Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM64118
Volume:
10 |
5 |
May 2026
Pages:
1-7
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Science and Engineering
KAKINADA INSTITUTE OF TECHNOLOGY AND SCIENCE
Department of Computer Science and Engineering
KAKINADA INSTITUTE OF TECHNOLOGY AND SCIENCE
Department of Computer Science and Engineering
KAKINADA INSTITUTE OF TECHNOLOGY AND SCIENCE
In recent years, edge computing has become an essential technology for real-time application development by moving processing and storage capabilities close to ending devices, thereby reducing latency, improving response time, and ensuring secure data exchange. Much research and numerous attempts have been made to apply the new IoT technology to agricultural areas. The main objective of this report is to protect the crop from animal attacks. The conventional techniques have the same kind of security applied to all the types of animals detected based on a Passive IR sensor, and only single-stage protection is applied. The images were captured and identified with the help of machine learning and deep learning techniques. The project was designed with a rectangular farm area. On each side of the entrance, the device was installed to capture the image for processing to identify the animals, based on the animal identification, different levels of security were applied, and that will produce different sounds with different Db levels and variety of dazzling light. This work provides a comprehensive description of the design, development, and assessment of an intelligent animal repelling system that allows for to detection and recognition of the animals. The enhancement is done by different levels of protection and different types of protection based on the classified animals. In initial level protection, making the noise and lightning from the opposite side send the animal out of the farm. If the animals are still on the farm, initiating the next stage that the image will send to the owner. The accuracy of all the methods discussed will be compared based on the complexity of the technique, implementation cost, reciprocating time, and accuracy of animal detection.
KEYWORDS
In this work, the test was carried out to classify the various wild animals to protect the crops, after identification repelling action needs to be initiated as part of the protection scheme. The research results using deep learning methods can save crop damage from wild animal attacks. Various methods were used to archive the crop protection, among the described methods, CNN provided the best results with the identification accuracy of 92.68% and the repelling time of less than 200ms. All the described methods were validated through the software same test system using python code and Tensor Flow. The proposed hardware setup can be developed a future work, the cost estimation and full implementation need a lot of mechanical and electrical-related work. The combined project will stand as interdisciplinary research work and novel in nature.
[1] Y. Liu, X. Ma, L. Shu, G. P. Hancke, and A. M. Abu-Mahfouz, ‘‘From industry 4.0 to agriculture 4.0: Current status, enabling technologies, and research challenges,’’ IEEE Trans. Ind. Information., vol. 17, no. 6, pp. 4322–4334, Jun. 2021. [2] M. S. Farooq, S. Riaz, A. Abid, K. Abid, and M. A. Naeem, ‘‘A survey on the role of IoT in agriculture for the implementation of smart farming,’’ IEEE Access, vol. 7, pp. 156237– 156271, 2019. [3] K. Kirkpatrick, ‘‘Technologizing agriculture,’’ Commun. ACM, vol. 62, no. 2, pp. 14–16,Jan. 2019. [4] M. O. Ojo, D. Adami, and S. Giordano, ‘‘Network performance evaluation of a LoRa- based IoT system for crop protection against ungulates,’’ in Proc. IEEE 25th Int. Workshop Comput. Aided Modeling Design Commun. Links Netw. (CAMAD), Sep. 2020, pp. 1–6. [5] A. Levisse, M. Rios, W.-A. Simon, P.-E. Gaillardon, and D. Atienza, ‘‘Functionality enhanced memories for edge-AI embedded systems,’’ in Proc. 19th Non-Volatile Memory Technol. Symp. (NVMTS), Oct. 2019, pp. 1–4. [6] J. Shuja, K. Bilal, W. Alasmary, H. Sinky, and E. Alanazi, ‘‘Applying machine learning techniques for caching in next-generation edge networks: A comprehensive survey,’’ J. Netw. Comput. Appl., vol. 181, no. 1, 2021, Art. no. 103005. [7] W. Dai, H. Nishi, V. Vyatkin, V. Huang, Y. Shi, and X. Guan, ‘‘Industrial edge computing: Enabling embedded intelligence,’’ IEEE Ind. Electron. Mag., vol. 13, no. 4, pp. 48–56, Dec. 2019. [8] E. Li, L. Zeng, Z. Zhou, and X. Chen, ‘‘Edge AI: On-demand accelerating deep neural network inference via edge computing,’’ IEEE Trans. Wireless Commun., vol. 19, no. 1, pp. 447–457, Jan. 2020. [9] Z. Zhou, X. Chen, E. Li, L. Zeng, K. Luo, and J. Zhang, ‘‘Edge intelligence: Paving the last mile of artificial intelligence with edge computing,’’ IEEE Proc., vol. 107, no. 8, pp. 1738– 1762, Aug. 2019. 10 G. Codeluppi, A. Cilfone, L. Davoli, and G. Ferrari, ‘‘LoRaFarM: A LoRaWAN-based smart farming modular IoT architecture,’’ Sensors, vol. 20, no. 7, p. 2028, Apr. 2020.
Publication Date
5/27/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...