• J.Suganya
• Dr. T .Chakravarthy

Cognitive skills (CS) play an imperative role in performance of any individual. Knowing the level of cognitive skill of student, we can predict their performance. Latest methods are insufficient to address the challenges created by study characteristics of a student. We present a multilayer method to predict student's cognitive skills. The proposed method consists of three stages. First is the quantization, during this multilayer model is initiated by splitting study characteristics into six factors (study time, travel time, outing time, free time, family relationships and health), and range is assigned to the above mentioned factor. Second, the range of CS is divided into 21 periodic intervals (0 – 20). The component-wise division of study characteristics and CS is done to ensure prediction accuracy. Third, simulation between CS intervals and study characteristics layers. Finally, we analyzed the simulated data using machine learning algorithms. The machine learning algorithms support vector machines (SVMs) is used for our study. The proposed method is tested on the students' performance data sets in UCI repository. The results shows that SVMs achieve higher accuracy than other the traditional approach.

Cognitive skills, Study related characteristics, quantization, Machine learning algorithms, Support vector machines

"COGNITIVE SKILL MEASURENT OF STUDENT USING SUPPORT VECTOR MACHINE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 1, page no.281-288, January-2019, Available :http://www.jetir.org/papers/JETIR1901938.pdf

"COGNITIVE SKILL MEASURENT OF STUDENT USING SUPPORT VECTOR MACHINE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 1, page no. pp281-288, January-2019, Available at : http://www.jetir.org/papers/JETIR1901938.pdf