• Nikita likhar
• Dr. Navdeep Kaur Saluja,
• Dr. Vishal Singh Chouhan,

Plant diseases pose a significant threat to global food security, causing substantial crop losses and economic hardship for farmers. This thesis presents an automated system for plant disease classification using the AlexNet Convolutional Neural Network (CNN) architecture, implemented in MATLAB. The proposed system demonstrates exceptional performance, achieving 99.61% accuracy on a comprehensive dataset of ten distinct plant disease classes. The methodology encompasses several critical stages: image acquisition, preprocessing through contrast enhancement and resizing, feature extraction using AlexNet's hierarchical architecture, and supervised classification. Hyperparameters including learning rate, epochs, batch size, and optimizer selection were systematically fine-tuned to maximize performance. Model evaluation employed standard metrics including accuracy, precision, recall, F1-score, specificity, and Matthews Correlation Coefficient (MCC). Comparative analysis reveals that the proposed AlexNet-based approach outperforms contemporary architectures such as Inception-V3, ResNet-50, VGG-16, and LeNet, delivering superior accuracy while maintaining computational efficiency. This research demonstrates the transformative potential of deep learning in precision agriculture, providing a scalable, efficient, and cost-effective tool for early disease detection. The system enables timely intervention strategies that reduce pesticide usage, minimize crop losses, and contribute to sustainable agricultural practices and global food security.

Transfer Learning Plant disease detection, deep learning, AlexNet CNN, convolutional neural networks, image classification, Crop Loss Reduction, precision agriculture, Model Comparison.

"Deep Convolutional Neural Network Approach for Automated Plant Disease Detection Using AlexNet", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 1, page no.c540-c548, January-2026, Available :http://www.jetir.org/papers/JETIR2601265.pdf

"Deep Convolutional Neural Network Approach for Automated Plant Disease Detection Using AlexNet", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 1, page no. ppc540-c548, January-2026, Available at : http://www.jetir.org/papers/JETIR2601265.pdf