Automated Bird Deterrent System: A Review

Muhammad Fauzan Hernadi (Mechatronics and Artificial Intelligence Study Program Universitas Pendidikan Indonesia, Bandung)
Yusuf Haryo Timur (Mechatronics and Artificial Intelligence Study Program Universitas Pendidikan Indonesia, Bandung)
Roy Dongan Putra Manalu (Mechatronics and Artificial Intelligence Study Program Universitas Pendidikan Indonesia, Bandung)
Nabilah Khairunnisa (Mechatronics and Artificial Intelligence Study Program Universitas Pendidikan Indonesia, Bandung)
Diky Zakaria (Mechatronics and Artificial Intelligence Study Program Universitas Pendidikan Indonesia, Bandung)

Journal of Electrical, Electronic, Information, and Communication Technology (JEEICT)
Vol 7, No 1 (2025): JOURNAL OF ELECTRICAL, ELECTRONIC, INFORMATION, AND COMMUNICATION TECHNOLOGY

Bird pests pose a significant threat to agriculture, causing extensive crop damage and economic losses. Traditional bird repellent methods, such as scarecrows and loud noises, often lose their effectiveness over time as birds adapt. This paper reviews the development and effectiveness of an automated bird repellent system, integrating Internet of Things (IoT) and Artificial Intelligence (AI) technologies. The study used a systematic literature review (SLR) methodology, analyzing 20 articles published between 2015 and 2024. Key findings show that automated systems, utilizing sensors and AI algorithms such as YOLO, DenseNet, and Mask R-CNN, significantly improve bird detection and repellent accuracy. The DenseNet model, in particular, achieved a detection accuracy of 99.65%. The review highlights the need for further research to optimize sensor placement and assess the long-term impacts of this technology on bird behavior and agricultural ecosystems. This comprehensive review underscores the potential of automated bird repellent systems to improve crop protection and sustainability in agriculture.