Chaotic Jaya Optimization Algorithm with Computer Vision based Soil Type Classification for Smart Farming

Smart farming helps to increase yield by smartly deciding the steps that should be practised in season. A few components of precision are recommending crops for cultivation, predicting weather conditions, examining soil; determining pesticides, and fertilizers have used. Farming utilizes advanced technologies namely data mining (DM), machine learning (ML), Internet Things (IoT), analytics collecting data, outcomes training system. One most significant parameters is proper soil prediction which decides crop manually executed agriculturalists. Hence, farmer’s efficacy can improved producing automated tools type classification. This study presents a Chaotic Jaya Optimization Algorithm with Computer Vision based Soil Type Classification (CJOCV-STC) smart farming. The presented CJOCV-STC technique applies CV metaheuristic algorithms classification process, identifies into distinct types. To accomplish this, uses SqueezeNet model set feature vectors. improve performance model, CJO algorithm used hyperparameter tuning process. Moreover, Elman neural network (ENN) applied related it adjusted chicken swarm (CSA). method studied on Kaggle dataset stated better over other recent approaches increased accuracy 98.47%.