Cybernetics approaches in intelligent systems for crops disease detection with the aid of IoT

Detection of crop diseases is imperative for agriculture to be sustainable. Automated disease detection a major issue in the current agricultural industry due its cluttered background. Internet Things (IoT) has gained immense interest past decade, as it accumulates high level contextual information identify diseases. This study paper presents novel method based on Taylor-Water Wave Optimization-based Generative Adversarial Network (Taylor-WWO-based GAN) industry. In this method, IoT nodes sense plant leaves, and sensed data are transmitted Base Station (BS) using Fractional Gravitational Gray Wolf Optimization. technique selects optimal path transmission. After performing routing, recognized at BS. For detecting disease, input image acquired from routing phase then forwarded next step, that is, preprocessing, improve quality further processing. Then, Segmentation (SegNet) adapted segment images, extraction significant features performed segments. The extracted by GAN, which trained Taylor-WWO. proposed Taylor-WWO newly devised integrating Taylor series WWO algorithms. Taylor-WWO-based GAN showed improved performance with maximum accuracy 91.6%, sensitivity 89.3%, specificity 92.3% comparison existing methods.