Vintage Prediction in Arachis Hypogaea using Fuzzy Cognitive Map and Multi Objective Firefly Approach

This work explores the yield exhibiting and prediction procedure in groundnut using the dynamic influence graph of Fuzzy Cognitive Maps (FCMs). In this work, a statistics determined non-linear FCM learning attitude was chosen to classify yield in Groundnut, where very few decision making techniques were inspected. Through the anticipated technique, FCMs were measured and recognized to epitomize experts' information for vintage estimate and crop supervision. The advanced FCM prototypical entails of nodes connected by focused boundaries, where the nodes characterize the main soil aspects moving produce, soil temperature, air temperature, humidity, organic matter (OM), soil surface temperature, and the directed edges show the cause-effect (weighted) relationships between the soil properties and yield. The main persistence of this learning was to categories groundnut yield using an resourceful FCM and firefly algorithm, and to compare it with the straight FCM tool and other hybrid algorithms. All algorithms have been executed in the similar data set of 56 cases restrained in 2005 in an groundnut orchard located in Coimbatore. The examination displayed the advantage of the FCM and multi objective approach in vintage forecast.