Feature Selection for Fatigue Segment Classification System Using Elitist Non-Dominated Sorting in Genetic Algorithm

Abstract:

Having relevant features for representing dataset would motivate such algorithms to provide a highly accurate classification system in less-consuming time. Unfortunately, one good set of features is sometimes not fit to all learning algorithms. To confirm that learning algorithm selection does not weights system accuracy user has to validate that the given dataset is a feature-oriented dataset. Thus, in this study we propose a simple verification procedure based on multi objective approach by means of elitist Non-dominated Sorting in Genetic Algorithm (NSGA-II). The way NSGA-II performs in this work is quite similar to the feature selection procedure except on interpretation of the results i.e. set of optimal solutions. Two conflicting minimization elements namely classification error and number of used features are taken as objective functions. A case study of fatigue segment classification was chosen for the purpose of this study where simulations were repeated using four single classifiers such as Naive-Bayes, k nearest neighbours, decision tree and radial basis function. The proposed procedure demonstrates that only two features are needed for classifying a fatigue segment task without having to place concern on learning algorithm

• Periodical: Applied Mechanics and Materials (Volume 165)
• Pages: 232-236
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.165.232
• Online since: April 2012
• Authors: Mohd Haniff Osman, Z.M. Nopiah, S. Abdullah
• Keywords: Classification, Fatigue Life, Feature Selection, Immune Features, NSGA-II

References

[1] J. Han and M. Kamber, Data Mining: Concepts and Techniques. California: Morgan Kaufmann, (2006).

[2] J. You and S. Shiliang, Feature selection for ensembles using Non-dominated Sorting in Genetic Algorithms, in Natural Computation (ICNC), 2010 Sixth International Conference on, 2010, pp.888-891.

DOI: 10.1109/icnc.2010.5583912

[3] O. Il-Seok, L. Jin-Seon, and M. Byung-Ro, Hybrid genetic algorithms for feature selection, Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 26, pp.1424-1437, (2004).

DOI: 10.1109/tpami.2004.105

[4] H. C. Lac and D. A. Stacey, Feature subset selection via multi-objective genetic algorithm, " in Neural Networks, 2005. IJCNN , 05. Proceedings. 2005 IEEE International Joint Conference on, 2005, pp.1349-1354 vol. 3.

DOI: 10.1109/ijcnn.2005.1556070

[5] C. -J. Huang, D. -X. Yang, and Y. -T. Chuang, Application of wrapper approach and composite classifier to the stock trend prediction, Expert Systems with Applications, vol. 34, pp.2870-2878, (2008).

DOI: 10.1016/j.eswa.2007.05.035

[6] S. B. Kotsiantis, Supervised Machine Learning: A Review of Classification Techniques, presented at the Proceeding of the 2007 conference on Emerging Artificial Intelligence Applications in Computer Engineering: Real Word AI Systems with Applications in eHealth, HCI, Information Retrieval and Pervasive Technologies, (2007).

[7] K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, A fast and elitist multiobjective genetic algorithm: NSGA-II, IEEE Trans. Evol. Comput, vol. 6, pp.182-197, (2002).

DOI: 10.1109/4235.996017

[8] Z. M. Nopiah, et al., Running damage extraction technique for identifying fatigue damaging events, WSEAS TRANSACTIONS on MATHEMATICS, vol. 9, pp.324-333, (2010).

[9] A. Nieslony, Rainflow Counting Algorithm, ed, (1999).

[10] B. Sreejith, A. K. Verma, and A. Srividya, Fault diagnosis of rolling element bearing using time-domain features and neural networks, in Industrial and Information Systems, 2008. ICIIS 2008. IEEE Region 10 and the Third international Conference on, 2008, pp.1-6.

DOI: 10.1109/iciinfs.2008.4798444

[11] N. E. Downing, Mean stress effects in stress-life and strain-life fatigue, in Fatigue 2004: Second SAE Brasil international conference on fatigue, Sao Paulo, Brazil, (2004).

DOI: 10.4271/2004-01-2227