EFFICIENT PEST DETECTION USING ENHANCED DEEP CONVOLUTIONAL NEURAL NETWORK

In agricultural and environmental management, pest identification is a crucial duty for minimizing pesticide usage and preventing crop losses. Efficient pest detection plays a crucial role in agricultural management and crop protection. In this research, we provide a method for detecting pests that uses many modules to efficiently and accurately identify pests. This study proposes an innovative approach utilizing an Enhanced Deep Convolutional Neural Network (EDCNN) for accurate and rapid pest detection. The training phase involves leveraging EDCNN in conjunction with the lightweight Mobilenet architecture, ensuring computational efficiency without compromising performance. Subsequently, segmentation techniques are applied using the EDCNN with 36 layers, enabling precise localization of pest- infested areas within agricultural images. The final stage involves classification utilizing the trained EDCNN model, which effectively distinguishes between healthy crops and pest-affected regions. This comprehensive framework not only streamlines the detection process but also enhances the overall accuracy and reliability of pest identification. Experimental results demonstrate the efficacy of the proposed methodology, showcasing significant improvements in detection speed and accuracy compared to traditional methods. This study contributes to advancing pest management strategies by harnessing the power of deep learning and image analysis techniques,