International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI based Wildlife Intrusion Detection & Prevention System |
|---|---|
| ABSTRACT | An AI-based Wildlife Intrusion Detection and Prevention System (WIDPS) represents a sophisticated fusion of computer vision, edge computing, and non-lethal deterrent technology designed to mitigate human-wildlife conflict. At its core, the system utilizes high-resolution thermal or RGB cameras coupled with Passive Infrared (PIR) sensors to monitor boundary zones in real-time. When motion is detected, the raw data is instantly processed by an on-site "Edge AI" unit—such as a Jetson Nano or Raspberry Pi—running deep learning architectures like YOLOv8 or SSD (Single Shot Detector). This localized processing is critical; it allows the system to distinguish between a "false positive" like a domestic dog or swaying branches and a "target threat" like an elephant or a leopard without relying on an unstable cloud connection. Once a specific species is classified, the system executes a tiered response: it simultaneously transmits a low-latency alert via LoRaWAN or GSM to forest rangers and triggers a species-specific deterrent. These deterrents are carefully calibrated to be effective yet harmless, utilizing ultrasonic frequency arrays, high-intensity LED strobes, or acoustic mimicry (such as the sound of bees to deter elephants) to steer the animal back into the forest. By logging every encounter, the system creates a granular heat map of animal movement patterns, allowing for data-driven conservation strategies and ensuring that the prevention methods remain dynamic and effective over time. |
| AUTHOR | DR. P. JAMUNA RANI, ABISHEK V, BHARANEDHARAN R, DEEPAK R, GOWTHAM S Associate Professor, Department of Chemistry, Mahendra Institute of Technology, Mallasamudram, Namakkal, Tamil Nadu, India UG Student, Department of Computer Science and Engineering, Mahendra Institute of Technology, Mallasamudram, Namakkal, Tamil Nadu, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405014 |
| pdf/14_AI based Wildlife Intrusion Detection & Prevention System.pdf | |
| KEYWORDS | |
| References | 1. Abed, N., et al., "IoT and AI-driven solutions for human-wildlife conflict: Advancing sustainable agriculture and biodiversity conservation," Smart Agricultural Technology, vol. 11, p. 100829, 2025. 2. Chinapureddy, L. R., et al., "Real Time AI-Based Wildlife Detection and Deterrent System for Farmland Protection," ResearchGate, 2024. [Focuses on YOLOv8 and species-specific deterrents]. 3. Ronoh, E. K., et al., "Early warning system for human-wildlife conflict using deep learning, IoT and SMS," NM-AIST Repository, 2023. [Details Raspberry Pi and YOLO implementation]. 4. Patil, M., et al., "Harmful Animal Identification and Detection in Forests Using AI & ML," Zenodo, 2025. [Covers CNN-based classification for threat detection]. 5. König, H. J., et al., "Human–wildlife coexistence in a changing world," Conservation Biology, vol. 34, no. 4, pp. 786–794, 2020. 6. Sree, S., et al., "Beast Sentinel: Smart IoT-Based Wildlife Tracking and Intrusion System," International Journal for Research in Applied Science and Engineering Technology (IJRASET), 2025. 7. Kumar, M. S., et al., "IoT Based Warning System from the Threat of Wild Animals," 6th International Conference on Communication and Electronics Systems (ICCES), pp. 550–553, 2021. 8. Sharma, P., et al., "AI-Based Animal Detection and Classification in Forest Areas," International Journal of Computer Vision and Image Processing, vol. 10, no. 2, 2020. [Focuses on thermal imaging]. 9. Nuchhi, S., et al., "Raspberry Pi-based animal detection system using YOLO-based deep learning algorithms," Journal of Embedded Systems, 2020. 10. Abed, N., et al., "Artificial intelligence-driven solutions for mitigating human–wildlife conflict in biodiversity hotspots," PMC (PubMed Central), vol. 12, 2025. |
