A Radial Basis Function Neural Network Classifier for the Discrimination of Individual Odor Using Responses of Thick-Film Tin-Oxide Sensors

• Published in: IEEE sensors journal Vol. 9; no. 10; pp. 1254 - 1261
• Main Authors: Kumar, R., Das, R.R., Mishra, V.N., Dwivedi, R.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2009; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Alcoholic beverages; Algorithm; Artificial neural networks; Backpropagation algorithms; Clustering algorithms; Electronic noses; Gas detectors; microsensors; Neural networks; pattern classification; Radial basis function networks; Sensor arrays; Thick film sensors
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2009.2030072

This paper presents a novel approach to odor discrimination of alcohols and alcoholic beverages using published data obtained from the responses of thick film tin oxide sensor array fabricated at our laboratory and employing a combination of transformed cluster analysis and radial basis function neural network. The performance of the new classifier was compared with others based on backpropagation (BP) algorithm. The new model has superior discrimination power with a much lower discrimination error. Also, it was found to be less sensitive to the variations in learning parameters apart from being significantly faster than the conventional models based on BP algorithm. Both raw data and data preprocessed by transformed cluster analysis (TCA) were used to train radial basis function neural network (RBFNN) and backpropagation network (BPN). Superior learning and classification performance was obtained using proposed model constituting TCA processed data and RBF network.