The Classification Model for Hard Disk Drive Functional Tests under Sparse Data Conditions

Authors: S. Pattanapairoj, D. Chetchotsak

Abstract:

This paper proposed classification models that would be used as a proxy for hard disk drive (HDD) functional test equitant which required approximately more than two weeks to perform the HDD status classification in either “Pass" or “Fail". These models were constructed by using committee network which consisted of a number of single neural networks. This paper also included the method to solve the problem of sparseness data in failed part, which was called “enforce learning method". Our results reveal that the constructed classification models with the proposed method could perform well in the sparse data conditions and thus the models, which used a few seconds for HDD classification, could be used to substitute the HDD functional tests.

Keywords: Sparse data, Classifications, Committee network

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1085319

References:

[1] A.G. da Cruz, E.H.M. Walter, R.S. Cadena, J.A.F. Faria, H.M.A. Bolini and A.M. Frattini Fileti, "Monitoring the authenticity of low-fat yogurts by an artificial neural network," Journal of Dairy Science., Vol. 92, pp. 4797-4804, 10 Oct. 2009.
[2] B. Efron, "Bootstrap methods: another look at the jackknife," Ann. Stat., vol. 7, No.1, pp. 1-26, 1979.
[3] D. Chetchotsak, and J. M. Twomey, "Combining neural networks for function approximation under conditions of sparse data: The biased regression approach," International Journal of general Systems., Vol. 36, No.4, pp.479-499, Aug. 2007.
[4] D. Chetchotsak, and W. Kanarkard, "Classification model to detect failed HDD components," Intelligent Engineering System Thorough Artificail Neural Networks., Vol. 18, pp. 697-703, St. Louis, MO, USA, Nov. 9-12, 2008.
[5] D. Chetchotsak, and S. Pattanapairoj, "Committee network model for HDD functional test," ANNIE-2010., St. Louis, MO, USA, Nov. 1-3, 2010.
[6] D. E. Rumelhart, G.E. Hilton, and R.J. Williums, "Learning representations of back-propagation errors," Nature, London, 1986.
[7] S. Haykin, "Neural networks: A comprehensive foundation," Mc Milan College Publishing, New York, 1994.
[8] S. Pattanapairoj, and D. Chetchotsak, "Quality monitoring model for failed parts detection in HDD manufacturing processes," Data Storage Technology conference., Bangkok , Thailand, May. 13-15, 2009.
[9] S. Pattanapairoj, and D. Chetchotsak, "Data mining framework for HDD yield improvement: The neural networks and association analysis approach," TISD-2010., Nongkhai, Thailand, Mar. 4-6, 2010.
[10] M. Bacauskiene, A. Verikas, A.Gelzinis, and D. Valincius, "A feature selection technigue for generation of classification committee and its application to categorization of laryngeal images," Pattern Recognition., vol. 42, pp. 645-654, Aug. 2008.
[11] M. Dash, and H. Liu, "Feature selection for classification," Intelligent Data Analysis: An Int- 1J., Vol. 1, No. 3 pp. 131-156, 1997.
[12] M. Zribi, "Non-parametric and unsupervised Bayesian classification with bootstrap sampling," Image and Vision Computing, Vol. 22, pp. 1- 8, June. 2003.
[13] R. E. Abdel-Aal, "Improved classification of medical data using abductive network committees trained on different feature subsets," Computer Methods and Programs in Biomedicine, Vol. 80, pp. 141-153, Aug. 2005.
[14] R. Nanthapodej, and D. Chetchotsak, "Classification performance of committee networks improvement under sparse data condition," KKU Res J (GS), Vol. 9, No. 2, pp. 65-76, Apr.-June. 2009
[15] R. P. Pein, and J. Lu, "Multi-feature query language for image classification," Procedia Computer Science, Vol. 1, pp. 2533-2541, 2010.