Dynamic Cluster Recognition with Multiple Self-Organising Maps

Abstract: A neural architecture, based on several self-organising maps, is presented which counteracts the parameter drift problem for an array of conducting polymer gas sensors when used for odour sensing. The neural architecture is named mSom, where m is the number of odours to be recognised, and is mainly constituted of m maps; each one approximates the statistical distribution of a given odour. Competition occurs both within each map and between maps for the selection of the minimum map distance in the Euclidean space. The network (mSom) is able to adapt itself to new changes of the input probability distribution by repetitive self-training processes based on its experience. This architecture has been tested and compared with other neural architectures, such as RBF and Fuzzy ARTMAP. The network shows long-term stable behaviour, and is completely autonomous during the testing phase, where re-adaptation of the neurons is needed due to the changes of the input probability distribution of the given data set.

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

[2]  Stephen Grossberg,et al.  ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.

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

[4]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[5]  I. Lundstrom,et al.  A Calibration Technique For An Electronic Nose , 1995, Proceedings of the International Solid-State Sensors and Actuators Conference - TRANSDUCERS '95.

[6]  Fabrizio Davide,et al.  Drift counteraction for an electronic nose , 1996 .

[7]  Fredrik Winquist,et al.  Drift counteraction in odour recognition applications: lifelong calibration method , 1997 .

[8]  Angel P. del Pobil,et al.  Multiple self-organizing maps: A hybrid learning scheme , 1997, Neurocomputing.

[9]  Antonio Pardo,et al.  Gas identification with tin oxide sensor array and self-organizing maps: adaptive correction of sensor drifts , 1998, IEEE Trans. Instrum. Meas..

[10]  Kaushal K. Shukla,et al.  ADAPTIVE RESONANCE NEURAL CLASSIFIER FOR IDENTIFICATION OF GASES/ODOURS USING AN INTEGRATED SENSOR ARRAY , 1998 .

[11]  Eduard Llobet,et al.  Fuzzy ARTMAP based electronic nose data analysis , 1999 .

[12]  J W Gardner and P N Bartlett,et al.  Electronic Noses: Principles and Applications , 1999 .

[13]  J. Haugen,et al.  A calibration method for handling the temporal drift of solid state gas-sensors , 2000 .

[14]  M. Sjöström,et al.  Drift correction for gas sensors using multivariate methods , 2000 .

[15]  Pietro Siciliano,et al.  Odor discrimination using adaptive resonance theory , 2000 .

[16]  Antonio A. F. Oliveira,et al.  Neural mechanisms for learning of attention control and pattern categorization as basis for robot cognition , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[17]  Panu Somervuo,et al.  Self-Organizing Maps and Learning Vector Quantization for Feature Sequences , 1999, Neural Processing Letters.