Monday, September 25, 2017
   
Text Size
Login

Journal of Information and Communication Technology (JICT) Vol. 3, No. 2 Dec 2004

A GENETIC ALGORITHM APPROACH FOR TIMETABLING PROBLEM: THE TIME GROUP STRATEGY
*A. B. M. Sultan, R. Mahmod, M. N. Sulaiman, and **M. R. A. Bakar
*Faculty of Computer Science and Information Technology
University Putra Malaysia, 43400 UPM Serdang Selangor, Malaysia
**Department of Mathematic
Faculty of Science and Environmental Studies
University Putra Malaysia
E-mail: {abakar, ramlan, nasix@fsktm.upm.edu.my}
E-mail: rizam@fsas.upm.edu.my
 
ABSTRACT FULL TEXT
The university timetabling problems (TTP) deal with the scheduling of the teaching program. Over the last decade variant of Genetic Algorithm (GA) approaches have been used to solve various types of TTP with great success. Most of the approaches are problem dependent, applied only to the institutions where they were designed. In this paper we proposed time group strategy and Simple GA (TGGA) to solve highly constrained TTP. The proposed model promises to solve highly constrained timetabling with less effort. The model is tested and results are discussed.
 
Keywords: timetabling, heuristic, genetic algorithm.
 

 
ICT AND SCHOOL TRANSFORMATION: AN EMPIRICAL STUDY ON THE PERCEPTION OF PRINCIPALS IN THE KLANG VALLEY AREA ON THE MALAYSIAN SMART SCHOOL
*Husnayati Hussin, **Mohd Adam Suhaimi and Zakiah Bind Abang Bawi
Department of Information Systems, Faculty of Information and Communication Technology
International Islamic University, Gombak, 53100 Kuala Lumpur
Tel: 603-2056 5166, Fax: 603-20565179, *Email: husnavati@iiu.edu.my
Tel: 603-2056 5151, Fax: 603-2056-5079, **Email: adam@iiu.edu.my
Tel: 603-2056 5161, Fax: 2056-5079
 
ABSTRACT FULL TEXT
Being one of the flagship applications in the Multimedia Super Corridor (MSC), the success of the Malaysian Smart School is very important to the country. Principals, being one of the stakeholders of the Smart Schools, are the drivers of the educational reinvention at school level. This study aims to investigate the perception of principals towards the implementation of Malaysian Smart Schools. A survey was done using questionnaires. The respondents were principals of pilot Malaysian Smart Schools and ordinary schools in the Federal Territory of Kuala Lumpur. Data from 40 respondents were analyzed. The findings revealed that the principals participating in the study have a positive perception towards the implementation of the Malaysian Smart School. The principals’ understanding and knowledge on the Smart School concept has a significant relationship with their perception. On the other hand, their skills in IT and computer usage, length of service and tenures as principals have no significant relationship with their perception on Smart School implementation. The study provides some insights on the perception of school leadership in building ICT-capable schools in the context of a developing country.
 
Keywords: ICT and Schools, ICT and Education, Malaysian Smart Schools, ICT and School Leadership.
 

 
MYOCARDIAL INFARCTION DIAGNOSIS USING FUZZY-EXPERT APPROACH
Fadzilah Siraj, **Rafikha Aliana A. Raof
Faculty & of Information Technology
Universiti Utara Malaysia
Tel.- (604) 04-9284672, Fax: (604) 04-9284753,
*Email.. fad173@webmail.uum.edu.my
**E-mail:
phica@yahoo.com
 
ABSTRACT FULL TEXT
A fuzzy expert system is a system which incorporates fuzzy sets and/or fuzzy logic into its reasoning process and/ or knowledge representation scheme. It allows the knowledge to be encoded in a form that reflects the way experts think about a complex problem. Since fuzzy expert approach model imprecise information, it improves the cognitive modelling of the problem and therefore makes it more powerful. The Expert system and fuzzy logic have their own significant capabilities; hence the combination of both technologies that form a fuzzy-expert system or a hybrid system could increase the systems performance (Herrmann, 1996). This paper presents the use of such technologies in the system known as FEMInS. The system assists the general medical practitioners in handling heart attack cases that have been referred to them. Unlike conventional expert systems, FEMIns implemented the fuzzy logic technique in its inference engine. Since fuzzy logic can be used for prediction, and expert system can provide explanation and reasoning, the combination of both fields is able to cope with the problems of uncertainty and provide the explanation of the results to the user. FEMIns demonstrates that both fuzzy logic and expert system complement rather than complete with each other.
 
Keywords: expert systems, fuzzy logic, hybrid system expert fuzzy system, artificial intelligence.
 

