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{204493,
        author = {Sanjaikumar V and Vijayalakshmi S and Marikkannan M},
        title = {Intelligent Grain Warehouse Monitoring, Pest Identification and Prevention System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {2021-2030},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204493},
        abstract = {post-harvest grain losses in developing nations account for 10–40% of annual production, attributed to two concurrent threats: hazardous environmental conditions (excess temperature, humidity, and CO gas buildup) and stored product insect infestations. Existing systems address these threats in isolation, leaving a critical gap in integrated risk assessment. This paper presents a dataset-driven intelligent monitoring framework that unifies environmental anomaly detection with deep learning-based insect species identification into a composite risk-scoring system. Using publicly available datasets the Smoke Detection IoT dataset and the IP102 insect pest image collection the system trains a Random Forest and a two-layer LSTM for environmental anomaly detection and a fine-tuned ResNet-50 Convolutional Neural Network for classifying five stored product insect species. A novel data fusion engine combines both model outputs using a weighted formula to generate a composite risk score mapped to three actionable alert levels: Stable, Moderate Risk, and High Risk. A tiered SMS notification system dispatches contextual alerts upon risk-level transitions, achieving alert precision of and recall. This work constitutes the first dataset-driven integration of environmental IoT monitoring and insect pest identification into a unified grain storage risk assessment platform.},
        keywords = {Anomaly detection, Deep learning, Food security, Grain storage, Insect classification, LSTM, Post-harvest loss, Smart agriculture.},
        month = {June},
        }