This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
L Irfana,
Abilash R S,
Jagan S S,
Sanio Solomon,
- Assistant Professor, Department of Electrical and Electronics Engineering, College of Engineering Muttathara, Kerala, India
- Assistant Professor, Department of Electrical and Electronics Engineering, College of Engineering Muttathara, Kerala, India
- Student, Department of Electrical and Electronics Engineering, College of Engineering Muttathara, Kerala, India
- Student, Department of Electrical and Electronics Engineering, College of Engineering Muttathara, Kerala, India
Abstract
Intrusion of humans and wild animals into protected areas such as forest boundaries and agricultural lands poses significant challenges in terms of safety and resource management. Conventional electric fencing systems operate continuously without distinguishing the type of intrusion, leading to inefficient energy usage and potential harm to wildlife. The design and partial implementation of an intrusion detection system for smart electric fence based on deep learning are presented in this study. The system utilizes a YOLOv11 object detection model to classify intrusions as human or animal in real time. A dataset composed of images from publicly available sources was used for training, along with preprocessing techniques such as resizing and normalization. Based on the classification output, the system triggers selective response mechanisms. In the case of animal detection, an ultrasonic deterrent is activated along with fence activation, while for human detection, both the electric fence and alarm are activated as preventive measures. A basic RFID-based system is proposed to provide secure access for authorized personnel. The implementation focuses on validating the detection accuracy and response behavior under controlled conditions. The results indicate that the system can perform reliable classification and appropriate response with minimal delay. The proposed approach demonstrates the feasibility of integrating deep learning with fencing systems to improve efficiency, safety, and operational control.
Keywords: Deep Learning, YOLOv11, Intrusion Detection, Selective Response, Ultrasonic Deterrent, RFID System
References
- Syahrani FP, Saputra HK, Anori S, Agustiarmi W, Ayasrah FT, Thanh PV. IoT- enabled smart fence: remote security and monitoring using NodeMCU ESP32 and Blynk. J Hypermedia Technol Enhanc Learn. 2025;3(1):1-15. doi:10.58536/j- hytel.158.
- Garcia-Cardarelli P, Sokoudjou JF, Aramberri Araiz P, Diaz JD, Ochoa I, Valderas D, et al. A compact and low-cost hybrid reader for chipless RFID systems. IEEE Trans Instrum Meas. 2025;74:1-13. doi:10.1109/TIM.2025.3602584.
- Chodon P, Adhikari DM, Nepal GC, Biswa R, Gyeltshen S. Passive Infrared (PIR) Sensor Based Security System. International Journal of Electrical, Electronics & Computer Systems. 2013 Jun 1;14(2):1
- Shali SS, Annrose J. YOLO Based Animal Repellent Device Using Raspberry Pi. In2025 International Conference on Innovative Trends in Information Technology (ICITIIT) 2025 Feb 21 (pp. 1-7). IEEE.
- Awajan A. A novel deep learning-based intrusion detection system for IOT networks. Computers. 2023 Feb 5;12(2):34.
- Qiang T. Engineering design of electronic fence system based on intelligent monitoring and wireless local area network. Alexandria Engineering Journal. 2022 Apr 1;61(4):2959-69.
- Wen Y, Zhi Q, Zhang K, Li Y, Cui Y, Du H. Construction of Intelligent Electronic Fence System Based on Computer Vision Algorithm. Procedia Computer Science. 2025 Jan 1;261:504-11.
- Liu B, Yan H, Meng F, Liu Z. Intrusion detection algorithm for electronic fence in substation area based on YOLOv4. International Journal of Powertrains. 2026;15(2):138-55.
- Shanmugavadivel G, Kirubasakthi A, Madhumitha K, Malini M, Manisha S. AI- Enabled Real-Time Electric Fence Safety System for Wild Animal Intrusion Detection in Agriculture. In2026 6th International Conference on Expert Clouds and Applications (ICOECA) 2026 Mar 9 (pp. 94-99). IEEE.
- Ambikha C, Alekhya B, Srichandana K, KF MM, Kalyani G, Kamalika M. AI assisted IOT framework for real-time detection and selective tripping to prevent unauthorized electric fence tapping. In2026 International Conference on Computing, Communication, Control and Cyber-Physical Systems (I5CPS) 2026 Feb 26 (pp. 1-6). IEEE.
Journal of Control & Instrumentation
| Volume | 17 | |
| 03 | ||
| Received | 15/05/2026 | |
| Accepted | 10/10/2026 | |
| Published | 26/10/2026 | |
| Publication Time | 164 Days |