Journal of Machine and Computing


Improving Agricultural Safety Through Deep Neural Networks for Intrusion Monitoring



Journal of Machine and Computing

Received On : 29 March 2025

Revised On : 14 May 2025

Accepted On : 14 June 2025

Published On : 05 July 2025

Volume 05, Issue 03

Pages : 1654-1672


Abstract


The intersection of agricultural activities and natural habitats presents several implications, one of the most pressing being the intrusion of various species into crop fields. To address the continued and growing challenge of discovering methods for successful mitigation and protection of crops, a new method must be introduced. Current practices, such as using pheromones and monitoring by humans, yield suboptimal results due to inefficiency, labour-intensive processes, and environmental damage. This paper proposes a novel method based on deep learning technologies, namely UNet and EfficientNet-B7 architectures, for semantic segmentation of crop-damaging species in agricultural habitats. The method provides a reliable means to detect species intrusion by integrating it into automated monitoring operations. Whether identifying the segmentation point of target species or utilizing feature-based detection with the proposed model, the application of advanced convolutional neural networks ensures the accuracy of these systems. This method demonstrates higher performance in species identification and proposes newer and ecologically friendly methods of implementing non-invasive monitoring for conservation alongside agriculture. The experimental results confirm that the proposed UNet with EfficientNet-B7 achieves a high accuracy ratio of 95.3%, an F1-score ratio of 92.4%, and an efficiency ratio of 97.6% compared to other existing models.


Keywords


Intrusion, Deep Learning, Semantic Segmentation, Convolutional Neural Networks, EfficientNet-B7, UNet.


  1. M. Negi, M. Goswami, and S. Nautiyal, “Agricultural loss due to wildlife: a case study on elephant depredation in a protected area of South India,” Journal of Social and Economic Development, vol. 25, no. 2, pp. 350–364, Dec. 2022, doi: 10.1007/s40847-022-00230-z.
  2. D. Yazezew, “Human-wildlife conflict and community perceptions towards wildlife conservation in and around Wof-Washa Natural State Forest, Ethiopia,” BMC Zoology, vol. 7, no. 1, Sep. 2022, doi: 10.1186/s40850-022-00154-5.
  3. A. J. Carpio, M. Apollonio, and P. Acevedo, “Wild ungulate overabundance in Europe: contexts, causes, monitoring and management recommendations,” Mammal Review, vol. 51, no. 1, pp. 95–108, Sep. 2020, doi: 10.1111/mam.12221.
  4. J. A. Zwerts et al., “Methods for wildlife monitoring in tropical forests: Comparing human observations, camera traps, and passive acoustic sensors,” Conservation Science and Practice, vol. 3, no. 12, Nov. 2021, doi: 10.1111/csp2.568.
  5. S. Mekonen, “Coexistence between human and wildlife: the nature, causes and mitigations of human wildlife conflict around Bale Mountains National Park, Southeast Ethiopia,” BMC Ecology, vol. 20, no. 1, Sep. 2020, doi: 10.1186/s12898-020-00319-1.
  6. T. Prasad, Pradeep. L, V. Aravind. K, Arumugam, and C. Lakshmi, “Coco-Based Crop Protection System with Integrated Buzzer,” 2023 9th International Conference on Smart Structures and Systems (ICSSS), pp. 1–8, Nov. 2023, doi: 10.1109/icsss58085.2023.10407056.
  7. A. V. Sayagavi, T. S. B. Sudarshan, and P. C. Ravoor, “Deep Learning Methods for Animal Recognition and Tracking to Detect Intrusions,” Information and Communication Technology for Intelligent Systems, pp. 617–626, Oct. 2020, doi: 10.1007/978-981-15-7062-9_62.
  8. R. S. Patel, D. D. Amin, S. Patel, M. Rahevar, C. Patel, and A. Nayak, “Smart Crop Protection Against Animal Encroachment using Deep Learning,” 2023 4th International Conference on Intelligent Engineering and Management (ICIEM), pp. 1–6, May 2023, doi: 10.1109/iciem59379.2023.10167118.
  9. B. Bhagabati, K. K. Sarma, and K. C. Bora, “An automated approach for human-animal conflict minimisation in Assam and protection of wildlife around the Kaziranga National Park using YOLO and SENet Attention Framework,” Ecological Informatics, vol. 79, p. 102398, Mar. 2024, doi: 10.1016/j.ecoinf.2023.102398.
  10. K. Rančić et al., “Animal Detection and Counting from UAV Images Using Convolutional Neural Networks,” Drones, vol. 7, no. 3, p. 179, Mar. 2023, doi: 10.3390/drones7030179.
  11. A. Mao, E. Huang, X. Wang, and K. Liu, “Deep learning-based animal activity recognition with wearable sensors: Overview, challenges, and future directions,” Computers and Electronics in Agriculture, vol. 211, p. 108043, Aug. 2023, doi: 10.1016/j.compag.2023.108043.
  12. W. P. S. Fernando, I. K. Madhubhashana, D. N. B. A. Gunasekara, Y. D. Gogerly, A. Karunasena, and R. Supunya, “Image Processing-Based Solution to Repel Crop-Damaging Wild Animals,” Intelligent Sustainable Systems, pp. 1–16, 2023, doi: 10.1007/978-981-99-1726-6_1.
  13. B. Natarajan, R. Elakkiya, R. Bhuvaneswari, K. Saleem, D. Chaudhary, and S. H. Samsudeen, “Creating Alert Messages Based on Wild Animal Activity Detection Using Hybrid Deep Neural Networks,” IEEE Access, vol. 11, pp. 67308–67321, 2023, doi: 10.1109/access.2023.3289586.
  14. S. Sajithra Varun and G. Nagarajan, “DeepAID: a design of smart animal intrusion detection and classification using deep hybrid neural networks,” Soft Computing, May 2023, doi: 10.1007/s00500-023-08270-1.
  15. A. K. Thomas, P. Poovizhi, M. Saravanan, and K. Tharageswari, “Animal Intrusion Detection using Deep Learning for Agricultural Fields,” 2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT), pp. 1021–1027, Jan. 2023, doi: 10.1109/icssit55814.2023.10060984.
  16. S. R. Bakana, Y. Zhang, and B. Twala, “WildARe-YOLO: A lightweight and efficient wild animal recognition model,” Ecological Informatics, vol. 80, p. 102541, May 2024, doi: 10.1016/j.ecoinf.2024.102541.
  17. S. Rajaretnam and V. Yesodharan, “A novel DbneAlexnet with Gazelle Hunting Optimization Algorithm enabled wild animal detection in WMSN data communication in IoT environment,” International Journal of Communication Systems, vol. 37, no. 11, Apr. 2024, doi: 10.1002/dac.5787.
  18. D. Bárbulo Barrios, J. Valente, and F. van Langevelde, “Monitoring mammalian herbivores via convolutional neural networks implemented on thermal UAV imagery,” Computers and Electronics in Agriculture, vol. 218, p. 108713, Mar. 2024, doi: 10.1016/j.compag.2024.108713.
  19. F. Chen, H. V. Nguyen, D. A. Taggart, K. Falkner, S. H. Rezatofighi, and D. C. Ranasinghe, “ConservationBots: Autonomous aerial robot for fast robust wildlife tracking in complex terrains,” Journal of Field Robotics, vol. 41, no. 2, pp. 443–469, Nov. 2023, doi: 10.1002/rob.22270.
  20. A. Mishra and K. K. Yadav, “Smart Animal Repelling Device: Utilizing IoT and AI for Effective Anti-Adaptive Harmful Animal Deterrence,” BIO Web of Conferences, vol. 82, p. 05014, 2024, doi: 10.1051/bioconf/20248205014.
  21. https://www.kaggle.com/datasets/trainingdatapro/farm-animals-pigs-detection-dataset.

