Work place: Faculty of Informatics and Computing, Universiti Sultan Zainal Abidin, Terengganu, Malaysia
E-mail: Fatma@unisza.edu.my
Website:
Research Interests: Computer systems and computational processes, Pattern Recognition, Image Processing, Data Structures and Algorithms
Biography
Fatma Susilawati Mohamad is an Associate Professor in the Department of Information Technology, Faculty of Informatics and Computing, UniSZA. She services 18 years in academic field and has been actively involved in teaching, research, publications, professional services, consulting, and administration. She was also been appointed for holding various administrative positions in faculty and university level. Now she serves as a Deputy Dean at the Graduate School, UniSZA. She has graduated a Bachelor of Science (Information System) from Oklahoma City University, U.S.A in 1997. She has continued his studies at Universiti Kebangsaan Malaysia and obtained her Master of Information Technology (Computer Science) in 2004. She received his Ph.D. in Computer Science from Universiti Teknologi Malaysia in 2012. During her tenure as an academic staff, she has taught various courses for undergraduate studies (Diploma and Bachelor Degree). Her experience gained not only from the aspect of academic, but also from the aspect of research, leadership, management and administration. She has published in more than 30 articles in various conferences and refereed journals where most of her publications came from Scopus and ISI indexed journals. She has led several research grants and her work is recognized in both national and international level. She was also invited to give talk in several conferences and technical workshops national and internationally. Currently, she has more than 10 postgraduate students under supervision where 5 of them were already graduated. Her specialization is in Computer Science focusing on Pattern Recognition and Image Processing.
Associate Professor Dr Fatma Susilawati Mohamad, Department of Information Technology, Faculty of Informatics and Computing Universiti Sultan Zainal Abidin (UniSZA), 21300 Gong Badak, Kuala Nerus, Terengganu, Telephone: 09-6688796, E-mail: fatma@unisza.edu.my, Website: http:/fik.unisza.edu.my/fatma
By Mohammed Sarhan AlDuais Fatma Susilawati Mohamad Mumtazimah Mohamad Mohd Nizam Husen
DOI: https://doi.org/10.5815/ijisa.2020.01.05, Pub. Date: 8 Feb. 2020
The batch back prorogation algorithm is anew style for weight updating. The drawback of the BBP algorithm is its slow learning rate and easy convergence to the local minimum. The learning rate and momentum factor are the are the most significant parameter for increasing the efficiency of the BBP algorithm. We created the dynamic learning rate and dynamic momentum factor for increasing the efficiency of the algorithm. We used several data set for testing the effects of the dynamic learning rate and dynamic momentum factor that we created in this paper. All the experiments for both algorithms were performed on Matlab 2016 a. The stop training was determined ten power -5. The average accuracy training is 0.9909 and average processing time improved of dynamic algorithm is 430 times faster than the BBP algorithm. From the experimental results, the dynamic algorithm provides superior performance in terms of faster training with highest accuracy training compared to the manual algorithm. The dynamic parameters which created in this paper helped the algorithm to escape the local minimum and eliminate training saturation, thereby reducing training time and the number of epochs. The dynamic algorithm was achieving a superior level of performance compared with existing works (latest studies).
[...] Read more.Subscribe to receive issue release notifications and newsletters from MECS Press journals