Feature Selection Assessment and Comparison using Two Saliency Measures in an Elman Recurrent Neural Network

Proceedings of the International Joint Conference on Neural Networks

Volumn 4, Issue , 2003, Pages 2807-2812

  Laine, Trevor I ^a   Bauer, Kenneth W ^a  

^a AIR FORCE INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

SALIENCY MEASURES;

FEATURE EXTRACTION; PROBLEM SOLVING; SIGNAL TO NOISE RATIO;

RECURRENT NEURAL NETWORKS;

EID: 0141592439     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (24)

1. K.W. Bauer, S.G. Alsing, and K.A. Greene, "Feature screening using signal to-noise ratios", Neurocomputing, Vol 31, Mar 2000, pp. 29-44.
2. G. Castellano and A. M. Fanelli, "Variable selection using neural-network models," Neurocomputing, Vol 31, Mar 2000, pp. 1-13.
3. J.L. Elman, "Finding structure in time," Cognitive Science, Vol 14, 1990, pp. 179-211.
4. R. Feraud and F. Clerot, "A methodology to explain neural network classification," Neural Networks, Vol 15, 2002, pp. 237-246.
5. K.A. Greene, Feature Saltency In Artificial Neural Networks With Application To Modeling Workload, Ph.D. Dissertation, Air Force Institute of Technology, WPAFB, OH, Dec 1998.
6. K.A. Greene, K.W. Bauer, M. Kabrisky, S.K. Rogers, and G.F. Wilson, "Estimating pilot workload using Elman recurrent neural networks: a preliminary investigation," Intelligent Engineering Systems through Artificial Neural Networks, Vol 7, Proc. of the ANNIE Int'l. Conf., Nov 1997, pp. 703-708.
7. K.A. Greene, K.W. Bauer, M. Kabrisky, S.K. Rogers, and G.F. Wilson, "Determining the memory capacity of an Elman recurrent neural network," Intelligent Engineering Systems through Artificial Neural Networks, Vol 8, Proc. of the ANNIE Int'l. Conf., Nov 1998, pp. 37-42.
8. K.A. Greene, K.W. Bauer, G.F. Wilson, C.A. Russell, S.K. Rogers, and M. Kabrisky, "Selection of psychophysiological features for classifying air traffic controller workload in neural networks," Smart Eng. Sys. Design, Vol 2, 2000, pp. 315-330.
9. N. Kwak. and C.H. Choi, "Input feature selection for classification problems," IEEE Trans. on Neural Networks, Vol. 13, No 1, Jan 2002, pp. 143-159.
10. T.I. Laine, K.W. Bauer, and J.W. Lanning, "Multiple crewmember workload classification using neural networks with input feature selection," Intelligent Engineering Systems through Artificial Neural Networks, Vol 9, Proc. of the ANNIE Int'l. Conf., St. Louis, MO, 7-10 Nov 1999.
11. T.I. Laine, K.W. Bauer, J.W. Lanning, C.A. Russel, and G.F. Wilson, "Selection of input features across subjects for classifying crewmember workload using artificial neural networks," IEEE Trans. on Sys., Man, and Cybernetics: Part A, Vol. 32, No. 6, Nov 2002, pp. 691-704.
12. B. Lazzerini and F. Marcelloni, "Feature selection based on similarity," Electronics Letters, Vol 38, No. 3, 2002, pp. 121-122.
13. B. Mak and R.W. Blanning, "An empirical measure of element contribution in neural networks," IEEE Trans. on Sys., Man, and Cybernetics: Part C, Vol 28, Nov 1998, pp. 561-564.
14. J. Moody, "Forecasting the economy with neural nets: a survey of challenges and solutions," Neural Networks: tricks of the trade, Orr, G.B and Muller, K.R. (ed.). New York, NY: Springer, 1998, pp. 348-371.
15. D. Nguyen and B. Widrow, "Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights," Int'l. Joint Conf. on Neural Networks, Vol 3, 1990, pp. 21-26.
16. B.P. Pearlmutter, "Gradient calculations for dynamic recurrent neural networks," A Field Guide to Dynamical Neural Networks, Kolen, J. F. and Kremer, S. C. (ed.). Piscataway, NJ: IEEE Press, 2001, pp179-206.
17. S Piramuthu. "Feature selection for financial credit-risk evaluation decisions," INFORMS J. on Computing, Vol 11, No 3, Summer 1999, pp. 258-266.
18. D.W. Ruck, Characterization Of Multilayer Perceptrons And Their Application To Multisensor Automatic Target Detection, Ph.D. Dissertation, Air Force Institute of Technology, WPAFB, OH, Dec 1990.
19. D.W. Ruck, S.K. Rogers, and M. Kabrisky, "Feature selection using a multilayer perceptron," J. of Neural Network Computing, Fall 1990, pp. 40-48.
20. G.L. Tarr, Multilayered Feedforward Neural Networks For Image Segmentation, Ph.D. Dissertation, Air Force Institute of Technology, WPAFB, OH, 1991.
21. J. Utans, J. Moody, S. Rehfuss, and H. Siegelmann, "Input variable selection for neural networks: application to predicting the U.S. buisiness cycle," Proc. of the IEEE/IAFE 1995 CIFE. New York, NY: IEEE Press, 1995, pp. 118-122.
22. A. Verikas, and M. Bacauskiene, "Feature selection with neural networks," Pattern Rec. Letters, Vol 23, 2002, pp. 1323-1335.
23. D. D. Wackerly, W. Mendenhall, and R. L. Scheafer, Mathematical Statistics with Applications. Belmont, CA: Duxbury Press, 1996.
24. H. Zhang and G. Sun, "Feature selection using tabu search method," Pattern Recognition, Vol 35, 2002, pp. 701-711.