Fuzzy ARTMAP based electronic nose data analysis

Abstract The Fuzzy ARTMAP neural network is a supervised pattern recognition method based on fuzzy adaptive resonance theory (ART). It is a promising method since Fuzzy ARTMAP is able to carry out on-line learning without forgetting previously learnt patterns (stable learning), it can recode previously learnt categories (adaptive to changes in the environment) and is self-organising. This paper presents the application of Fuzzy ARTMAP to odour discrimination with electronic nose (EN) instruments. EN data from three different datasets, alcohol, coffee and cow's breath (in order of complexity) were classified using Fuzzy ARTMAP. The accuracy of the method was 100% with alcohol, 97% with coffee and 79%, respectively. Fuzzy ARTMAP outperforms the best accuracy so far obtained using the back-propagation trained multilayer perceptron (MLP) (100%, 81% and 68%, respectively). The MLP being by far the most popular neural network method in both the field of EN instruments and elsewhere. These results, in the case of alcohol and coffee, are better than those obtained using self-organising maps, constructive algorithms and other ART techniques. Furthermore, the time necessary to train Fuzzy ARTMAP was typically one order of magnitude faster than back-propagation. The results show that this technique is very promising for developing intelligent EN equipment, in terms of its possibility for on-line learning, generalisation ability and ability to deal with uncertainty (in terms of measurement accuracy, noise rejection, etc.).

[1]  Julian W. Gardner,et al.  Olfactory Feature Maps from an Electronic Nose , 1997 .

[2]  Lutgarde M. C. Buydens,et al.  ADAPTIVE RESONANCE THEORY-BASED NEURAL NETWORKS - THE ART OF REAL-TIME PATTERN-RECOGNITION IN CHEMICAL PROCESS MONITORING , 1995 .

[3]  Julian W. Gardner,et al.  Detection of Vapours and Odours from a Multisensor Array Using Pattern Recognition: Self-Organising Adaptive Resonance Techniques , 1996 .

[4]  Chin-Teng Lin,et al.  Neural fuzzy systems , 1994 .

[5]  J. Brezmes,et al.  Qualitative and quantitative analysis of volatile organic compounds using transient and steady-state responses of a thick-film tin oxide gas sensor array , 1997 .

[6]  Evor L. Hines,et al.  Genetic Algorithm Design of Neural Net Based Electronic Nose , 1993 .

[7]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[8]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[9]  Stephen Grossberg,et al.  Neural dynamics of surface perception: Boundary webs, illuminants, and shape-from-shading , 1987, Comput. Vis. Graph. Image Process..

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

[11]  Stephen Grossberg,et al.  A fuzzy ARTMAP nonparametric probability estimator for nonstationary pattern recognition problems , 1995, IEEE Trans. Neural Networks.

[12]  Julian W. Gardner,et al.  A brief history of electronic noses , 1994 .

[13]  Evor L. Hines,et al.  Prediction of health of dairy cattle from breath samples using neural network with parametric model of dynamic response of array of semiconducting gas sensors , 1999 .

[14]  J. Gardner,et al.  Application of an electronic nose to the discrimination of coffees , 1992 .

[15]  J. Gardner,et al.  Application of artificial neural networks to an electronic olfactory system , 1990 .

[16]  Julian W. Gardner,et al.  Pattern Recognition in Odour Sensing , 1992 .