Odorant recognition using biological responses recorded in olfactory bulb of rats

In this study we applied pattern recognition (PR) techniques to extract odorant information from local field potential (LFP) signals recorded in the olfactory bulb (OB) of rats subjected to different odorant stimuli. We claim that LFP signals registered on the OB, the first stage of olfactory processing, are stimulus specific in animals with normal sensory experience, and that these patterns correspond to the neural substrate likely required for perceptual discrimination. Thus, these signals can be used as input to an artificial odorant classification system with great success. In this paper we have designed and compared the performance of several configurations of artificial olfaction systems (AOS) based on the combination of four feature extraction (FE) methods (Principal Component Analysis (PCA), Fisher Transformation (FT), Sammon NonLinear Map (NLM) and Wavelet Transform (WT)), and three PR techniques (Linear Discriminant Analysis (LDA), Multilayer Perceptron (MLP) and Support Vector Machine (SVM)), when four different stimuli are presented to rats. The best results were reached when PCA extraction followed by SVM as classifier were used, obtaining a classification accuracy of over 95% for all four stimuli.

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

[2]  Eran Stark,et al.  Predicting Movement from Multiunit Activity , 2007, The Journal of Neuroscience.

[3]  S. Pixley,et al.  Cultured rat olfactory neurons are excitable and respond to odors. , 1990, Brain research. Developmental brain research.

[4]  Stephen C. Trowell,et al.  Bio-Benchmarking of Electronic Nose Sensors , 2009, PloS one.

[5]  S. A. Salah,et al.  Feature extraction and classification of Chilean wines , 2006 .

[6]  Alphus D. Wilson,et al.  Diverse Applications of Electronic-Nose Technologies in Agriculture and Forestry , 2013, Sensors.

[7]  O. Rioul,et al.  Wavelets and signal processing , 1991, IEEE Signal Processing Magazine.

[8]  C. Braun,et al.  Hand Movement Direction Decoded from MEG and EEG , 2008, The Journal of Neuroscience.

[9]  Ambuj Tewari,et al.  On the Consistency of Multiclass Classification Methods , 2007, J. Mach. Learn. Res..

[10]  J. E. Skinner,et al.  Field potential response changes in the rabbit olfactory bulb accompany behavioral habituation during the repeated presentation of unreinforced odors , 2004, Experimental Brain Research.

[11]  Linda B. Buck,et al.  A Large-Scale Analysis of Odor Coding in the Olfactory Epithelium , 2011, The Journal of Neuroscience.

[12]  M. C. Horrillo,et al.  Identification of typical wine aromas by means of an electronic nose , 2004, Proceedings of IEEE Sensors, 2004..

[13]  Manuel A. Duarte-Mermoud,et al.  Classification of Chilean Wines , 2008 .

[14]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[15]  Qingjun Liu,et al.  The Study on Bionic Olfactory Neurochip Based on Light-addressable Potentiometric Sensor , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[16]  Alexander Vergara,et al.  Algorithmic mitigation of sensor failure: is sensor replacement really necessary? , 2013 .

[17]  L. Haberly,et al.  Beta and gamma oscillations in the olfactory system of the urethane-anesthetized rat. , 2003, Journal of neurophysiology.

[18]  Manuel A. Duarte-Mermoud,et al.  Chilean Wine Classification Using Volatile Organic Compounds Data Obtained With a Fast GC Analyzer , 2008, IEEE Transactions on Instrumentation and Measurement.

[19]  King-Sun Fu,et al.  Digital pattern recognition , 1976, Communication and cybernetics.

[20]  O. Bertrand,et al.  Olfactory learning modifies the expression of odour‐induced oscillatory responses in the gamma (60–90 Hz) and beta (15–40 Hz) bands in the rat olfactory bulb , 2003, The European journal of neuroscience.

[21]  C. Koch,et al.  Decoding visual inputs from multiple neurons in the human temporal lobe. , 2007, Journal of neurophysiology.

[22]  V. Jayaraman,et al.  Intensity versus Identity Coding in an Olfactory System , 2003, Neuron.

[23]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[24]  Sergios Theodoridis,et al.  Pattern Recognition , 1998, IEEE Trans. Neural Networks.

[25]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[26]  Hua Yu,et al.  A direct LDA algorithm for high-dimensional data - with application to face recognition , 2001, Pattern Recognit..

[27]  P. Maldonado,et al.  Odorant modulation of neuronal activity and local field potential in sensory-deprived olfactory bulb , 2009, Neuroscience.

[28]  Leslie M Kay,et al.  Chemical factors determine olfactory system beta oscillations in waking rats. , 2007, Journal of neurophysiology.

[29]  L. Pla.  Analisis Multivariado: Metodo de Componentes Principales. , 1987 .

[30]  Xuewen Lu,et al.  Use of the electronic nose and gas chromatography-mass spectrometry to determine the optimum time for aging of beer , 2002 .

[31]  J. William Ahwood,et al.  CLASSIFICATION , 1931, Foundations of Familiar Language.

[32]  Andrew R. Webb,et al.  Statistical Pattern Recognition , 1999 .

