Pattern analysis for machine olfaction: a review

IEEE Sensors Journal - Tập 2 Số 3 - Trang 189-202 - 2002
R. Gutierrez-Osuna1
1Department of Computer Science, Texas A and M University, College Station, TX, USA

Tóm tắt

Pattern analysis constitutes a critical building block in the development of gas sensor array instruments capable of detecting, identifying, and measuring volatile compounds, a technology that has been proposed as an artificial substitute for the human olfactory system. The successful design of a pattern analysis system for machine olfaction requires a careful consideration of the various issues involved in processing multivariate data: signal-preprocessing, feature extraction, feature selection, classification, regression, clustering, and validation. A considerable number of methods from statistical pattern recognition, neural networks, chemometrics, machine learning, and biological cybernetics have been used to process electronic nose data. The objective of this review paper is to provide a summary and guidelines for using the most widely used pattern analysis techniques, as well as to identify research directions that are at the frontier of sensor-based machine olfaction.

Từ khóa

#Pattern analysis #Sensor arrays #Feature extraction #Gas detectors #Instruments #Humans #Olfactory #Signal design #Signal processing #Pattern recognition

Tài liệu tham khảo

kirkpatrick, 1983, optimization by simulated annealing, Science, 220, 671, 10.1126/science.220.4598.671 10.1016/0167-8655(94)90127-9 gutierrez-osuna, 1998, Signal Processing and Pattern Recognition for an Electronic Nose 10.1109/34.824819 10.1016/S0168-1699(96)01307-5 10.1109/T-C.1969.222678 10.1109/TC.1977.1674939 doak, 1992, An Evaluation of Feature Selection Methods and Their Application to Computer Security devijver, 1982, Pattern Recognition a Statistical Approach kermani, 1996, On using neural networks and genetic algorithms to optimize the performance of an electronic nose fukunaga, 1991, Introduction to statistical pattern recognition 10.1016/S0925-4005(97)80335-8 duda, 2000, Pattern Classification 10.1002/1099-128X(200009/12)14:5/6<711::AID-CEM607>3.3.CO;2-W 10.1016/S0925-4005(97)80096-2 gutierrez-osuna, 2000, drift reduction for metal-oxide sensor arrays using canonical correlation regression and partial least squares, Electronic Noses and Olfaction 2000 10.1016/0925-4005(94)01593-7 10.1016/0925-4005(94)87073-X sundic, 2000, fuzzy logic processing in combined carbon monoxide and methane domestic gas alarms, Electronic Noses and Olfaction 2000 10.1016/S0925-4005(97)80124-4 10.1109/IMTC.1997.610256 bargagna, 2000, fuzzy logic classification of olive oils, Electronic Noses and Olfaction 2000 rumelhart, 1986, learning internal representations by error backpropagation, Parallel Distributed Processing Explorations in the Microstructure of Cognition Vol1 Foundations, 318 le cun, 1998, efficient backprop, Neural Networks Tricks of the Trade, 9, 10.1007/3-540-49430-8_2 10.1016/0893-6080(91)90033-2 sarle, 1995, stopped training and other remedies for overfitting, Proc 27th Symp Interface Comput Sci Statistics, 352 hassibi, 1993, second order derivatives for network pruning: optimal brain surgeon, Advances in Neural Inform Processing Systems, 5, 164 le cun, 1990, optimal brain damage, Advances in Neural Inform Processing Systems, 2, 598 fahlman, 1990, the cascade-correlation learning architecture, Advances in Neural Inform Processing Systems, 2, 524 bishop, 1995, Neural Networks for Pattern Recognition 10.1007/BF02551274 haykin, 1999, Neural Networks A Comprehensive Foundation 10.1007/978-3-662-03315-9 10.1016/S0925-4005(97)80272-9 10.1002/3527601597.ch5 10.1016/0925-4005(94)01572-4 10.1002/1616-8984(199801)3:1<61::AID-SEUP61>3.0.CO;2-7 ikohura, 