Combining genetic algorithms and neural networks to build a signal pattern classifier

In this paper we show how genetic algorithms and neural networks are combined to build a high-performance signal pattern classifier (GNSPC). Signal patterns are intrinsic to many sensor-based systems. The goal of GNSPC is to differentiate among large numbers of signal pattern classes with low classification cost and high classification performance. Classification performance is measured by the correct classification of noisy signal patterns despite using pure signal patterns for building the classifier. GNSPC is basically a decision tree classifier with similarity classification rules. The rules are used to test the similarity of signal patterns. A combination of a genetic algorithm and a neural network is used to find the best rules for the decision tree. This combination provides powerful classification capabilities with great tuning flexibility for either performance or cost-efficiency. Learning techniques are employed to set the genetic algorithm global parameters and to obtain training data for the neural network.

[1]  Carey E. Priebe,et al.  Olfactory Classification via Interpoint Distance Analysis , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Ricardo Gutierrez-Osuna,et al.  Pattern analysis for machine olfaction: a review , 2002 .

[3]  T. Ross.  Fuzzy Logic with Engineering Applications , 1994 .

[4]  H. T. Nagle,et al.  Using neural networks and genetic algorithms to enhance performance in an electronic nose , 1999, IEEE Transactions on Biomedical Engineering.

[5]  G. Dozier,et al.  Odor detection using pulse coupled neural networks , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[6]  Francisco Herrera,et al.  GENERATING FUZZY RULES FROM EXAMPLES USING GENETIC ALGORITHMS , 1995 .

[7]  C. Distante,et al.  A comparison between feature extraction methods of an electronic nose response , 2001, ICECS 2001. 8th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.01EX483).

[8]  I. Sugimoto,et al.  A neural network model for an electronic nose based on quartz-crystal microbalance sensors , 1999 .

[9]  J. Li,et al.  The Cyranose Chemical Vapor Analyzer , 2000 .

[10]  Roshdy S. Youssif,et al.  Fuzzy Similarity Measures for Signal Pattern Classification , 2003, MAICS.

[11]  Kenneth A. De Jong,et al.  Using genetic algorithms for supervised concept learning , 1990, [1990] Proceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence.

[12]  Ricardo Gutierrez-Osuna,et al.  The how and why of electronic noses , 1998 .

[13]  Kenneth A. De Jong,et al.  Using genetic algorithms for concept learning , 1993, Machine Learning.

[14]  Julian W. Gardner,et al.  Electronic noses: a review of signal processing techniques , 1999 .

[15]  E. J. Staples.  Virtual Chemical Sensor Arrays and High-Resolution Olfactory Images: The zNose , 2001 .

[16]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[17]  Carla Purdy,et al.  A multistrategy signal pattern classifier , 2002, The 2002 45th Midwest Symposium on Circuits and Systems, 2002. MWSCAS-2002..

[18]  Christopher R. Houck,et al.  A Genetic Algorithm for Function Optimization: A Matlab Implementation , 2001 .

[19]  Bernadette Bouchon-Meunier,et al.  Fuzzy Logic And Soft Computing , 1995 .

[20]  Jerzy W. Bala,et al.  Hybrid Learning Using Genetic Algorithms and Decision Trees for Pattern Classification , 1995, IJCAI.

[21]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[22]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[23]  C. Burrus,et al.  Noise reduction using an undecimated discrete wavelet transform , 1996, IEEE Signal Processing Letters.