 
ROAD SIGN RECOGNITION USING AFFINE MOMENT INVARIANT
*Liong Choong Yeun
School of Mathematical Sciences, Faculty of Science and Technology
Universiti Kehangsaan Malaysia, 43600 UKM Bangi, Selangor D.E.
Tel : 03- 8921 3712 * E-mail: lg@,pkrisc.cc.ukm.my
 
ABSTRACT FULL TEXT
Ability to recognise road signs in due time is an essential aspect of safe driving especially at night. Hence an auto road sign recognition system is a desirable add-on to a night vision system. This paper presents the use of affine moment invariants (AMIs) as the invariant feature vectors, and the multilayer perceptron (MLP) neural network as the pattern classifier, in developing a road sign recognition system. Six classes of road signs of different position, size and orientation, which were extracted from various near infra-red (NIR) road scenes, have been processed to validate the system. The first four simple AMIs I, - I, were used for the image registration. The AMIs, which were computed from central moments, formed a feature vector that was invariant under the general affine transformation. These feature vectors were then fed into an MLP neural network for classification. The MLP used was trained with the quickprop algorithm (QA), a variation of the standard back-propagation (BPA) algorithm. Scaling and transformation of the feature vectors have reduced its dynamic range significantly towards improving the network convergence and performance. The trained and tested MLP was then validated with a set of feature vectors. This study has achieved a 100% successful classification rate using a limited validation set of road sign images.
 
Keywords: Road sign recognition, affine moment invariants (AMIs), multilayer percepstron (MLP), quickprop, quickprop algorithm (QA).
 

 
THE IMPACT OF STRATEGY ON ICT PROJECTS
*G. Udechukwu Ojiako, D. Eric Johansen and **David J. Greenwood
*British Telecom, Newcastle-upon-Tyne, NE1 2JQ UK
**School of the Built Environment, Northumbria University, Ellison Place,
Newcastle-upon-Tyne, NE1 8ST, UK
 
 
ABSTRACT FULL TEXT
Strategic planning processes are oriented towards the selection of objectives and product/market choices by senior management. From this viewpoint strategic planning provides a mechanism for setting and reviewing objectives, focusing on choices of long-term significance, identifying strategic options, allocating resources, and achieving corporate-wide co-ordination, monitoring, and control. Current literature on strategic planning has recognised the problems with traditional approaches to planning. In this article, the authors seek to consider links between strategy and the implementation of ICT projects within the telecommunications industry.
 
Keywords: Strategy, Implementation.
 

 
TRANSACTION DECOMPOSITION TECHNIQUE
*H. Ibrahim
Department of Computer Science, Faculty of Computer Science
and Information Technology, Universiti Putra Malaysia,
43400 UPM, Serdang, Malaysia.
 
ABSTRACT FULL TEXT
A transaction is a collection of operations that performs a single logical function in a database application. Each transaction is a unit of both atomicity and consistency. Thus, transactions are required not to violate any database consistency constraints. In most cases, the update operations in a transaction are executed sequentially. The effect of a single operation in a transaction potentially may be changed by another operation in the same transaction. This implies that the sequential execution sometimes does some redundant work. It is the transaction designer’s responsibility to define properly the various transactions so that it preserves the consistency of the database. In the literature, three types of faults have been identified in transactions, namely: inefficient, unsafe and unreliable. In this paper, we present a technique that can be applied to generate subtransactions to exploit parallelism. In our work, we have identified four types of relationships which can occur in a transaction. They are: redundancy, subsumption, dependent and independent. By analysing these relationships, the transaction can be improved and inefficient transactions can be avoided. Furthermore, generating subtransactions and executing them in parallel can reduce the execution time.
 
Keywords: transaction, transaction decomposition, substransaction, update operations, parallel processing.
 

 
SEARCHING MALAY TEXT USING STEMMING ALGORITHM
**Rizauddin Saian and **K. R. Ku-Mahamud
*Department of Mathematical Sciences and Statistics,
Universiti Teknologi MARA Perlis, 02600 Arau, Perlis.
**Faculty of Information Technology,
Universiti Utara Malaysia, 06010 Sintok, Kedah.
 
ABSTRACT FULL TEXT
Stemming is an important process to improve the performance of a search engine by reducing the variant word forms to common forms. This paper evaluates the retrieval effectiveness of stemming algorithm in searching and retrieving relevant Malay web pages based on user natural query words. The retrieved web pages are weighted and ranked using inverse document frequency function. The retrieval effectiveness is measured using standard recall and precision. Experiments performed show that searching with stemming improves retrieval effectiveness when compared to searching without stemming algorithm.
 
Keywords: stemming, information retrieval, retrieval effectiveness.

Universiti Utara Malaysia Press
 Universiti Utara Malaysia, 06010 UUM Sintok
Kedah Darul Aman, MALAYSIA
Phone: +604-928 4816, Fax : +604-928 4792

All Right Reserved. Copyright © 2010, Universiti Utara Malaysia Press