Upload
doliharahap
View
219
Download
0
Embed Size (px)
Citation preview
8/9/2019 AI Paper - Class Selection Advisor for Graduate Student
1/9
Intelligent System Development at FTSM-UKM:
Implementing Expert System as Graduate Student Class
Selection Advisor by Using ExSys CORVID
Doli Anggia Harahap, Syafrani Fithri1
1Departement of Management Information System
Faculty of Information Science and Technology
Universiti Kebangsaan Malaysia
[email protected] , [email protected]
Abstract. Today Information Technology has growth very fast. It has pushed
the innovations creation in course of study. FTSM-UKMs staffs have a lot of
work every new semester specially in overcoming registration problem.
Students also always face a small problem in specifying class to be taken for the
next or current semester. Students also need a guidance to assist them for
choosing the best class for them to be taken. This paper is proposed a
commercial expert system called ExSys Corvid for helping member of FTSM-
UKM solve their problem for every new semester.
Keywords: Intelligent System, Expert System, FTSM, UKM, Graduate Student
1 Introduction
Fakulti Teknologi dan Sains Maklumat (FTSM) is one of faculty in Universiti
Kebangsaan Malaysia (UKM). Back to the history, UKM for the first time, offering
computer science courses. As well as development of UKM, the Computer Sciences
unit became a Department of Computer Science. By that time, this Department has
already offered program for Bachelor's Degree, Master Degree, and Doctorate levels.
Since Malaysia started focusing Information Technology as one of main Industry in
Malaysia, Department of Computer Science again was upgraded the status became a
Faculty of Information Science and Technology. And now, the numbers of students
are increasing for each year, especially the number of Graduate students1.
In academic matters, of course students need guidance and advice from their
lecturers, advisor, supervisor, or even the head of each department. In fact, students
are very confusing or need someone expert to guide them for choosing class they have
1 From now until the end of this paper, every word of student(s) mentioned in this
paper means Graduate Students of UKM).
mailto:[email protected]:[email protected]:[email protected]:[email protected]8/9/2019 AI Paper - Class Selection Advisor for Graduate Student
2/9
to attend, based on their interests, previous results, previous experiences, or other
things. These things become a little problem as the limitation number of lecturers who
can be an advisor to the students. Finding appropriate timing between students and
their advisor has also become constraint.
From the problems above, expert system in educational field can be a solution, at
least to help lecturers give advice to the students, and of course help students make
decision for choosing which classes to attend. Expert system with decision-support
technique will be discussed in this paper.
1.1 Overview of FTSM-UKM
FTSM-UKM is lead by a Dean as a Head Manager for administration in FTSM. TheDean is assisted by two Deputy Dean. First Deputy Dean is responsible for handling
research, international relation, and industry. The second one is responsible for
handling undergraduate, alumni, and community partnership.
FTSM-UKM consisted of 4 departments that for each department is lead by a Head
of Department. The departments are Department of Computer Science, Department of
Information System, Department of Science and System Management, and
Department of Industrial Computing.
The Computer Science Department is responsible for conducting programmes of
studies that produce graduated who possess the necessary knowledge and skill for
spearheading and developing the software industry of the nation.
The aim of the System Science Management Department is to increase and
enhance to knowledge and the scholar in the Concept and Development Methodology.The Objective of the department of Information Science, though its graduate
programme, is to produce scholar with high degree of expertise in the field of
information access and multimedia study.
The objective of the Industrial Computing Programme is aimed to produce skilled
graduate and professional in utilizing information technology into production industry
and manufacturing.
Graduate Student Center Department is for helping graduate students in
administration matters, and provides facilities that graduate students need. In every
new semester this department is faced with a lot of work to handle students problem
in registration class.
2 Intelligent System
Intelligence is the computational part of the ability to achieve goals in the world.
