Hybrid Optimization Feature Selection for Predicting Student Performance

Sri Vasavi College, Erode Self-Finance Wing 3rd February 2017 National Conference on Computer and Communication NCCC’17

Format: Volume 5, Issue 1, No 9, 2017

Copyright: All Rights Reserved ©2017

Year of Publication: 2017

Author: R.Sasiregha,Dr.R.Umarani

Reference:IJCS-198

View PDF Format

Abstract

Education plays a vital role in deciding the society and it undergoes many changes. As a result, the education related digital data is been increasing rapidly. This made data mining approaches to spot over educational data ended in Educational data mining (EDM). The regulation focuses on investigating educational data to build models for enhancing learning experiences and improving institutional effectiveness. In this paper, the data mining techniques is used for predicting the student performance in different educational levels. Irrelevant features, along with redundant features, rigorously influence the accuracy of the classification of student performance. Therefore, feature selection should be able to detect and eliminate both irrelevant and redundant features as hard as possible. A hybrid technique of Artificial fish swarm-Cuckoo search optimization is introduced for feature or attributes selection. After feature selecting process, two effective classification techniques i.e., Prism and J48 is used for predicting the student performance. Experimentation result is shown that the feature selection method is well effective.

References

[1] E. Baker, International Encyclopedia of Education (3rd edition), Oxford, UK: Elsevier, (In Press). [2] P. Mitra, C. A. Murthy and S. K. Pal. “Unsupervised feature selection using feature similarity,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 3, pp. 301–312, 2002. [3] Miller, “Subset Selection in Regression,” Chapman & Hall/CRC (2nd Ed.), 2002. [4] H. Almuallim and T. G. Dietterich. “Learning boolean concepts in the presence of many irrelevant features,” Artificial Intelligence, vol. 69, no. 1-2, pp. 279–305, 1994. [5] D. Koller and M. Sahami, “Toward optimal feature selection,” In Proceedings of the Thirteenth International Conference on Machine Learning, pp. 284–292, 1996. [6] K. R. Kohavi and G.H. John, “Wrappers for Feature Subset Selection,” Artificial Intelligence, vol. 97, nos.1-2, pp. 273-324, 1997. [7] M.Dash and H.Liu, “Feature Selection for Classification,” An International Journal of Intelligent Data Analysis, vol. 1, no. 3, pp.131-156, 1997.


Keywords

Educational Data Mining (EDM), Feature Selection, Symmetric Uncertainty (SU) and Classification Artificial fish swarm, Cuckoo search optimization.

This work is licensed under a Creative Commons Attribution 3.0 Unported License.   

TOP
Facebook IconYouTube IconTwitter IconVisit Our Blog