Sunflower Optimization Technique for Ideal Water Control using Deep CNN

IoT offers integrating networks to provide seamless services to people. In regions with limited water resources, agriculture is essential to the sustainable cultivation of sugarcane. Due to rising water demands and excessive demands to increase output, effective water use is a serious limitation in agriculture. For the best water management of sugarcane crops, the Sun-flower Atom Optimization DCNN is suggested in this paper. For this situation, the push-based strategy and log change are utilized to set up the information for handling. Additionally, a feature score is adjusted using the Apriori algorithm to pick the most useful feature from a large place of available features. The Apriori algorithm contributes to a classifier's increased accuracy. The new feature score was developed to identify. The feature score is a brand-new tool created to find useful features for calculating watering quantity. Using DeepCNN, which was prepared utilizing the proposed Sunflower Atom Optimization (SFAO) calculation, the water controlling stage is completed. The proposed SFAO-profound CNN overcame different strategies with maximal Specificity of 91.2%, sensitivity of 94.1% and accuracy of 91.2% separately.