6. : The DOP cartography when the mobile is moving in the first floor
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 44
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 43
The third step of our experiments has been carried out to The model presented in this paper may provide the
analyse the efficiency of our model by comparing the guaranty we need. In fact, as shown in the results
real trajectory and the estimated one with Wi-Fi DOP obtained in the previous section, our model illustrates
values (see Fig. 9). The analysis shows that the the positioning system accuracy.
trajectories (the real one and the estimated one) are
more or less similar except when the Wi-Fi DOP is up to The idea consists in the observation of the results of the
eight. model and when the values of this one reach a given
threshold, we inform the user that the position accuracy
is not sufficient and then anticipate a solution to
guaranty the quality and continuity of service.
7. Future Trends
Our model opens and leads to numerous extensions and
perspectives.
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 44
[6] Radar, Sonar and Navigation, IEE Proceedings - Volume infrastructure. In 6th Int. Symp. on Satellite Navigation
147, Issue 5, Oct. 2000 Page(s):259 - 264 Yarlagadda, Technology Including Mobile Positioning and Location
R.; Ali, I.; Al-Dhahir, N.; Hershey, J., GPS GDOP metric Services, number paper 54, Melbourne, July 2003. CD-
Radar, Sonar and Navigation, IEE Proceedings - Volume ROM proc.
147, Issue 5, Oct. 2000 Page(s):259 - 264 . [16] Matteo Cypriani, Frédéric Lassabe, Soumaya Zirari,
[7] Ling X., Yeung K.L., ?Joint access point placement and Philippe Canalda, François Spies. Open Wireless
channel assignment for 802.11 wireless LANs?, IEEE Positioning System : un système de géopositionnement par
Wireless Communication and Networking Conference, pp. Wi-Fi en intérieur. JDIR, belfort, France, 2009.
1583-1588, 2005. [17] M. Cypriani, F. Lassabe, S. Zirari, P. Canalda, and F.
[8] Amaldi E., Capone A., Cesana M., Malucelli F., Spies, Open wireless positioning system, Université de
Optimizing WLAN Radio Coverage, IEEE International Franche-Comté, Tech. Rep. RT2008-02.
Conference on Communications 2004, 1, pp.180-184,
2004 Soumaya Zirari was born in 1981. She received her diploma in
[9] Gondran, A.; Baala, O.; Caminada, A.; Mabed, H., "3-D engineering in 2006. She is preparing her Ph.D Thesis at the
Computer Science Laboratory at the University of Franche-ComtŽ
BSS geometric indicator for WLAN planning" Software,
in France, to be defended the 1st semester of 2010. She is
Telecommunications and Computer Networks, 2007. focusing on hybrid location-based services and service continuity.
SoftCOM 2007. 15th International Conference on Volume
, Issue , 27-29 Sept. 2007 Page(s):1 – 5 Dr Philippe Canalda got M.Sc. and Ph.D. Degrees in computer
[10] H. Mabed, A. Caminada, Geometric criteria to improve science from the University of OrlŽans (France) in 1991 and 1997,
the interference performances of cellular network, IEEE respectively. He worked at INRIA Rocquencourt from 1991 to 1996
on the automatic generation of optimizing and parallel n-to-n cross-
Vehicular Technology Conference, Montreal. Sept. 2006. compilers. From 1996 to 1998, he worked as Research Engineer in
[11] S. Zirari, P. Canalda, and F. Spies. Modelling and the Associated Compiler Expert start-up factory at Amsterdam, The
Emulation of an Extended GDOP For Hybrid And Netherlands. Then he worked 2 years at LORIA on the
Combined Positioning System. In ENC-GNSS'09, synchronisation of cooperative process fragment, based on
European Navigation Conference - Global Navigation workflow model, and applied to ephemeral enterprise. Since 2001,
he is an Associate Professor at the Computer Science Laboratory
Satellite Systems, Naples, Italy, May 2009 (LIFC, EA 4269) at the University of Franche-Comté in France. His
[12] S. Zirari, P. Canalda, and F. Spies. A Very First research topics deal with, on the one hand mobility services and
Geometric Dilution Of Precision Proposal For Wireless wireless positioning, and on the other hand on robust and flexible
Access Mobile Networks. In SPACOMM'09, The First optimizing algorithms based on graph, automata and rewriting
International Conference on Advances in Satellite and theories..