Varying kinds and degrees of intelligence occur in people, many animals and some
machines. Intelligence is their ability to understand and learn things. Intelligence is
8/9/2019 AI Paper - Class Selection Advisor for Graduate Student
3/9
the ability to think and understand instead of doing things by instinct or
automatically2.
Artificial Intelligence is the science and engineering of making intelligent
machines, especially intelligent computer programs. It is related to the similar task of
using computers to understand human intelligence, but AI does not have to confine
itself to methods that are biologically observable.
2.1 Concept and Definition of Expert System
Knowledge-based expert systems, or simply expert systems, use human knowledge to
solve problems that normally would require human intelligence. These expert systems
represent the expertise knowledge as data or rules within the computer. These rulesand data can be called upon when needed to solve problems. Books and manuals have
a tremendous amount of knowledge but a human has to read and interpret the
knowledge for it to be used. Conventional computer programs perform tasks using
conventional decision-making logic -- containing little knowledge other than the basic
algorithm for solving that specific problem and the necessary boundary conditions.
This program knowledge is often embedded as part of the programming code, so that
as the knowledge changes, the program has to be changed and then rebuilt.
Knowledge-based systems collect the small fragments of human know-how into a
knowledge-base which is used to reason through a problem, using the knowledge that
is appropriate. A different problem, within the domain of the knowledge-base, can be
solved using the same program without reprogramming. The ability of these systems
to explain the reasoning process through back-traces and to handle levels ofconfidence and uncertainty provides an additional feature that conventional
programming does not handle.
Most expert systems are developed via specialized software tools called shells.
These shells come equipped with an inference mechanism (backward chaining,
forward chaining, or both), and require knowledge to be entered according to a
specified format (all of which might lead some to categorize OPS5 as a shell). They
typically come with a number of other features, such as tools for writing hypertext,
for constructing friendly user interfaces, for manipulating lists, strings, and objects,
and for interfacing with external programs and databases. These shells qualify as
languages, although certainly with a narrower range of application than most
programming languages. For more detailed information on expert system shells, see
the "Expert System Shells at Work" series by Schmuller PC AI, (1991, 1992).
2.2 ExSys Corvid
EXSYS Inc., founded in 1983, for the first time brought an interactive advisory
system to the Web in 1996. Then EXSYS continue developing breakthrough
technology with their new Corvid Product Line. Instead of just providing data, Exsys
2 (Essential English Dictionary, Collins, London, 1990).
8/9/2019 AI Paper - Class Selection Advisor for Graduate Student
4/9
CORVID brings benefits to the Web sites and stand-alone PCs by providing logical
Answers that apply specifically to each visitor.
Exsys CORVID is software the represents a proven knowledge automation expert
system paradigm, resulting from a close examination of what is needed to build and
implement decision-making systems in todays Internet-oriented world. Corvid is
designed to allow system developers to easily capture knowledge, build powerful
interactive advisory applications and deliver them online (Internet, Intranet, wireless)
quickly and effectively producing significant return on investment.
3 Basic Theory
Today, UKM has been one of university in Malaysia that accepted so many graduate
students for doing their study, and FTSM has become one of faculty in UKM that has
so many graduate students, local students and international students. Every
departments now in FTSM, has big job to do in each beginning of a new semester,
especially for handling the registration. Students are always faced by very basic
problem, which is to determine which class they have to take for current semester and
what for the next semester. Graduate Student Center Department is the department
that always busy because of this. Some students need guidance from the head of
Graduate Student Center Department for deciding what suitable class to be taken. Not
only Graduate Student Center Department, but also the lecturers or Head of each
department is being busy for giving advice to students.
3.1 FTSMs Department is Suitable Using Intelligent System
Graduate Student Center Department is a place of administration of graduate students,
and registration thing is being held in this department. Problems like has been stated
above is a major problem occurred in this department, and I thing it is the time for
FTSM UKM, especially for Graduate Students Center to implement Intelligent
System that can provide solution. At least to advice students and provide guidance for
students as well as the expert, lecturers or Head of each department, can do.
