Kernel Approach on Detection of Ethanol Concentration Using ZnO Gas Sensor

Ethanol is the major consumable biofuel which is highly inflammable. So the detection of ethanol at its different concentration is certainly required. In this paper a cost effective thick-film gas sensor based on ethanol detection has been described. The sensor exhibits excellent ethanol sensing characteristics at the temperatures between 175 °C to 300 °C and the characteristics of the sensor for different concentration of the ethanol gas has been successfully studied by performing a nonlinear form of principal component analysis (PCA) to cluster the different concentration of ethanol. The present method is to classify the 230 samples of each concentration levels of gas using kernel principal component analysis (KPCA). Ethanol gas is a volatile organic compound (VOC) which is little difficult to distinguish the different concentration level in their nominal method.In this regard, classifiers having the machine learning ability can be of great benefit by automatically including the newly presented patterns in the training dataset without affecting class integrity of the previously trained system. In the presented paper, the kernel principal component analysis (KPCA) is used in the clustering algorithm for ethanol concentration discrimination with the help of thick film gas sensor.

[1]  B. Tudu,et al.  Comparison of multivariate normalization techniques as applied to electronic nose based pattern classification for black tea , 2008, 2008 3rd International Conference on Sensing Technology.

[2]  C. Natale,et al.  Evaluation of Italian wine by the electronic tongue: recognition, quantitative analysis and correlation with human sensory perception , 2003 .

[3]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[4]  K. Toko,et al.  Electronic tongue. , 1998, Biosensors & bioelectronics.

[5]  Kiyoshi Toko,et al.  RETRACTED: Electronic tongue , 1998 .

[6]  Thomas S. Huang,et al.  Facial expression recognition: A clustering-based approach , 2003, Pattern Recognit. Lett..

[7]  S. Phanichphant,et al.  Fabrication of various thickness of flame-made nano zinc oxide thick film and its response to ethanol , 2008, 2008 2nd IEEE International Nanoelectronics Conference.

[8]  Ingemar Lundström,et al.  Data preprocessing enhances the classification of different brands of Espresso coffee with an electronic nose , 2000 .

[9]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[10]  G. Baudat,et al.  Generalized Discriminant Analysis Using a Kernel Approach , 2000, Neural Computation.

[11]  Nabarun Bhattacharyya,et al.  Electronic Nose for Black Tea Classification and Correlation of Measurements With “Tea Taster” Marks , 2008, IEEE Transactions on Instrumentation and Measurement.

[12]  Sadaaki Miyamoto,et al.  Possibilistic Approach to Kernel-Based Fuzzy c-Means Clustering with Entropy Regularization , 2005, MDAI.

[13]  H. T. Nagle,et al.  Handbook of Machine Olfaction , 2002 .

[14]  Hiroyuki Goto,et al.  Efficient Scheduling Focusing on the Duality of MPL Representation , 2007, 2007 IEEE Symposium on Computational Intelligence in Scheduling.

[15]  Gregory A. Bakken,et al.  Computational methods for the analysis of chemical sensor array data from volatile analytes. , 2000, Chemical reviews.