Aranya AI

Abstract

Limited access to veterinary services in rural areas often delays livestock disease detection and results in economic losses for farmers. To address this issue, this paper presents Aranya-AI, an artificial intelligence-based livestock health monitoring and management system designed for early disease detection and improved animal welfare. The system utilizes a Convolutional Neural Network (CNN) for image-based disease identification and an LSTM Autoencoder for anomaly detection in physiological time-series data. These models are integrated through a conversational chatbot interface that provides automated health insights and preventive recommendations in an accessible manner. Additionally, the cloud-based architecture ensures secure and scalable data handling. Experimental evaluation demonstrates improved diagnostic accuracy and system responsiveness, supporting timely decision-making in rural farming environments. The proposed system contributes toward sustainable and technology-enabled livestock management.

Introduction

The text discusses the challenges in livestock farming, particularly the lack of timely veterinary support, limited monitoring tools in rural areas, and dependence on manual observation, which often leads to delayed disease detection and higher mortality rates. Farmers also face difficulties in accessing accurate diagnosis and maintaining secure, long-term livestock data.

To address these issues, the paper introduces Aranya-AI, an intelligent livestock health monitoring system that combines multiple AI technologies. It integrates CNN-based image classification for disease detection, LSTM-based anomaly detection for analyzing time-series health data, and a chatbot interface to provide advisory support. The system is deployed in a secure cloud environment to improve accessibility and data protection.

The literature review highlights that existing livestock monitoring systems use IoT sensors, mobile apps, and cloud platforms, but they are often expensive, incomplete, or not suitable for small-scale farmers. Many systems either focus on sensor data or image analysis alone, lacking a unified approach. Additionally, weak data security measures remain a concern in agricultural digital platforms.

A comparison of existing systems shows that most provide only partial AI support and limited security, whereas Aranya-AI offers full AI integration along with stronger protection (e.g., encryption and role-based access control) and better accessibility for rural users.

The proposed system architecture consists of three layers: a presentation layer (user interface and chatbot), an application layer (AI models like CNN and LSTM Autoencoder), and a data layer (secure cloud database).

Conclusion

This research presented Aranya-AI, an intelligent livestock health monitoring system designed to support farmers through early disease detection, secure data management, and accessible AI-driven insights. The system integrates CNN-based image disease classification, LSTM Autoencoder-based anomaly detection, and a chatbot interface to provide proactive livestock healthcare support. Experimental evaluation demonstrated that Aranya-AI can effectively identify visible livestock diseases and detect abnormal health patterns from physiological data, enabling timely intervention in rural and resource-limited environments. The secure architecture, supported by encryption and role-based access control, ensures data privacy while maintaining system reliability and scalability. The proposed system highlights the potential of combining artificial intelligence and digital agriculture to improve animal welfare, reduce economic losses, and enhance farm sustainability. By offering a farmer-centric and modular design, Aranya-AI provides a strong foundation for future smart livestock management solutions. Future work will focus on integrating IoT-based real-time sensing, expanding multilingual chatbot support, and validating system performance through large-scale field deployment to further enhance practical applicability.

References

[1] K. Darvesh, N. Khande, S. Avhad, and M. Khemchandani, “IoT and AI based smart cattle health monitoring,” J. Livestock Sci., vol. 14, pp. 211-218, Jul. 2023, doi: 10.33259/JLivestSci.2023.211-218. [2] Walid Abdullah; Sudeep Tanwar; Mohamed Abouhawwash. “Deep Learning-Based Detection of Lumpy Skin Disease in Livestock using CNNs.” Sustainable Machine Intelligence Journal, vol. 11, no. 1, Article 6, 2025. [3] “A deep contrastive learning-based image retrieval system for automatic detection of infectious cattle diseases.” Journal of Big Data, vol. 12, Article number 2, 2025. [4] Design of a Cattle-Health-Monitoring System Using Microservices and IoT Devices.” Computers, vol. 11, no. 5, 2022, Article 79 [5] Shinde, V.; Jha, S.; Taral, A.; Salgaonkar, K.; Salgaonkar, S. “IoT Based Cattle Health Monitoring System.” International Journal of Engineering Research & Technology (IJERT), vol. 5, Issue 01, 2017. [6] Jazant Pawar; Rahul Sonavale; Prajkta S. Sarkale. “Transforming Cattle Farming with Artificial Intelligence: Innovations, Applications, and Implications for Precision Livestock Management and Sustainable Agriculture Practices.” Revista Electrónica de Veterinaria, 2025. [7] B. Aharwal, B. Roy, S. Meshram, and A. Yadav, “Worth of Artificial Intelligence in the Epoch of Modern Livestock Farming: A Review,” Agricultural Science Digest, vol. 43, no. 1, pp. 01-09, Feb. 2023, doi: 10.18805/ag.D-5355. [8] P. Felcy Judith and P. Sagaya Aurelia, “AI Technologies for Livestock Health Monitoring and Diagnosis,” International Journal of Arts & Education Research, vol. 12, no. 3, May-Jun. 2023. [9] “AI for Livestock Management,” India AI Case Study, TCS – mKRISHI Platform, [Online]. [10] “Cluster-based real-time analysis of mobile healthcare application for prediction of physiological data”, Google Scholar, Published: 18 August 2017, Volume 9, pages 429–445, (2018) [11] “A real time intelligent image based document classification using CNN and SVM”, SP Potharaju, SN Tambe,SB Tambe – 2023, doi: https://doi.org/10.21203/rs.3.rs-3409814/v1 [12] “Enhanced X-ray image Classification for Pneumonia Detection Using Deep Learning Based CBAM and SE Mechanisms”, S Potharaju, SN Tambe, K Dasari, N Srikanth, R Venkatarao, S Tambe Intelligence-Based Medicine, 100299

Copyright

Copyright © 2026 Sagar Tambe, Ayush Jain, Ankit Verma, Keya Goashandhe, Anu Gudi. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.