Smart Hiking Stick with IMU & AI Fatigue Monitoring

This paper presents the development of a smart hiking stick integrated with Inertial Measurement Unit(IMU) sensors and an AI-based fatigue monitoring system. The project focuses on real-time data acquisition, offline storage, and efficient fatigue prediction using lightweight neural networks. We designed a custom mobile application to collect gyroscope and accelerometer data, which are transmitted via a secure SFTP channel to a self-hosted Linux server. The collected time- series data is segmented and used to train a GRU-based binary classification model to distinguish between fatigued and non- fatigued states. The model demonstrates strong classification performance and is optimized for mobile deployment, contributing to enhanced hiking safety through early fatigue detection.