[33]  Michael L. Hines,et al.  Sparse Distributed Representation of Odors in a Large-scale Olfactory Bulb Circuit , 2013, PLoS Comput. Biol..

[34]  Gilles Sicard,et al.  Rhythm sequence through the olfactory bulb layers during the time window of a respiratory cycle , 2003, The European journal of neuroscience.

[35]  Alexandre Perera-Lluna,et al.  Biologically Inspired Computation for Chemical Sensing , 2011, FET.

[36]  Nello Cristianini,et al.  Advances in Kernel Methods - Support Vector Learning , 1999 .

[37]  G. Laurent,et al.  Temporal Representations of Odors in an Olfactory Network , 1996, The Journal of Neuroscience.

[38]  Gonzalo Bailador,et al.  Analysis of pattern recognition and dimensionality reduction techniques for odor biometrics , 2013, Knowl. Based Syst..

[39]  Pere Caminal,et al.  Drift Compensation of Gas Sensor Array Data by Common Principal Component Analysis , 2010 .

[40]  M. C. Horrillo,et al.  Electronic nose for the identification of spoiled Iberian hams , 2005, Conference on Electron Devices, 2005 Spanish.

[41]  L. C. Katz,et al.  Optical Imaging of Odorant Representations in the Mammalian Olfactory Bulb , 1999, Neuron.

[42]  Manuele Bernabei,et al.  Design of a very large chemical sensor system for mimicking biological olfaction , 2010 .

[43]  Sergios Theodoridis,et al.  Pattern Recognition, Third Edition , 2006 .

[44]  E. Patrick,et al.  Fundamentals of Pattern Recognition , 1973 .

[45]  G. Laurent,et al.  Impaired odour discrimination on desynchronization of odour-encoding neural assemblies , 1997, Nature.

[46]  Shankar Vembu,et al.  Chemical gas sensor drift compensation using classifier ensembles , 2012 .

[47]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[48]  Paul Henderson.  Sammon Mapping , 2010 .

[49]  Ricardo Gutierrez-Osuna,et al.  Pattern analysis for machine olfaction: a review , 2002 .

[50]  Qingjun Liu,et al.  Olfactory cell-based biosensor: a first step towards a neurochip of bioelectronic nose. , 2006, Biosensors & bioelectronics.

[51]  Manuel A. Duarte-Mermoud,et al.  Chilean wine varietal classification using quadratic Fisher transformation , 2010, Pattern Analysis and Applications.

[52]  K. Persaud,et al.  Analysis of discrimination mechanisms in the mammalian olfactory system using a model nose , 1982, Nature.

[53]  Rached Tourki,et al.  Effect of the feature vector size on the generalization error: the case of MLPNN and RBFNN classifiers , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[54]  Ricardo Gutierrez-Osuna,et al.  Sensor-based machine olfaction with a neurodynamics model of the olfactory bulb , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[55]  N. Kopell,et al.  Olfactory Bulb Gamma Oscillations Are Enhanced with Task Demands , 2007, The Journal of Neuroscience.

[56]  Claire Martin,et al.  Learning-induced modulation of oscillatory activities in the mammalian olfactory system: The role of the centrifugal fibres , 2004, Journal of Physiology-Paris.

[57]  Davis Yen Pan.  Digital Audio Compression , 1993, Digit. Tech. J..

[58]  C. Mehring,et al.  Inference of hand movements from local field potentials in monkey motor cortex , 2003, Nature Neuroscience.

[59]  M. Gribaudo,et al.  2002 , 2001, Cell and Tissue Research.

[60]  Tzay Y. Young,et al.  Classification, Estimation and Pattern Recognition , 1974 .

[61]  Ma Yun-hui.  Discoveries of odorant receptors and the organization of the olfactory system , 2005 .

[62]  Naoshige Uchida,et al.  Odor maps in the mammalian olfactory bulb: domain organization and odorant structural features , 2000, Nature Neuroscience.

[63]  W. Freeman,et al.  Frequency analysis of olfactory system EEG in cat, rabbit, and rat. , 1980, Electroencephalography and clinical neurophysiology.

[64]  Jordi Fonollosa,et al.  Quality Coding by Neural Populations in the Early Olfactory Pathway: Analysis Using Information Theory and Lessons for Artificial Olfactory Systems , 2012, PloS one.

[65]  A. Gutierrez-Galvez,et al.  Signal and Data Processing for Machine Olfaction and Chemical Sensing: A Review , 2012, IEEE Sensors Journal.

[66]  Matt Wachowiak,et al.  Distributed and concentration-invariant spatial representations of odorants by receptor neuron input to the turtle olfactory bulb. , 2002, Journal of neurophysiology.

[67]  G. P. Nason.  A little introduction to wavelets , 1999 .

[68]  John W. Sammon,et al.  A Nonlinear Mapping for Data Structure Analysis , 1969, IEEE Transactions on Computers.

[69]  R. Fisher.  THE STATISTICAL UTILIZATION OF MULTIPLE MEASUREMENTS , 1938 .