Optimization Accuracy of Cotton Disease Detection using Gradient Boosting Neural Network Techniques

Abstract

Cotton is an economically important crop, but its productivity is significantly affected by various leaf diseases that can reduce crop quality and yield. Early and accurate identification of cotton diseases is therefore essential for effective crop management and timely treatment. Traditional disease identification methods rely heavily on manual inspection by experts, which can be time-consuming, subjective, and difficult to apply over large agricultural fields. This study proposes an optimized deep learning-based approach for automatic cotton disease detection using Gradient Boosting Neural Network (GBNN) techniques. The proposed framework utilizes image preprocessing, feature representation, and optimized learning to distinguish between healthy cotton leaves and different disease categories. Gradient boosting is incorporated to improve classification accuracy by iteratively reducing prediction errors and strengthening the model's ability to identify complex disease patterns. The performance of the proposed approach is evaluated using standard classification measures, including accuracy, precision, recall, and F1-score. The optimization strategy aims to enhance the robustness and generalization capability of the model while reducing misclassification among visually similar disease symptoms. The proposed system can provide a reliable and automated solution for early cotton disease diagnosis, supporting farmers and agricultural experts in making timely crop-management decisions. The study demonstrates the potential of optimized Gradient Boosting Neural Network techniques for developing efficient, accurate, and scalable intelligent systems for cotton disease detection and precision agriculture.