The Feasibility Study of Utilising Electronic Nose and ANN for Plant Malaise Detection

Abstract

The agricultural industry has been,for a long time, dependent upon human expertise in using odour for classification, grading, differentiating and discriminating different typesof produce. Odour was also used to determine the state of health of crops, although this is not favourable when dealing with detecting plant malaise that may pose health threats to human beings. In addition to these, human experts may take years of training and can be inconsistent, as well as prone to fatigue. This paper presents a work conducted on utilising an electronic nose incorporating artificial intelligence to detect plant malaise, specifically basal stem rot (BSR) disease that is caused by ganoderma boninense fungus affecting oil palm plantations. This study used a commercially available electronic nose, Cyranose 320 as the front end sensors and artificial neural networks for pattern recognition. The odour samples were captured on site at Besout oil palm plantation, and the classification performed on a PC. The results showed that the system was able to differentiate healthy and infected oil palm tree using different odour parameters with a high rate of accuracy. This proved the feasibility of using an enose with artificial intelligence to discriminate healthy and infected plants.