Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{175036,
        author = {Pratik Mohod and Dr. P.D. Khandait and Khushendra Waghmare and Sejal Girhepunje},
        title = {Deep Learning-Based Approaches for Pest Detection and Classification in Agriculture},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {1447-1454},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175036},
        abstract = {Pest infestations pose a major threat to agricultural productivity, necessitating the development of intelligent and automated detection systems for timely intervention and effective pest management. This research proposes a deep learning-based approach for pest identification and classification, utilizing Convolutional Neural Networks (CNNs) along with transfer learning techniques. Pre-trained models such as InceptionV3, ResNet-50, and AlexNet are employed to enhance classification accuracy. A diverse dataset comprising pest images from open-access sources and real-world agricultural settings is used to improve model generalization.
To enhance model robustness, preprocessing techniques such as image resizing (299×299 pixels), normalization, and data augmentation—including flipping, rotation, and zooming—are applied. The models are evaluated using key performance metrics, including accuracy, precision, recall, and F1-score. Among the tested architectures, InceptionV3 achieves the highest accuracy of 98% on the test dataset, demonstrating superior feature extraction capabilities. The integration of global average pooling layers helps mitigate overfitting while preserving high classification accuracy.
The study highlights the potential of deep learning-based systems in automating pest detection, offering farmers a reliable tool for real-time pest monitoring. This scalable framework can be seamlessly integrated into precision agriculture, aiding in pest control while reducing excessive pesticide use. The implementation of such intelligent systems can contribute to improved crop health and promote sustainable agricultural practices.},
        keywords = {Deep Learning, Convolutional Neural Networks (CNNs), Pest Detection, InceptionV3,Image Processing.},
        month = {April},
        }