Dwarf Mongoose Optimization with DL Based Soil Classification Model for Precision Agriculture

Abstract

In the agricultural sector, soil quality plays a pivotal role in determining crop types. Traditional manual soil analysis can be time-consuming and reliant on a limited number of experts, often resulting in insufficient knowledge about local soil conditions. For accurate soil classification process, this study develops a Dwarf Mongoose Optimization with DL Based Soil Classification (DMODL-SC) model. The presented DMODL-SC technique majorly recognizes different kinds of soil using CV and DL models. In the presented DMODL-SC technique, bilateral filtering (BF) technique is used for noise removal process which eradicate the presence of noise exist in the soil images and enhances its quality. In addition, the presented DMODL-SC technique employs capsule network (CapsNet) model for feature extraction process. Moreover, Denoising Auto Encoder (DAE) is exploited for the identification and classification of soil. Since the manual hyperparameter tuning is a tedious process, the DMO algorithm is applied to tune the hyperparameters related to the DAE model. To demonstrate the enhanced performance of the projected DMODL-SC system, an extensive range of experiments were performed. The comparison study reported the improvised soil classification performance of the DMODL-SC technique over other approaches with maximum accuracy of 95.92%.