Pawlytics: Pet Behaviour and Health Analysis Using AI / ML

Authors:

Asst. Prof. A. S. Khaple, Ghanashyam Ahire, Anuj Bankar, Soham Bende, Sanika Dharme

Asst. Prof. A. S. Khaple, Computer Engineering & Zeal college of Engineering and Research. Ghanashyam Ahire, Computer Engineering & Zeal college of Engineering and Research Anuj Bankar, Computer Engineering & Zeal college of Engineering and Research

Soham Bende, Computer Engineering & Zeal college of Engineering and Research Sanika Dharme, Computer Engineering & Zeal college of Engineering and Research

Abstract - The proactive assessment of pet health and emotional well-being presents a significant challenge for owners and veterinarians, as subtle behavioural changes often go unnoticed until symptoms become severe. This paper presents Pawlytics, a novel, mobile-first application designed to address this gap by leveraging Artificial Intelligence (AI) and Machine Learning (ML) for comprehensive pet health and behaviour analysis. The system's primary objective is to develop an AI-based tracking system for cats and dogs that classifies emotional states (e.g., happy, anxious, distress) from user-provided images and audio (barking, meowing). Utilizing a Flutter front-end, a Flask API server, and a Convolutional Neural Network (CNN) model, Pawlytics analyses multimodal data to predict potential health risks, generate personalized recommendations for diet and activity, and create detailed, vet-compatible health reports. The implementation of this non-invasive, low-cost solution shifts pet care from a reactive to a proactive model, aiming to reduce medical costs and significantly improve the overall life expectancy and quality of life for pets.

Keywords: Pet Health, Behavioural Analysis, Artificial Intelligence, Machine Learning, CNN, Emotion Detection, MobileNetV2.