Optimized Physics-Informed Neural Network Framework for Wild Animal Activity Detection and Classification with Real Time Alert Message Generation
DOI:
https://doi.org/10.63503/j.ijcma.2025.50Keywords:
Wild animal detection, activity classification, Physics-Informed Neural Networks, optimization, real-time alerts, wildlife monitoringAbstract
The growing contact between wild animals and humans has forced the creation of intelligent systems capable of monitoring, detecting, and classifying animal behaviors. This research describes a unique technique for wild animal activity detection and categorization that employs optimized Physics-Informed Neural Networks (PINNs) designed to provide real-time alarm signals. By incorporating domain-specific physical models into neural network training, the proposed method outperforms standard strategies in terms of accuracy and resilience. This article describes the model's design, optimization, and implementation, as well as its use in detecting animal activity in a variety of environments. The findings em phasize the model's ability to accurately classify and generate timely alerts, em phasizing its practical value for wildlife monitoring and protection. The findings offer a transformative perspective on deploying physics-informed deep learning for ecological applications.
References
[1]. Sakhri, A. Ahmed, M. Maimour, M. Kherbache, E. Rondeau, and N. Doghmane, “A digital twin-based energy-efficient wireless multimedia sensor network for waterbirds monitoring,” Future Generation Computer Systems, vol. 155, pp. 146–163, 2024.
[2]. P. P. Hamedany, “A Survey on Ambient Intelligence Contexts: A Context-Aware Taxonomy based on Deep Learning and Internet of Things Synergy,” unpublished.
[3]. E. O. Oluwasakin and A. Q. Khaliq, “Optimizing Physics-Informed Neural Network in Dynamic System Simulation and Learning of Parameters,” Algorithms, vol. 16, no. 12, p. 547, 2023.
[4]. H. Alsharif, “Physics-informed Neural Networks for Encoding Dynamics in Real Physical Systems,” arXiv preprint, arXiv:2401.03534, 2024.
[5]. M. E. C. Bento, “Physics-Informed Neural Network for Load Margin Assessment of Power Systems with Optimal Phasor Measurement Unit Placement,” Electricity, vol. 5, no. 4, pp. 785–803, 2024.
[6]. S. D. Prajapati, Physics-Informed Motion Planning Using RGB-Based Spectral Analysis, Master’s thesis, Northeastern University, 2024.
[7]. M. Chu, L. Liu, Q. Zheng, E. Franz, H. P. Seidel, C. Theobalt, and R. Zayer, “Physics-informed neural fields for smoke reconstruction with sparse data,” ACM Transactions on Graphics (ToG), vol. 41, no. 4, pp. 1–14, 2022.
[8]. G. Nentidis, “Evaluation of Physics Informed Neural Networks in engineering simple structural analysis problems,” unpublished.
[9]. P. Ray, R. Rawal, and A. Z. Rizvi, “Application of Random Forest and Decision Tree Classifier Approach for The Survival of Heart Patients using Characteristic Extraction,” International Journal on Engineering Artificial Intelligence Management,
Decision Support, and Policies, vol. 1, no. 1, pp. 1–11, 2024.
[10]. 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.
[11]. V. K. Vatsavayi and N. Andavarapu, “Identification and classification of wild animals from video sequences using hybrid deep residual convolutional neural network,” Multimedia Tools and Applications, vol. 81, no. 23, pp. 33335–33360,
2022.
[12]. J. P. Dominguez-Morales, A. Rios-Navarro, M. Dominguez-Morales, R. Tapiador Morales, D. Gutierrez-Galan, D. Cascado-Caballero, and A. Linares-Barranco, “Wireless sensor network for wildlife tracking and behavior classification of animals in Doñana,” IEEE Communications Letters, vol. 20, no. 12, pp. 2534–2537, 2016.
[13]. F. Schindler and V. Steinhage, “Identification of animals and recognition of their actions in wildlife videos using deep learning techniques,” Ecological Informatics, vol. 61, p. 101215, 2021.
[14]. S. Vaddi and J. Saripella, “Create Alert Based on Wild Animal Activity Detection Using Hybrid Deep Neural Networks,” International Journal of HRM and Organizational Behavior, vol. 12, no. 2, pp. 186–196, 2024.
[15]. G. K. Verma and P. Gupta, “Wild animal detection using deep convolutional neural network,” in Proceedings of 2nd International Conference on Computer Vision & Image Processing: CVIP 2017, vol. 2, Springer Singapore, pp. 327–338, 2018.
[16]. J. P. Dominguez-Morales, L. Duran-Lopez, D. Gutierrez-Galan, A. Rios-Navarro, A. Linares-Barranco, and A. Jimenez-Fernandez, “Wildlife monitoring on the edge: A performance evaluation of embedded neural networks on microcontrollers for animal behavior classification,” Sensors, vol. 21, no. 9, p. 2975, 2021.
[17]. Mohanty, A. G. Mohapatra, P. K. Tripathy, P. K. Bal, A. K. Tripathy, S. Nayak, and B. Jena, “Smart hospitality using IoT enabled integrated face recognition, machine learning, and fuzzy AHP for analyzing customer satisfaction measurements,” International Journal of Information Technology, pp. 1–9, 2024.
[18]. M. Tabassum, “Precision Irrigation Scheduling using Real-Time Environmental Data,” International Journal on Computational Modelling Applications, vol. 1, no. 2, pp. 20–34, 2024.
[19]. F. Weninger and B. Schuller, “Audio recognition in the wild: Static and dynamic classification on a real-world database of animal vocalizations,” in 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Pra
gue, Czech Republic, pp. 337–340, 2011.
[20]. L. Benoit, N. C. Bonnot, L. Debeffe, D. Grémillet, A. M. Hewison, P. Marchand, and N. Morellet, “Using accelerometers to infer behaviour of cryptic species in the wild,” bioRxiv, no. 2023-03, 2023.