The basic idea is, for the future this system can be replaced expert for giving
advice and guidance for students especially in the beginning of each semester.
Hopefully it can help students without having difficulty to make appointment like
they have to with lecturers, and it can be more effective for lecturers in time, so that
they can spare their time for another things.
3.2 Proposed Systems: ExSys CORVID
ExSys Corvid is a Java based expert system knowledge automation. It allows the
logic rules and procedural step by steps that usually used by experts, domain
knowledge, or business operations to be efficiently simulated/emulated in a system.
8/9/2019 AI Paper - Class Selection Advisor for Graduate Student
5/9
Why ExSys Corvid is appropriate or matches for solving problem in FTSM-UKM
like mentioned above? It is because ExSys Corvid using Knowledge Automation
technique.
When system is developed, the decision-making knowledge of human experts will
be converted to rules, a form or logical representation that the computer understand.
Then the rules are analyzed and processed by the engine or expert system to produce
data. Then the data is used to take action for reach the specific goal or end point.
System will asked users bunch of questions and use their input to determine which
rules are true so that system can provide advice.
Other than that, Exsys Corvid is suitable for solving FTSM-UKMs problem
because these below feature it has.
- Easy to learn Developer Interface
- Powerful Inference Engine- Web-Enabled Runtime
- Flexible System User Interface
- Can be integrated with Database and CRM
On the product datasheet also sated that Exsys Corvid are best to use for
Automates Routine Task. It is very suitable for FTSM-UKM to handle routine task in
registering Graduate students class.
For writing this paper and propose this system, authors has been tried the 30-days
trial version of Exsys Corvid System.
4 Implementation Planning of ExSys CORVID in FTSM-UKM
Hardware. Exsys Corvid can be used as stand alone system and also can be used as a
client-server system. Exsys Corvid can be accessed to the server on a web page via
serlet runtime. Minimum configuration that is needed is a computer with Pentium 4
above, 258Mb of RAM, Harddisk spcace, Mouse, and 1024x768resolution of monitor
or better.
Applet Runtime (for browser). Browser supporting Java Applets (requires only
Java 1.1 or above).
(Optional) Servlet Runtime (if the system located in server and accessed by
client). Servlet with Apache Tomcat and Java Runtime 1.3 or higher.
4.1 Developing System
1. Analysis and Design
In this phase, communication between user and human expert will be done to
discuss the problem is face. In this case, Graduate students and Lecturer as the
expert will be asked for the issues.
2. Requirement Analysis
In this phase, identifying requirements will be done. To figure out where this
system should be placed, the number of workstation will be needed, the number
8/9/2019 AI Paper - Class Selection Advisor for Graduate Student
6/9
of license should be paid for the Exsys system, the lecturer should be interviewed
as the human expert, etc.
3. Gathering information from expert and user.
This phase is the most important for this case. Users, in this case students, and
the experts, in this case lecturer, will be questioned and interviewed to get
information about the logic as the knowledge representation. Their information
later will be provided for the system as rules.
4. Determine an Architecture for the Sytem
There are many ways to build system in Corvid. It requires an approach to the
problem and an architecture that will produce correct result, make sense to
developer and will be easy for others to understand and maintain.
5. Use Corvid to Represent the System Logic
Information from the users and experts, as well known as rules, will be processed
by the system. Then the output will become the system logics.
6. Design the End of User Interface
This phase is not taking much time, because this system only needs simple user
interface. The main thing is, the user interface should be easy to understand and
not becoming a new problem to be used.
7. Test the System
A Corvid system should be treated like other software development projects
thoroughly beta tested and validated the data by the experts to make sure it
provides the correct results. This result should be printed out and reviewed by the
experts to make sure they are individually correct.
5 Conclusion and Suggestion
This paper provides proposal to FTSM-UKM to use expert system for helping
students make decision making and helping lecturers assist their students. At first,
authors do examination and observation based on personal experiences in FTSM-
UKM, that author feel it is very hard to determine which class to attend for current
semester and for next following semester. It is also very hard to find an appropriate
time to consult with the lecturers as the experts.
