Publication Type:

Conference Paper

Authors:

Adeena, K.D.; R. Remya

Source:

2015 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015, Institute of Electrical and Electronics Engineers Inc., p.222-227 (2015)

ISBN:

9781479987917

URL:

http://www.scopus.com/inward/record.url?eid=2-s2.0-84946200302&partnerID=40&md5=1d07cf258fd6f1a75490eaf27c2064cc

Keywords:

Artificial intelligence, Classification accuracy, Decision trees, Fisher linear discriminants, Information science, Large dataset, Learning systems, Machine learning techniques, Q R decomposition, Support vector, Support vector machines, SVM, Training time

Abstract:

Support Vector Machine (SVM) is a popular machine learning technique for classification. SVM is computationally infeasible with large dataset due to its large training time. In this paper we compare three different methods for training time reduction of SVM. Different combination of Decision Tree (DT), Fisher Linear Discriminant (FLD), QR Decomposition (QRD) and Modified Fisher Linear Discriminant (MFLD) makes reduced dataset for SVM training. Experimental results indicates that SVM with QRD and MFLD have good classification accuracy with significantly smaller training time. © 2015 IEEE.

Notes:

cited By 0; Conference of International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015 ; Conference Date: 10 August 2015 Through 13 August 2015; Conference Code:115835

Cite this Research Publication

K. D. Adeena and R. Remya, “Extraction of relevant dataset for support vector machine training: A comparison”, in 2015 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015, 2015, pp. 222-227.