Profit Suggestion Technique in Agronomics Using a New Heuristic-Based Barnacle Mating Honey Badger Algorithm I-BMHBA

Abstract

Second phase, the prediction in Minimum Support Price (MSP) is made through detected species. The required data in the price is gathered through online resources that are utilized for the data normalization stage in further. These normalized data are used in the deep feature extraction stage by utilizing the autoencoder and the Conventional Neural Network (CNN) to extract the required deep feature; it is then fused in that stage. Further, these fused features are fed into the optimal feature selection stage to choose the important optimal features by utilizing the newly developed algorithm Intensity-based Barnacle Mating Honey Badger Algorithm (I-BMHBA). Then, the selected features are fed into the Optimized Radial Basis Function + Gated Recurrent Unit (RBF + GRU) to predict MSP prices based on the crop type. The predicted prices are then divided into four shares as well as made the profit suggestion is through training the regional and location crops data. In the end, the Optimized RBF + GRU provide better profitable harvest outcomes. From these investigations, it is proven that the proposed profit suggestion via species prediction and MSP prediction method is better when assimilated with another existing model by utilizing the various performance metrics.