Design and Development of an Apple Fruit Disease Identification Methodology Based on Enhanced Deep Learning Strategy

Apple Fruit Disease Identification plays a pivotal role in ensuring optimal crop health and yield in agricultural settings. In this study, we propose a novel approach leveraging Enhanced Deep Learning Strategy (EDLS) with Cascaded ShuffleNet architecture for accurate and efficient detection of apple fruit diseases. The proposed methodology integrates state-of-the-art deep learning techniques with a lightweight and efficient architecture to achieve high accuracy in disease identification. Through extensive experimentation and validation on a diverse dataset of apple fruit images, our approach demonstrates exceptional performance, with an accuracy of 97%. The utilization of Cascaded ShuffleNet enables effective feature extraction while minimizing computational resources, making it suitable for deployment in resource-constrained environments. Our findings underscore the efficacy of the proposed methodology in addressing the challenges of apple fruit disease identification, thereby contributing to enhanced crop management practices and sustainable agriculture.