Hybrid CNN - LSTM Model for Visual and Behavioral Rabies Detection
DOI:
https://doi.org/10.15662/IJEETR.2026.0802054Keywords:
Rabies Diagnoses, CNNs, ResNet50, LSTMs, Transfer Learning, Zoonotic Diseases, Deep Learning, Multimodal Classification Systems, Veterinarian AI Applications, Public Health ScreeningAbstract
Rabies is one of the most serious zoonotic viral diseases and is one of several viral zoonotic diseases that can be transmitted from animals to humans. Approximately 59,000 people die from rabies each year. Almost all rabies cases in people are caused by transmission of rabies virus (RabV) from rabid domestic dogs (99% of rabies cases in people worldwide), the primary rabies virus reservoir. Rabies can be diagnosed using a recognized "gold standard" method of diagnosis, the Fluorescent Antibody Test (FAT), which is based on the post-mortem examination of brain tissue of the infected animal. However, because FAT diagnosis requires the collection of animal post-mortem brain tissue for laboratory analysis, rabies cannot be diagnosed in an animal until after death. This paper describes a dual modal artificial intelligence (AI) based screening system that uses complementary image classification (deep learning) and text classification (deep learning) to simultaneously identify rabies in dogs based on classical ('textbook') clinical signs. The dual modal AI based screening system consists of: (1) a fine-tuned Convolutional Neural Network (CNN) based on the ResNet50 architecture is used to classify visual signs associated with furious rabies such as: excessive salivation, abnormal behaviour and frothy saliva, and (2) a Long Short Term Memory (LSTM) Recurrent Neural Network (RNN) is used to semantically classify written signs describing clinical manifestations of dumb (paralytic) rabies. In addition, because of the variance of the symptoms chosen for training the models, each of these models ultimately achieved a final predicted accuracy of 100% during the validation iterations; Both of these CNN models share their outputs in a single Streamlit application that calculates an overall risk score for the use of rabies vaccines and provides recommendations on the use of rabies vaccines to prevent further rabies infections. This study is an important advancement toward allowing for a quick and easy method for non-expert healthcare providers to diagnose rabies in developing countries worldwide.
References
1. K. Balakrishna and V. Dhanushree, “A review on animal detection and classification using computer vision techniques: scope for future enhancement to application,” Proc. 2023 Int. Conf. Recent Trends in Electronics and Communication (ICRTEC), pp. 1–6, 2023.
2. M. A. Candia-Puma et al., “Evaluating Rabies Test Accuracy: A Systematic Review and Meta-Analysis of Human and Canine Diagnostic Methods,” Diagnostics, vol. 15, no. 4, p. 412, 2025.
3. C. Demetria et al., “Evaluation of a real-time mobile PCR device (PCR 1100) for the detection of the rabies gene in field samples,” Tropical Medicine and Health, vol. 51, no. 1, p. 17, 2023.
4. D. M. A. Dissanayaka et al., “Skin disease detection of pet dogs and identifying home remedies using machine learning (SVM, NLP) and AI,” Proc. 2022 3rd Int. Informatics and Software Engineering Conf. (IISEC), pp. 1–6, 2022.
5. A. Bhosale et al., “Stray dog detection system using YOLOv5,” Procedia Computer Science, vol. 252, pp. 806–813, 2025.
6. B. Valarmathi, N. Srinivasa Gupta, G. Prakash, R. Hemadri Reddy, S. Saravanan, and P. Shanmugasundaram, “Hybrid deep learning algorithms for dog breed identification—A comparative analysis,” IEEE Access, vol. 11, pp. 77228–77239, 2023.
7. S. D. Meena and L. Agilandeeswari, “An efficient framework for animal breeds classification using semi-supervised learning and multi-part convolutional neural network (MP-CNN),” IEEE Access, vol. 7, pp. 151783–151802, 2019.
8. S. Islam, M. T. Aziz, H. R. Nabil, J. R. Jim, M. F. Mridha, M. Mohsin Kabir, N. Asai, and J. Shin, “Generative adversarial networks (GANs) in medical imaging: Advancements, applications, and challenges,” IEEE Access, vol. 12, pp. 35728–35752, 2024.
9. G. Liang, H. Hong, W. Xie, and L. Zheng, “Combining a convolutional neural network with recursive neural network for blood cell image classification,” IEEE Access, vol. 6, pp. 36188–36197, 2018.
10. R. Keshavamurthy, C. Boutelle, Y. Nakazawa, H. Joseph, D. W. Joseph, P. Dilius, A. D. Gibson, and R. M. Wallace, “Machine learning to improve the understanding of rabies epidemiology in low surveillance settings,” Scientific Reports, vol. 14, p. 25851, 2024.
11. A. Bhosale et al., “Stray dog detection system using YOLOv5,” Procedia Computer Science, vol. 252, pp. 806–813, 2025
12. J. Hampson et al., “Estimating the global burden of endemic canine rabies,” PLoS Neglected Tropical Diseases, vol. 9, no. 4, p. e0003709, 2015.
13. WHO Expert Consultation on Rabies, “WHO expert consultation on rabies: Third report,” World Health Organization, Tech. Rep., 2018.
14. J. Cleaveland et al., “Rabies control and elimination: A test case for One Health,” The Veterinary Record, vol. 175, no. 8, pp. 188–193, 2014.
