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{202761,
        author = {Prof. Kokare S. A. and Vikas Rajkumar Mandlik and Rushikesh Gaikwad and Swapnali Lambhate and Dr. Shah Saloni Niranjan},
        title = {Creating Alert Messages Based on Wild Animal Activity Detection Using Hybrid Deep Neural Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {9132-9140},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202761},
        abstract = {Wild animal movement near human settlements, agricultural fields, forest boundaries, highways, and railway areas has become a serious concern due to increasing human-wildlife conflict. In many rural and forest-border regions, sudden entry of wild animals such as tigers, elephants, leopards, bears, lions, and other species can cause crop damage, property loss, livestock attacks, road accidents, and life-threatening situations for humans. Traditional monitoring methods such as manual patrolling, camera traps, watch towers, and delayed reporting systems are not always reliable because they require continuous human observation and often fail to provide real-time warnings. This paper presents an intelligent system for creating alert messages based on wild animal activity detection using Hybrid Deep Neural Networks. The proposed system uses deep learning-based object detection to identify wild animals from live camera input or video streams. A YOLOv8-based detection model is used for fast and accurate animal detection, while OpenCV is used for real-time video frame processing. After detecting wild animal activity, the system generates alert messages, activates an alarm, updates the monitoring status, and stores alert history for future analysis. The system is implemented using a Flask-based web dashboard that displays live video streaming, detection status, detected ani-mal name, alert count, alarm indication, and previous detection records. The proposed system reduces manual monitoring effort and provides quick warnings to farmers, forest officers, wildlife departments, security teams, and local authorities. This system can be used in forest-border villages, agricultural fields, wildlife-sensitive roads, railway zones, and protected areas to improve safety and reduce human-wildlife conflict.},
        keywords = {Wild Animal Detection, Deep Learning, YOLOv8, Hybrid Deep Neural Networks, Computer Vision, OpenCV, Flask, Alert Message Generation, Real-Time Monitoring, Human-Wildlife Conflict.},
        month = {May},
        }