期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2013
卷号：2
期号：9
页码：4425
出版社：S&S Publications
摘要：The paper presents a Neural Network model for modeling academic profile of students. The proposed modelallows prediction of students’ academic performance based on some of their qualitative observations. Classifying andpredicting students’ academic performance using arithmetical and statistical techniques may not necessarily offer thebest way to evaluate human acquisition of knowledge and skills, but a hybridized fuzzy neural network modelsuccessfully handles reasoning with imprecise information, and enables representation of student modeling in thelinguistic form - the same way the human teachers do. The model is designed, developed and tested in MATLAB andJAVA which considers factors like age, gender, education, past performance, work status, study environment etc. forperformance prediction of students.A Fuzzy Probabilistic Neural Network model has been proposed which enables the design of an easy-to-use,personalized student performance prediction component. The results of experiments show that the model outperformstraditional back-propagation neural networks as well as statistical models. It is also found to be a useful tool inpredicting the performance of students belonging to any stream. The model may provide dual advantage to theeducational institutions; first by helping teachers to amend their teaching methodology based on the level of studentsthereby improving students’ performances and secondly classifying the likely successful and unsuccessful students.
