Determination of food age using neural network

Artificial intelligence (AI) is the aspect of computing concerned with programming computers to behave like humans. In spite of the fact that no artificial intelligence system is capable of fully simulating human behaviour, there are aspects which have been successfully mimicked. One of these applications is the development of intelligent systems to model the human sense of smell. The artificial neural network is one tool which makes inferences based on pattern recognition of selected parameters in their environment. This paper applies the neural network to the determination of food age using ammonia concentration as the major metric. The resulting algorithm is capable of determining age of common food types (in days) using supervised learning to obtain the knowledge inference database. A two process-layer neural network topology was observed to provide most accurate results with overall accuracy of 95 percent. Food samples used to obtain inference database include rice, beans, fresh vegetables, yam and potatoes.