As the problem mentioned, authors think that it is the time for FTSM-UKM to
implement expert system. Exsys Corvid is one of expert systems in the market
(commercially) which is using knowledge automation as its core technique for
problem solving. Besides that, Exsys Corvid provides other features and based on
authors reading, it is very suitable to be implemented in FTSM-UKM.
Authors suggest FTSM-UKM implement expert system in FTSM-UKM as soon as
possible, it can be using this Exsys Corvid like authors suggest or it can be using
another expert system or even develop FTSM-UKMs expert system itself.
8/9/2019 AI Paper - Class Selection Advisor for Graduate Student
7/9
References
1. Ferdian, E., Fahrial, J., Parmahaki., Panagaribuan, R.: Sistem Pakar: Mengidentifikasi
Kerusakan Gangguan Telepon PT. TELKOM (Stdui Kasus). IlmuKomputer.Com. (2004)
2. Firebaugh, W., M.: Artificial Intelligence: A Knowledge Based Approach. pp. 335-365.
PWS-KENT Publishing, Boston (1988)
3. Rao, T, M., Coleman, S., Hollenback, C.: ADVISOR an Expert System for Student
Advesiment, 15th Annual Conference on Computer Science, pp. 3235. ACM, New York
(1987)
4. Zainab A.N., Nor Eliza Mohd. Zaid.: Introducing MAKLUM: The General Reference
Expert Adviser Developed For A University Library, Malaysian Journal of Library &
Information Science, 1 (1). pp. 93-107. Kuala Lumpur (1996)
5. Awad, E.: Building Knowledge Automation Expert System with Exsys Corvid,.
Alberqueque (2002)
6. F. Javed, P.A. Venkatachalam, and A.F.M. Hani.: A Signal Processing Module Integrated
Expert System for Diagnosing Heart Diseases, Proceeding TELEHEALT (2006)
7. Yen-Ting Lu., Chia-Jung Liao., Ming-Hung Ou., Ying-Fong Huang.: World Congress on
Medical Physics and Biomedical Engineering in IFMBE Proceedings, Volume 14, Springer
(2007)
8. Merrill E. Warkentin, P. K. R. Nair, Stephen R. Ruth, Kristopher Sprague.: A knowledge-
based expert system for planning and design of agroforestry systems, Agroforestry Systems
Vol. 11, pp 7183, Springer Netherlands (2004)
9. Rich, Elaine, Knight, Kevin.: Artificial Intelligence, 2nd Edition, Mc.Graw Hill, New York
(1991)
10.Setiarso, Bambang.: The Design and Technology Web-Based Knowledge: A Case LIPI
website, Adegira, Jakarta (2000)
11.M. Llyod-Williams, P. Beynon-Davies.: Expert System for Database Design: a ComparativeReview, Artificial Intelligence Review, Vol. 6, pp 263283 (1992)
12.Fakuti Teknologi dan Sains Maklumat.: Panduan Siswazah , Sesi Akademik 2009-2010
13.Durkin, J.: Expert System Design and Development, Prentice Hall, Englewood, Cliffs(1994)
14.Kementrian Komunikas dan Informasi Republik Indonesia.: Teknologi Informasi Pilar
Bangsa Indonesia Bangkit, Jakarta (2003)
15.Charnoak, Eugene, Mc.Demott, Drew.: Introduction to Artificial Intelligence, 2nd Edition,
Addition-Wesley (1985)
8/9/2019 AI Paper - Class Selection Advisor for Graduate Student
8/9
Appendix: Screenshot of ExSys CORVID in Various
Institutions/Organizations and Online Demos
1. United States Department Of Labor, OSHA Fire Safety Advisor
8/9/2019 AI Paper - Class Selection Advisor for Graduate Student
9/9
2. Online Demos, Camcoder Selection Advisor