Space Communications, Colmar, France, July 2009
Prof. François Spies received his Ph.D. and the French
[13] H. T. Friis, A note on a simple transmission formula, “Accreditation to supervise research” Degrees in 1994 and 1999,
Proc. IRE, pp. 254-256, 1946. (NOAA), Environmental respectively. He was an Associate Professor at the Computer
Technology Laboratory (ETL), in Boulder, Colorado Science Laboratory at the University of Franche-Comté in France
[14] Inc Interlink Networks. A practical approach to from 1996-1999. Since 1999, he has held a Professor position at
identifying and tracking unauthorized 802.11 cards and the University of Franche-Comté. Currently he is focusing on
managing video streams on wireless and mobile architecture.
access points. Technical report, 2002. Researches on, cooperative video cache strategies including
[15] Y. Wang, X. Jia, and H.K Lee. An indoors wireless mobility and video quality levels, transport, congestion control and
positioning system based on wireless local area network quality of service of video streams are the main developed topics.
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 45
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 46
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
"an" (sandhi is, however, reflected in the writing English l-sandhi [3] involves an allophonic alternation
system of Sanskrit and Hindi). External sandhi effects in alveolar contact for word-final /l/ in connected
can sometimes become morphologized. Most tonal speech [4]. EPG data for five Scottish Standard English
languages have Tone sandhi, in which the tones of and five Southern Standard British English speakers
words alter according to pre-determined rules. For shows that there is individual and dialectal variation in
example: Mandarin has four tones: a high monotone, a contact patterns.
rising tone, a falling-rising tone, and a falling tone. In III PROBLEM DEFINITION
the common greeting nǐ hǎo, both words in isolation
would normally have the falling-rising tone. However,
Developing programs that understand a natural
this is difficult to say, so the tone on nǐ is pronounced
language is a difficult task. Natural languages are large.
as ní (but still written nǐ in Hanyu Pinyin).
They contain an infinity of different sentences. No
The Sanskrit Sandhi engine software is not currently matter how many sentences a person has heard or seen,
available as a standalone application, since its local use new ones can always be produced. Also, there is much
demands the installation of an HTTP server on the ambiguity in a natural language. Many words have
user's host. several meanings and sentences can have different
meanings in different contexts. Compound words are
The Sandhi module[1] developed by RCILTS- created by joining an arbitrary number of existing
Sanskrit, Japanese, Chinese at Jawaharlal Nehru words together, and this can lead to a large increase of
University, New Delhi. RCILTS, JNU is a resource the vocabulary size, and thus also to sparse data
center for Sanskrit language of DIT, Government of problems. Therefore the problem of compound words
India. At JNU work started in three languages viz., poses challenges for many NLP applications. The
Sanskrit, Japanese, and Chinese. Using this module the problem domain, to which this paper is concerned, is
user can get the information about Sandhi rules and breaking up of Hindi compound words into constituent
processes. Sutra number in Astyadhayi and its words. In Hindi, words are a sequence of characters.
description is displayed. User can learn three types of These words are combined with ‘swar’, ‘vyanjan’, and
Svara Sandhi, Vyanjan Sandhi, Hal Sandhi through this matra’s. Hindi has its own rules of Sandhi-vicheda.
Sandhi module Data is in Unicode. Sandhi exceptions They are, however, not so well-defined as, and much
and options are also incorporated. This module takes fewer in number than, the Sanskrit rules. So my
two words as input. First word cannot be null but problem is to break the compound word into
second word can be. A user can input the two words constituent words with the help of rules of ‘Sandhi-
and submit the form to get the result of the given input. vicheda’ in Hindi grammar. My problem is to design a
Graphical User Interface, which accepts input as a
Chinese Tone Sandhi,[2] Cheng and Chin-Chuan Hindi language word (source text) from the keyboard
from California University, Berkeley, Phonology or mouse and break it into constituent words (target
Laboratory faced the problem that English stresses are text). The source text is converted into target text in
interpreted by Chinese speakers when they speak Unicode Format.
