Classification of Electronic Nose Data in Wound Infection Detection Based on PSO-SVM Combined with Wavelet Transform

Abstract

Abstract In this paper, a new method for classifying electronic nose data in rats wound infection detection based on support vector machine (SVM) and wavelet analysis was developed. Signals of the sensors were decomposed using wavelet analysis for feature extraction and a PSO-SVM classifier was developed for pattern recognition. The sensor array was optimized and model parameters were selected to achieve the maximum classification accuracy of SVM. Particle swarm optimization (PSO) was used to achieve optimization of the sensor array and the SVM model parameters. A classification rate of 97.5% was achieved by the proposed method for data discrimination. Compared with the methods of radial basis function (RBF) neural network classifier with maximum or wavelet coefficients feature and SVM without sensor array optimization, this method gave better performance on classification rate and time consumption in rats wound infection data recognition.