15. S. Taylor et al., “Advances in rabies diagnosis using molecular and immunological techniques,” Journal of Virological Methods, vol. 262, pp. 1–10, 2018.
16. P. Banyard et al., “Rabies pathogenesis and epidemiology,” Nature Reviews Microbiology, vol. 11, pp. 568–580, 2013.
17. A. Nel et al., “Rabies virus: Molecular biology, diagnosis and control,” The Lancet Infectious Diseases, vol. 10, pp. 1–12, 2010.
18. M. Scott et al., “Modeling rabies transmission and control strategies,” Epidemiology and Infection, vol. 145, no. 2, pp. 1–12, 2017.
19. T. Lembo et al., “Feasibility of canine rabies elimination in Africa,” PLoS Neglected Tropical Diseases, vol. 4, no. 3, p. e626, 2010.
20. L. Fitzpatrick et al., “Machine learning approaches for infectious disease prediction,” IEEE Reviews in Biomedical Engineering, vol. 13, pp. 1–15, 2020.
21. N. Hegde et al., “Deep learning for medical image analysis: A review,” IEEE Reviews in Biomedical Engineering, vol. 12, pp. 1–20, 2019.
22. H. S. N. Rajapaksha, R. S. Vidanapathirana, and K. Premaratne, “Deep learning-based animal disease detection using image classification,” IEEE Access, vol. 10, pp. 112345–112356, 2022.
23. C.Nagarajan and M.Madheswaran - ‘Stability Analysis of Series Parallel Resonant Converter with Fuzzy Logic Controller Using State Space Techniques’- Taylor &Francis, Electric Power Components and Systems, Vol.39 (8), pp.780-793, May 2011. DOI: 10.1080/15325008.2010.541746
24. C.Nagarajan and M.Madheswaran - ‘Experimental verification and stability state space analysis of CLL-T Series Parallel Resonant Converter’ - Journal of Electrical Engineering, Vol.63 (6), pp.365-372, Dec.2012. DOI: 10.2478/v10187-012-0054-2
25. C.Nagarajan and M.Madheswaran - ‘Performance Analysis of LCL-T Resonant Converter with Fuzzy/PID Using State Space Analysis’- Springer, Electrical Engineering, Vol.93 (3), pp.167-178, September 2011. DOI 10.1007/s00202-011-0203-9
26. S.Tamilselvi, R.Prakash, C.Nagarajan,“Solar System Integrated Smart Grid Utilizing Hybrid Coot-Genetic Algorithm Optimized ANN Controller” Iranian Journal Of Science And Technology-Transactions Of Electrical Engineering, DOI10.1007/s40998-025-00917-z,2025
27. S.Tamilselvi, R.Prakash, C.Nagarajan,“ Adaptive sliding mode control of multilevel grid-connected inverters using reinforcement learning for enhanced LVRT performance” Electric Power Systems Research 253 (2026) 112428, doi.org/10.1016/j.epsr.2025.112428
28. S.Thirunavukkarasu, C. Nagarajan, 2024, “Performance Investigation on OCF and SCF study in BLDC machine using FTANN Controller," Journal of Electrical Engineering And Technology, Volume 20, pages 2675–2688, (2025), doi.org/10.1007/s42835-024-02126-w
29. C. Nagarajan, M.Madheswaran and D.Ramasubramanian- ‘Development of DSP based Robust Control Method for General Resonant Converter Topologies using Transfer Function Model’- Acta Electrotechnica et Informatica Journal , Vol.13 (2), pp.18-31,April-June.2013, DOI: 10.2478/aeei-2013-0025.
30. C.Nagarajan and M.Madheswaran - ‘DSP Based Fuzzy Controller for Series Parallel Resonant converter’- Springer, Frontiers of Electrical and Electronic Engineering, Vol. 7(4), pp. 438-446, Dec.12. DOI 10.1007/s11460-012-0212-0.
31. C.Nagarajan and M.Madheswaran - ‘Experimental Study and steady state stability analysis of CLL-T Series Parallel Resonant Converter with Fuzzy controller using State Space Analysis’- Iranian Journal of Electrical & Electronic Engineering, Vol.8 (3), pp.259-267, September 2012.
32. C.Nagarajan and M.Madheswaran, “Analysis and Simulation of LCL Series Resonant Full Bridge Converter Using PWM Technique with Load Independent Operation” has been presented in ICTES’08, a IEEE / IET International Conference organized by M.G.R.University, Chennai.Vol.no.1, pp.190-195, Dec.2007
33. Suganthi Mullainathan, Ramesh Natarajan, “An SPSS and CNN modelling based quality assessment using ceramic materials and membrane filtration techniques”, Revista Materia (Rio J.) Vol. 30, 2025, DOI: https://doi.org/10.1590/1517-7076-RMAT-2024-0721
34. M Suganthi, N Ramesh, “Treatment of water using natural zeolite as membrane filter”, Journal of Environmental Protection and Ecology, Volume 23, Issue 2, pp: 520-530,2022
35. M. A. Khan, S. Kadry, and Y. Nam, “AI-driven infectious disease prediction using machine learning models,” IEEE Access, vol. 9, pp. 150345–150358, 2021.
36. [24] A. Esteva, B. Kuprel, R. A. Novoa, et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, pp. 115–118, 2017.
37. S. Litjens et al., “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, 2017.