CRediT Author Statement


The authors confirm contribution to the paper as follows:

Conceptualization: Thirupathi Battu and Lakshmi Sreenivasa Reddy D; Methodology: Thirupathi Battu; Software: Lakshmi Sreenivasa Reddy D; Data Curation: Thirupathi Battu; Writing- Original Draft Preparation: Thirupathi Battu and Lakshmi Sreenivasa Reddy D; Visualization: Lakshmi Sreenivasa Reddy D; Investigation: Thirupathi Battu; Supervision: Lakshmi Sreenivasa Reddy D; Validation: Thirupathi Battu; Writing- Reviewing and Editing: Thirupathi Battu and Lakshmi Sreenivasa Reddy D; All authors reviewed the results and approved the final version of the manuscript.


Acknowledgements


Author(s) thanks to Dr.Lakshmi Sreenivasa Reddy D for this research completion and support.


Funding


No funding was received to assist with the preparation of this manuscript.


Ethics declarations


Conflict of interest

The authors have no conflicts of interest to declare that are relevant to the content of this article.


Availability of data and materials


Data sharing is not applicable to this article as no new data were created or analysed in this study.


Author information


Contributions

All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.


Corresponding author


Rights and permissions


Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/


Cite this article


Thirupathi Battu and Lakshmi Sreenivasa Reddy D, “Improving Agricultural Safety Through Deep Neural Networks for Intrusion Monitoring”, Journal of Machine and Computing, vol.5, no.3, pp. 1654-1672, July 2025, doi: 10.53759/7669/jmc202505131.


Copyright


© 2025 Thirupathi Battu and Lakshmi Sreenivasa Reddy D. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.