Application Specific Electronic Nose (ASEN) for Ganoderma boninense detection using artificial neural network

Abstract

Oil palm has many usages and mainly is used in food, detergent and medical products. However, the crop is susceptible to diseases where one of them, the Basal Stem Rot (BSR) disease, is affecting oil palm plantations in Malaysia and Indonesia. Currently, most of the detection techniques in treating the disease require detailed operating procedures and some are still not fully tested. In this paper, the Application Specific Electronic Nose (ASEN) is proposed to be used in Ganoderma boninense detection which is the basidiomycetes fungi of BSR disease. The specific sensor arrays will increase the instrument performance while reducing the cost, processing time and noise. The instrument data processing uses Artificial Neural Network (MLP, PNN and RBF) classification model. Initial results show that the instrument was able to detect the fungus. The instrument provides an effective low cost non-destructive method for the disease detection. This indicates that the instrument can be used as a detection system for plant disease monitoring.