Norlina Mohd Sabri

Application of the Clonal Selection Algorithm in artificial immune systems for shape recognition

Artificial Immune Systems (AISs) emerged in 1990s. The capability of AISs for learning new information, recalling what has been learned and recognizing a decentralized pattern are reasons why numerous models have been developed, implemented and used in various types of problems. This paper describes the implementation of AISs in solving an image classification problem. The Clonal Selection Algorithm has been chosen to evolve solutions in the form of antibodies during the recognizing process. In this approach, three types of shape were treated as antigens. Two experiments have been undertaken and the results show that the algorithm can perform with an accuracy of up to 95%. As a conclusion, the study showed that the Clonal Selection Algorithm can be applied to shape recognition problems.

Development and potential analysis of Heuristic Evaluation for Courseware

Heuristics Evaluation is commonly used in the evaluation process of websites and system and it has been expended from general interface evaluation to more specific evaluation such as computer games, virtual reality and shared workspace groupware. Developed heuristics evaluations of related multimedia based application were thoroughly analyzed based on specific criteria being used in the heuristics. As a conclusion, Heuristics Evaluation for Courseware (HECW) was proposed to be developed because of the important elements of courseware that need to be addressed in order to develop a usable and acceptable courseware. The development process of HECW involved five major steps; initial study, proposed heuristics, experts review, evaluation process and final heuristics. The discussions of this paper only focus on the fourth step which is evaluation process on HECW. At the end of this paper, a potential analysis for HECW using quantitative method is proposed.

Optimization of Nano-Process Deposition Parameters Based on Gravitational Search Algorithm

This research is focusing on the radio frequency (RF) magnetron sputtering process, a physical vapor deposition technique which is widely used in thin film production. This process requires the optimized combination of deposition parameters in order to obtain the desirable thin film. The conventional method in the optimization of the deposition parameters had been reported to be costly and time consuming due to its trial and error nature. Thus, gravitational search algorithm (GSA) technique had been proposed to solve this nano-process parameters optimization problem. In this research, the optimized parameter combination was expected to produce the desirable electrical and optical properties of the thin film. The performance of GSA in this research was compared with that of Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Artificial Immune System (AIS) and Ant Colony Optimization (ACO). Based on the overall results, the GSA optimized parameter combination had generated the best electrical and an acceptable optical properties of thin film compared to the others. This computational experiment is expected to overcome the problem of having to conduct repetitive laboratory experiments in obtaining the most optimized parameter combination. Based on this initial experiment, the adaptation of GSA into this problem could offer a more efficient and productive way of depositing quality thin film in the fabrication process.

Prediction of Nanostructured ZnO Thin Film Properties Based on Neural Network

An approach in the prediction of zinc oxide (ZnO) thin films properties based on neural network is presented in this paper. The research had been focused on the electrical properties of ZnO. The sputtering power, substrate temperature, deposition time and oxygen ratio were selected as the input variables while the resistivity and conductivity were selected as the output. The numerical results obtained through the neural network model were compared with the experimental results. The result obtained from the system model of the proposed procedure was reasonably good and promising. Therefore, the prediction based on neural network model is a reliable approach compared to the traditional method of trial-and-error process.

Utilization of Soft Computing Techniques in Sputtering Processes: A Review

This paper presents an overview of research works on the utilizing of soft computing in the optimization of process parameters and in the prediction of thin film properties in sputtering processes. The papers from this review were obtained from relevant databases and from various scientific journals. The papers collected were published from 2008 to 2012. The focus of the review is to provide an outlook on the utilization of soft computing techniques in sputtering processes. Based on the review, the soft computing techniques which have been applied so far are ANN, GA and Fuzzy Logic. The first finding of this review is that soft computing technique is a promising and more reliable approach to optimize and predict process parameters compared to the traditional methods. The second finding is that the utilizing of soft computing techniques in sputtering processes are still limited and still in exploratory phase as they have not yet been extensively and stably applied. The techniques applied are also limited to ANN, GA and Fuzzy, whereas the exploration into other techniques is also necessary to be conducted in order to seek the most reliable technique and so as to expand the application of soft computing approach. Future research could focus on the exploration of other soft computing techniques for optimization in order to find the best optimization techniques based on the specific processes.

Enhancement of Mandarin courseware through formative evaluation

A Mandarin courseware has been developed initially to help Bumiputera students to improve in Mandarin pronunciations and speaking skills in Universiti Teknologi MARA (UiTM) Terengganu. Before the courseware could be distributed to students, a formative evaluation has been done to guarantee its quality as a supplementary learning material. The study has been conducted during July 2008 - November 2008 semester which involved 32 Bachelor of Business Computing students at UiTM Terengganu. The formative evaluation has been carried out using paper based questionnaire presented to the students to evaluate different aspects of the courseware. The result reveals that most of the students agreed that the courseware could be used as a supplementary learning material. Among the recommendations from the students were to improve certain audio with unclear sounds in the Phonetics and Dictionary parts and to enhance the animation in the Chapter section. Based on the evaluation result, the enhancement of the Mandarin courseware was made by stages starting from Dec 2008 - April 2009 semester. There were 3 main things that have been enhanced since the first formative evaluation. The enhancements were the addition of English version of the courseware, the design of new interface (screen design) and the improvement of the sounds in most parts of the courseware.