Umi Hanim Mazlan

Diagnostic tool to detect early stage of breast cancer using fuzzy logic

Cancer is a dangerous disease that can be treated at an early stage. Most of the cancers will show their early symptoms. However, the people at risk usually ignore the early symptoms they have cause they cannot be treated quickly. For breast cancer, Breast Self Examination (BSE), is the fastest screening test that can be conducted individually to detect the early symptoms. However, the BSE alone only makes people ambiguous with their own test. This problem can be tackled with the diagnostic tool that can support BSE in producing convincing result to rely on. In order to develop the diagnostic tool, fuzzy logic technique is applied since one of the major contributions of this method is its high level of precision. The intention of this study is also to provide information regarding breast cancer, thus the diagnostic tool is incorporated with informative web-based system.

Enhanced Interactive Mathematical Learning Courseware Using Mental Arithmetic for Preschool Children

Interactive Mathematical Learning Courseware 2.0 (iMLc2.0) is an enhanced version of multimedia application which aims to expose the pre-school children in mental arithmetic technique with; (i) larger range of numbers, (ii) implementation of standard written method and, (iii) video support to visualize both techniques. The application integrates all multimedia elements and mental arithmetic techniques in interactive and supportive ways which are suitable for pre-school children. It is divided into three modules, addition, subtraction, and quizzes. The addition operation has been designed to apply the finger-brain approach which is a part of mental arithmetic technique while, mental-imagery approach is adapted for subtraction operation. Experimental test and user acceptance test have been conducted to evaluate the application. The implementation of iMLC2.0 in enriched interactive multimedia environment can be used as additional teaching and learning tool since it is supportive and attractive. In addition, it can motivate the preschooler to be prepared for future mathematical learning.

Classification of breast cancer microarray data using Radial Basis Function Network

Breast cancer is the number one killer disease among women worldwide. Although this disease may affect women and men but the rate of incidence and number of deaths are high among women compared to men. Early detection of breast cancer helps to increase the chance of survival since early treatment can be decided for the patients who suffer from this disease. The advent of the Microarray Technology enables it to be applied to the medical area in terms of classification of cancer and diseases. By using the microarray, the expressions of thousands of genes can be determined simultaneously. However, this microarray suffers several drawbacks such as high dimensionality and contains irrelevant genes. Therefore, various techniques of feature selection have been developed in order to reduce the dimensionality of the microarray and also to select only the appropriate genes. For this study, the microarray breast cancer data, which is obtained from the Center for Computational Intelligence, is used in the experiment. The Relief-F Algorithm is chosen as the method of the feature selection. As for comparison, another two methods of feature selection, which are Information Gain and Chi-Square, are also used in the experiment. The Radial Basis Function (RBF) Network is used as the classifier to distinguish between the cancerous and noncancerous cells. The accuracy of the classification is evaluated by using the chosen metric, namely Receiver Operating Characteristic (ROC).

Android Application to Test for Nicotine Dependence

Nicotine dependence is categorized as tobacco addiction where the smokers are unable to stop taking cigarettes even though it causes harm. It is estimated that tobacco use has increased the death rate of smokers, that is, 5.4 million. It kills up with an average of one person in every 6 seconds. Many smokers do not realize that smoking is dangerous until they have suffered from health problems. If there is no prevention, the smoking habit will lead to cardiovascular disease. Therefore, the aim of this project to design an application to measure the addictive level of nicotine dependence using Fagerstrom test for Nicotine Dependence Therapy (NRT) product with appropriate dosage based on the nicotine level. Thus, by using mobile application, the smokers can interact with this application to monitor their nicotine level. From the tests that had been conducted, this application has been accepted by the experts and also target user who is a smoker.

The Evaluation of Performance and Quality of Preschool Using Fuzzy Logic Approach

Malaysia is currently transforming its education system to achieve world-class status. High-quality preschool education improves children’s health and promotes their development and learning. Educators have a role in promoting the quality of early education and childcare by examining the issues and challenges involved. The performance of children includes four major factors which are based on the physical aspect, socio-emotional, spiritual, and intellectual of preschool children in their learning process. This paper presents a methodology to improve these four factors by analyzing the performance of individual students. This study focuses on 17 preschools in Johor which consist of five selected schools in the year 2015. For this purpose, the whole data from the four aspects are divided into various ranges. This is done by fuzzy logic system. It has been shown that the performance of the five selected schools is successful in their process of learning.

