Modeling Artificial Neural Network of Insect’s Proliferation During Cocoa Beans Storage

The cocoa bean is a grain which is the raw material for the economy of Côte d'Ivoire. Thus, throughout the bean value chain, particular attention is paid to quality. In this chain, storage remains an imported step. Indeed, insects are one of the pests causing enormous damage and losses in the conservation of stored grains. These insects are also present during the storage of cocoa beans. The proliferation of insects is due to several physico-chemical and environmental factors such as water content (Te), sugar content (TSu) and temperature (T°) which interact in the bean ecosystem. This proliferation remains difficult to control and estimate. In this work, we invented a method based on neural networks to determine the evolution of insect density. Indeed, an Insect Dynamics Model (MDI) has been established. To validate the effectiveness of the proposed method, we have chosen as performance criteria the coefficient of determination R²=0.9982. This shows a good correlation of the experimental values and those predicted. This result was obtained, with an optimal 4-5-1 architecture selected by Akaike's information criterion.