Sensor Array Optimization by Cluster Analysis and GeneticAlgorithms

摘要

In a sensor array system, sensor selection is a feature space optimization problem where the optimal sensors arechosen to maximize the distance among sensor responses to different analytes. The purpose is to improve the qualityof inputs to a pattern classifier, thereby, improve correct classification rate. This paper introduces an integratedapproach of cluster analysis (CA) and genetic algorithms (GA) to find the optimal subset of sensors in the arraywhich can provide maximum distance in response to certain analytes, on the premise that more diversity of sensorsleads to better classification performance. The cluster analysis is able to identify the number of sensors to form anarray. The results obtained from the cluster analysis are then used by the genetic algorithm to obtain the best subsetfrom the array. The results indicate that the proposed procedure can successfully identify a sensor subset capable ofperforming the detection task with improved selectivity.