Towards an AI-Driven Elderly Assistance Framework with Multi-Sensor Data for Real-Time Fall Detection

Wearable sensors have revolutionized continuous human activity monitoring, significantly influencing health tracking, rehabilitation, and assistive technologies. This study investigates the feasibility of a belt-mounted array of Inertial Measurement Units (IMUs) for real-time fall detection and activity recognition. A deep learning framework based on Long Short-Term Memory (LSTM) networks is developed and compared against classical machine learning models, including Support Vector Machines (SVM), Random Forest, and XGBoost. The experimental setup employs a custom prototype integrating the Adafruit ICM-20948 IMU sensor across three different devices: a knee-mounted sensor, a waist-mounted sensor, and an ankle-mounted sensor, along with the Huzzah32 microcontroller, utilizing Bluetooth Low Energy (BLE) for realtime data transmission. Experimental results show that the LSTM model achieves the highest recognition accuracy of 93.6% using data from a knee-mounted sensor, outperforming traditional machine learning approaches. These findings underscore the potential of IMU-based wearable systems for reliable and portable fall detection, contributing to enhanced elderly home care and emergency response applications.