Chinese with Engish words inserted. Chinese speakers
in the United States usually speak Chinese with Engish
words inserted. In Mandarin Chinese, a tone-sandhi Compound Word Sandhi-vicheda
rule changes a third tone preceding another third tone ijk/khu ij $ v/khu
to a second tone. Using the tone-sandhi rule, they
designed the experiment to find out hoe English HkkokFkZ Hkko $ vFkZ
stresses are interpreted in Chinese sentences. Stress f’koky; f’ko $ vky;
does not exist in the underlying representations of dohUnz dfo $ bUnz
English phonology. But in studying bilingual
phenomena, the phonetic level is also important. Fry x.ks’k x.k $ bZ’k
(1995) found that when a vowel was long and of high ijes’oj ije $ bZ’oj
intensity, listeners agreed that the vowel was strongly
,dSd ,d $ ,d
stressed. The results of his experiments indicate that
the duration ratio has a stronger influence on ;FkSd ;Fkk $ ,d
judgements of stress than has the intensity ratio. ijksidkj ij $ midkj
Lehiste and Peterson (1959) also reported experiments
on stress. lfU/kPNsn lfU/k $ Nsn
foPNsn fo $ Nsn
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 47
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
,dSd ,d $ ,d
Hkkstuky; Hkkstu $ vky;
Table 7: Rule VI Implemented Word List
Table 3: Rule II Implemented Word List
Step 4.7: (Rule for “Sign-EE ( S )” replaced with
Step 4.3: (Rule for “Sign-E( h )” replaced with Swar “Letter-EE ( ,s )” in Sandhi Vicheda)
“Letter-E( b )” in Sandhi vicheda)
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 48
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
fuLrkj fu% $ rkj We would like to thank Dr. G.S. Lehal, Professor and
Head, Department of Computer Science, Punjabi
Table 10: Rule IX Implemented Word List University, Patiala for many helpful suggestions and
comments.
Step 5: Repeat Steps 4.1 to 4.9 to check the next word
for checking the Vyanjan that combined with Matra.
Then replace the Matra with Swar.
Step 6: Find the Unicode value for each of the Hindi REFERENCES
characters and additional characters and use those [1] Bharati, Akshar, Vineet Chaitanya & Rajeev Sangal,
values to implement above rules. 1991, A Computational Grammar for Indian languages
processing, Indian Linguistics Journal, pp.52, 91-103.
Step 7: Display the results.
[2] Bharati A., Chaitanya V and Sangal R, "Natural
Language processing: A Paninian Perspective", Prentice
Our module was developed in Visual Basic.NET
Hall of India, 1995.
(2005) and the encoding used for text was in Unicode,
most suitable for other applications as well. Unicode [3] Cheng, Chin-Chuan “English Stresses and Chinese Tones
uses a 16 bit encoding that provision for 65536 in Chinese Sentences” California University, Berkeley,
characters. Unicode standard [18] assigns each Phonology Laboratory.
character a unique numeric value and name. Presently
it provides codes for 49194 characters: [4] Dan W. Patterson “Introduction to Artificial Intelligence
In Hindi Language: Total Swar=13 and Expert Systems” Prentice Hall P-227.
Total Vyanjan=33
IJCSI
IJCSI International Journal of Computer Science Issues, Vol. 3, 2009 49
ISSN (Online): 1694-0784
ISSN (Printed): 1694-0814
IJCSI
IJCSI CALL FOR PAPERS JANUARY 2010 ISSUE
The topics suggested by this issue can be discussed in term of concepts, surveys, state of the
art, research, standards, implementations, running experiments, applications, and industrial
case studies. Authors are invited to submit complete unpublished papers, which are not under
review in any other conference or journal in the following, but not limited to, topic areas.
See authors guide for manuscript preparation and submission guidelines.
Accepted papers will be published online and authors will be provided with printed
copies and indexed by Google Scholar, CiteSeerX, Directory for Open Access Journal
(DOAJ), Bielefeld Academic Search Engine (BASE), SCIRUS and more.
All submitted papers will be judged based on their quality by the technical committee and
reviewers. Papers that describe research and experimentation are encouraged.
All paper submissions will be handled electronically and detailed instructions on submission
procedure are available on IJCSI website (http://www.ijcsi.org).
It also provides a venue for researchers, students and professionals to submit on-
going research and developments in these areas. Authors are encouraged to
contribute to the journal by submitting articles that illustrate new research results,
projects, surveying works and industrial experiences that describe significant advances
in field of computer science.
Indexing of IJCSI:
1. Google Scholar
2. Directory for Open Access Journals (DOAJ)
3. Bielefeld Academic Search Engine (BASE)
4. CiteSeerX
5. SCIRUS
© IJCSI PUBLICATION
www.IJCSI.org