EmoTrack: AI-Powered Wearable System for Emotion, Fatigue, and Fall Detection in Elderly Healthcare

Abstract

The elderly population is increasingly vulnerable to health risks such as falls, fatigue, emotional stress, and sudden medical emergencies, particularly when living alone without con- tinuous supervision. Delayed medical response in such situations can result in severe injuries or fatal outcomes. Although existing healthcare monitoring systems and wearable devices provide basic physiological tracking, they often lack intelligent emotion analysis, fatigue detection, and real-time alert mechanisms. This paper presents EmoTrack, an AI-powered wearable healthcare monitoring system designed specifically for elderly individuals. The proposed system integrates physiological sensor data, motion data, and emotion analysis to continuously monitor the physical and emotional well-being of users. An ESP32 microcontroller processes sensor inputs such as heart rate, motion, and fatigue indicators, while machine learning models analyze emotional states and abnormal activity patterns. The system detects falls using motion sensor data and triggers real-time alerts with GPS-based location tracking.Emergency situations are handled through an SOS mechanism that immediately notifies caregivers via wireless communication. EmoTrack aims to provide an affordable, intelligent, and reliable healthcare solution that enhances elderly safety, supports independent living, and enables timely medical intervention.