International Journal of
Physical Sciences

  • Abbreviation: Int. J. Phys. Sci.
  • Language: English
  • ISSN: 1992-1950
  • DOI: 10.5897/IJPS
  • Start Year: 2006
  • Published Articles: 2563

Full Length Research Paper

Comparison of Naïve bayes classifier with back propagation neural network classifier based on f - folds feature extraction algorithm for ball bearing fault diagnostic system

O. Addin1, S. M. Sapuan2*, M. Othman3 and B. A. Ahmed Ali4
  1Laboratory of Intelligent Systems, Institute of Advanced Technology, Universiti Putra Malaysia, 43400 UPM Serdang, Selangor, Malaysia. 2Department of Mechanical and Manufacturing Engineering, Universiti Putra Malaysia, 43400 UPM Serdang, Selangor, Malaysia. 3Department of Communication Technology and Networks, Universiti Putra Malaysia, 43400 UPM Serdang, Selangor, Malaysia. 4Institute of Advanced Technology, Universiti Putra Malaysia, 43400 UPM Serdang, Selangor, Malaysia.
Email: [email protected]

  •  Accepted: 18 April 2011
  •  Published: 31 July 2011

Abstract

 

This paper is intended to compare the Naïve bayes classifier for ball bearing fault diagnostic system with the back propagation neural network based on the f-folds feature extraction algorithm. The f-folds feature extraction algorithm has been used with different number of folders and clusters. The two classifiers have shown similar classification accuracies. The Naive bayes classifier has not shown any case of false negative or false positive classification. However, the back propagation neural network classifier has shown many cases of false positive and false negative classifications.

 

Key words: Neural network classifier, Naive bayes classifier, diagnostic system, engineering materials.