1994, The Stannic Oxide Gas Sensor 10.1088/0957-0233/2/5/008 dasarathy, 1991, Nearest Neighbor (NN) Norms NN Pattern Classification Techniques 10.1016/0925-4005(90)85002-G 10.1016/S0924-4247(99)00195-8 theodoridis, 1999, Pattern Recognition 10.2307/2289860 10.1007/978-1-4899-3324-9 hall, 1997, feature subset selection: a correlation based filter approach, Proc Intl Conf Neural Inform Processing Intell Inform Syst, 855 10.1016/B978-1-55860-335-6.50023-4 10.1016/S0925-4005(98)00083-5 10.1016/S0003-2670(98)00739-9 10.1002/cem.1180070104 10.1016/0003-2670(86)80028-9 wold, 1975, soft modeling by latent variables; the nonlinear iterative partial least squares approach, Perspectives in Probability and Statistics Papers in Honor of M S Bartlett, 520 10.1017/CBO9780511812651 10.1016/0003-2670(93)80001-2 10.1016/0925-4005(92)80187-3 10.1016/S0003-2670(98)00780-6 10.1016/0925-4005(94)87091-8 10.1016/S0925-4005(99)00386-X 10.1016/S0925-4005(00)00485-8 10.1016/0893-6080(90)90019-H 10.1162/neco.1989.1.2.281 hampshire, 1990, equivalence proofs for multi-layer perceptron classifiers and the bayesian discriminant function, Connectionist Models Proc 1990 Summer School, 159 10.1109/79.180705 10.1109/72.80341 schürmann, 1996, Pattern Classification A Unified View of Statistical and Neural Approaches gardner, 1999, Electronic Noses Principles and Applications 10.1016/S0303-2647(96)01660-7 10.2307/1269656 10.1109/3477.790446 10.1016/S0925-4005(00)00645-6 10.1088/0957-0233/9/1/016 gardner, 1996, detection of vapors and odours from a multisensor array using pattern recognition: self-organizing adaptive resonance theory, Meas Contr, 29, 172, 10.1177/002029409602900603 10.1006/jcss.1997.1504 grossberg, 1976, adaptive pattern classification and universal recoding: ii. feedback, expectation, olfaction and illusions, Biol Cybern, 23, 187, 10.1007/BF00340335 10.1007/BF00058655 10.1016/S0924-4247(97)80096-9 masters, 1995, Advanced Algorithms for Neural Networks 10.1109/IJCNN.1998.682358 10.1007/978-1-4899-4541-9 10.1016/0925-4005(96)01917-X hines, 1997, olfactory feature maps from an electronic nose, Meas Contr, 30, 262, 10.1177/002029409703000902 10.1016/S0925-4005(97)80134-7 10.1088/0957-0233/8/11/004 10.1016/S0167-8655(01)00040-X yea, 1994, the discrimination of many kinds of odour species using fuzzy reasoning and neural networks, Sens Actuators A, 45, 159, 10.1016/0924-4247(94)00831-0 10.1016/S0925-4005(97)00309-2 10.1016/S0303-2647(96)01661-9 10.1016/S0925-4005(99)00288-9 10.1016/S0019-9958(65)90241-X 10.1088/0957-0233/8/2/005 10.1039/a804018d 10.1049/ip-cds:19990670 10.1016/0925-4005(91)80185-M 10.1016/S0925-4005(97)80080-9 10.1016/S0003-2670(97)87788-4 10.1016/S0925-4005(99)00290-7 10.1016/S0925-4005(99)00186-0 10.1039/a804019b 10.1002/3527601597.ch13 10.1016/S0925-4005(97)80283-3 10.1016/0925-4005(92)80203-A 10.1007/s004220050430 10.1016/S0003-2670(99)00784-9 10.1021/ac970427x 10.1109/SENSOR.1995.717323 therrien, 1989, Decision Estimation and Classification An Introduction to Pattern Recognition and Related Topics 10.1016/S0925-2312(01)00455-6 10.1021/ac950671t 10.1016/S0925-4005(97)00240-2 10.1007/BF00317988 10.1126/science.2315702 wilson, 1989, the simulation of large-scale neural networks, Methods in Neuronal Modeling From Synapses to Networks, 291 10.1016/0925-4005(94)01531-L 10.1088/0954-898X/11/1/305 10.1109/BIBE.2001.974433 albrecht, 1994, an intelligent gas sensor system for the identification of hazardous airborne compounds using an array of semiconductor gas sensors and kohonen feature map neural networks, Second International Conference on Intelligent Systems Engineering (Conf Publ No 395), 130, 10.1049/cp:19940614 10.1007/BF00337288 10.1016/0003-2670(94)00085-9 10.1016/0925-4005(94)01595-9 10.1016/S0003-2670(00)82573-8