ADAPTIVE RESONANCE NEURAL CLASSIFIER FOR IDENTIFICATION OF GASES/ODOURS USING AN INTEGRATED SENSOR ARRAY

Abstract A new approach to intelligent gas sensor (IGS) design using a classifier based on adaptive resonance theory (ART) artificial neural network (ANN) is presented. Using published data of sensor arrays fabricated and characterised at our laboratory, we demonstrate excellent gas/odour identification performance of our classifier for a 4-gas, 4-sensor system to identify individual gas/odour. Since the ART neural network is a self-organising classifier trained in the unsupervised mode, it avoids the drawbacks associated with static feedforward neural networks trained with a locally optimal backpropagation-type training algorithms applied by researchers in the recent past. The ART neural network offers easy implementability and real time performance in addition to giving excellent classification accuracy as demonstrated by our experiments.

[1]  Dominique Rebière,et al.  Thick film pellistor array with a neural network post-treatment , 1995 .

[2]  M. Siegel,et al.  Intelligent Thick‐film Gas Sensor , 1987 .

[3]  J. V. Hatfield,et al.  A new generation of integrated electronic noses , 1995 .

[4]  T. Kohonen.  Adaptive, associative, and self-organizing functions in neural computing. , 1987, Applied optics.

[5]  Sunil K. Srivastava,et al.  Sensitivity and response times of doped tin oxide integrated gas sensors , 1994 .

[6]  Evor L. Hines,et al.  Detection of vapours and odours from a multisensor array using pattern-recognition techniques Part 2. Artificial neural networks , 1992 .

[7]  C. Ranson,et al.  Application of multiple regression methods and automatic testing equipment to the characterization of ‘smart’ sensors☆ , 1987 .

[8]  S.K. Pal,et al.  Neurocomputing motivation, models, and hybridization , 1996, Computer.

[9]  Wolfgang Rosenstiel,et al.  Application of neural-network systems to the dynamic response of polymer-based sensor arrays , 1995 .

[10]  Diana Hodgins,et al.  The development of an electronic ‘nose’ for industrial and environmental applications , 1995 .

[11]  M. S. Nayak,et al.  Transformed cluster analysis: an approach to the identification of gases/odours using an integrated gas-sensor array , 1993 .

[12]  G. Horner,et al.  Gas analysis by partial model building , 1990 .

[13]  Konrad Colbow,et al.  Selective thermally cycled gas sensing using fast Fourier-transform techniques , 1990 .

[14]  Y. S. Tarng,et al.  Adaptive pattern recognition of drilling chatter , 1995 .

[15]  H. V. Shurmer,et al.  The application of discrimination technique to alcohols and tobaccos using tin-oxide sensors , 1989 .

[16]  T. Nakamoto,et al.  Perfume and flavour identification by odour-sensing system using quartz-resonator sensor array and neural-network pattern recognition☆ , 1993 .

[17]  Erkki Oja,et al.  Neural and statistical classifiers-taxonomy and two case studies , 1997, IEEE Trans. Neural Networks.

[18]  P. Mars,et al.  Vapour recognition using organic films and artificial neural networks , 1994 .

[19]  S. Grossberg,et al.  ART 2: self-organization of stable category recognition codes for analog input patterns. , 1987, Applied optics.

[20]  J. Gardner.  Detection of vapours and odours from a multisensor array using pattern recognition Part 1. Principal component and cluster analysis , 1991 .