Copyright © 2026 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{201966,
        author = {Soundararajan K and Jayapriya R and Lavanya D and Sivasundhari M and Tamilmani K},
        title = {A Deep Learning-Based Web Framework for Automated Pest Detection and Intelligent Treatment Recommendation Using Transfer Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {5779-5785},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201966},
        abstract = {Pest detection and treatment recommendation systems are computational agricultural frameworks that automatically identify pest species and generate context-aware control strategies to mitigate crop damage. An Artificial Intelligence (AI)-based pest detection and treatment recommendation system advances this paradigm by leveraging deep convolutional learning for high-dimensional visual feature extraction and automated decision support. Nevertheless, existing AI-driven approaches exhibit limitations such as domain shift sensitivity, overfitting due to limited annotated datasets, and significant computational overhead during training and inference. To overcome these challenges, this study introduces a novel three-stage architecture integrating Adaptive Agro-Image Normalization and Augmentation Algorithm (AAINAA), which performs spatial standardization, distribution normalization, and stochastic perturbation to enhance data invariance; Transfer Learning-based Residual Feature Optimization Algorithm (TL-RFOA), which exploits Residual Neural Network (ResNet50) with fine-tuned deep layers for hierarchical feature abstraction and gradient stabilization; and Probabilistic Pest Classification and Intelligent Recommendation Algorithm (PPCIRA), which employs Softmax-based posterior estimation optimized via Adaptive Moment Estimation (Adam) with Categorical Cross-Entropy (CCE) for multi-class inference and knowledge-driven treatment mapping. Furthermore, Automatic Mixed Precision (AMP) is incorporated to accelerate computation and reduce memory footprint. The proposed framework delivers a scalable, robust, and real-time intelligent pest management solution.},
        keywords = {pest, agriculture, AI, AAINAA, TL-RFOA, PPCIRA, treatment recommendation.},
        month = {May},
        }