Classification and yield prediction in smart agriculture system using IoT

The modern agriculture industry is data-centred, precise and smarter than ever. Advanced development of Internet-of-Things (IoT) based systems redesigned “smart agriculture”. This emergence in innovative farming gradually increases crop yields, reduces irrigation wastages making it more profitable. Machine learning (ML) methods achieve the requirement scaling performance model. paper introduces a hybrid ML model with IoT for yield prediction. work involves three phases: pre-processing, feature selection (FS) classification. Initially, dataset pre-processed FS done on basis Correlation (CBFS) Variance Inflation Factor algorithm (VIF). Finally, two-tier an smart system proposed. In first tier, Adaptive k-Nearest Centroid Neighbour Classifier (aKNCN) proposed to estimate soil quality classify samples into different classes input properties. second predicted using Extreme Learning (ELM). optimized strategy, weights are updated modified Butterfly Optimization Algorithm (mBOA) improve accuracy ELM minimum error values. PYTHON implementation tool evaluating system. Soil utilized evaluation prediction Various metrics such as accuracy, RMSE, R2, MSE, MedAE, MAE, MSLE, MAPE Explained Score (EVS) considered evaluation.