Cognitive Attribute Selection and Laurent Series with Intelligent Multidimensional Object Optimization for Paddy Disease Detection

Sustainable agriculture depends on detecting diseases in rice crops and its diagnostic methods. Rice plant diseases must be minimized or avoided to achieve the best yield for farmers. Therefore, many researchers have been working to find the best solution. Disease has led to a more than 38% yearly drop in paddy production. Various crop disease detection methods require high accuracy and dimensionality corrections. Disease detection is indispensable for maintaining agriculture. In the meantime, automated rice plant disease detection systems also face various problems in detecting diseases in the current situation. The proposed research work provides solutions for the above-mentioned problems and requirements with a novel approach, which is the combination of the Laurent series with Intelligent Multidimensional object Optimization (LIMO classification framework) based on Generative Adversarial Network (GAN) and Swarm Intelligence Optimal Classification through Cognitive Attribute Selection (SIOC-CAS) to recognize various types of crop diseases in an agricultural field. A novel framework introduced to improve computational efficiency through optimized feature selection and scalable modeling, such as the SIOC+LIMO framework, a combination of SIOC and LIMO models. In the proposed approach, all preprocessing steps are controlled by the cognitive advisor, and for segmentation and better feature selection, the SIOC model is used. Also, the LIMO model is used for intelligent classification and optimal outcomes. The proposed SIOC+LIMO-based GAN network provides effective and improved performance metrics with overall precision, recall, F1 score, accuracy, sensitivity, and specificity values of 93.8%, 93.9%, 93.8%, 92.97%, 93.3%, and 92.97% respectively in evaluation with existing crop diseases detection.