Forecasting River Water Level Using Artificial Neural Network

Flood is a natural phenomenon that occurs without warning. The occurrence of flood can cause many damages in terms of property, money, and even death. In order to prevent more loss, an early warning system of the increment of river water level needs to be forecasted in a more accurate and effective way to predict the best result. In this study, Artificial Neural Network (ANN) is implemented in order to forecast the river water level in Pelarit River, Perlis. The objectives of this study are to determine the efficiency of ANN in forecasting the river water level and to forecast the water level of Pelarit River for one week in advance. This study uses Multilayer Feed Forward Artificial Neural Network with two input neurons, seven hidden neurons, and one output neuron in order to forecast the water level. Three different types of algorithms, namely quick propagation, conjugate gradient descent, and Levenberg–Marquardt algorithms, are compared to get the most significant result in forecasting one week of river water level. Among all the algorithms used, conjugate gradient descent is proved to be the most reliable value to forecast the Pelarit River in terms of the lowest value of Root-Mean-Square Error and the highest value of correlation.

Scholarship Eligibility and Selection: A Fuzzy Analytic Hierarchy Process Approach

A scholarship is an award of financial aid for a student to further his or her education. This research focuses on Federal Scholarship awarded by the Malaysian Education Ministry. It demonstrates the scholarship selection with cases in Sekolah Menengah Kebangsaan To’ Uban, Pasir Mas, Kelantan, in 2015. The scholarship was given to form one to form five students and was awarded to those who performed in their academics and co-curricular activities but only for students whose parents with low income. The selection of eligible students in receiving the scholarship has become more challenging throughout the years due to competitiveness and an increasing number of applicants. In order to overcome this problem, Fuzzy Analytic Hierarchy Process (AHP) method was applied in this research. The objective is to identify the most important criteria and sub-criteria for the selection of students and aims to select the students who fulfil the criteria and sub-criteria. The result shows that the most important criteria are academic performance (0.712) followed by parents’ income (0.220) and co-curriculum (0.068), respectively. Moreover, for the sub-criteria of academic performance, the most important sub-criteria is “High” (0.760). The criteria for the parents’ income is left out since the sub-criteria exists is only one. Lastly, for the criteria co-curriculum the most important sub-criteria is “Sports” (0.741). The final results show that Alternative 9 (0.056) is the best choice in selecting the student.

i-Wirid: Construction of digital wirid via mobile platform

Wirid is a recitation or practice that has been taken from certain verses in Al-Quran and it was arranged to the readers, especially Muslims, read and understand easily. Wirid is a good practice for Muslims as it can bring them closer to their Creator that is Allah SWT and in forming them to become good leaders or caliphs in the future. Therefore, the main intention of this project is to investigate and design a mobile application for wirid as a guide to recite and understand wirid via mobile platform. This after prayer wirid is embedded in mobile environment with the integration of multimedia elements as a medium to attract and encourage Muslims to recite and memorize a wirid. This i-Wirid application has been developed using Eclipse as the main platform and has undergone two testing phases which are User Acceptance Test and Heuristic Evaluation in order to assess the application. The Heuristic Test was done by the experts and the User Acceptance Test was implemented on 70 respondents. Based on the results collected, there is about 93 percent of respondents who are satisfied with the application and 97 percent agreed that the application is interesting to be used in their daily lives.

Developing an architectural visualization using 3D for photo tourism

Tourism is one of the factors in contributing to economic growth and it also provides the knowledge based in historical and architectural places around the country. However, many people did not realize the speciality and uniqueness about these historical and architectural places especially the mosque and the Islamic architecture, this may happens because of the lack of interest and appreciation among the community. Therefore, this study undertakes two tasks in order to venture into building interest of the community. First, to investigate and model a 3D virtual environment of Masjid Zahir that is situated in Kedah and second is to develop a multimedia montage for photo tourism. Thus, the focus of the project is on developing a building model in three dimensional forms. This project is developed using Autodesk Maya software that includes building the model, rendering, and camera motion. From this project, the results show that new attraction is created and effective understanding is developed to the viewer from its earlier days. It also shows that the project enables people to view in a better way. The heuristic evaluation and usability test was conducted by an expert and civilian in order to allow researchers to understand the needs, response and understanding of the viewer regarding the project.