EMG-Based Hand Motion Analyser and Real-Time Energy Tracking

This paper presents the development of an EMG-based hand motion analyzer integrated with real-time energy tracking for biomedical and fitness applications. Surface EMG electrodes are employed to capture muscle activity, and the acquired signals are amplified, filtered, and processed using an ESP32 microcontroller. Key features such as Mean Absolute Value (MAV), contraction intensity, repetition count, fatigue index, and energy expenditure are extracted and transmitted wirelessly to an IoT-enabled Blynk dashboard. Experimental evaluation was conducted under resting and active conditions. The estimated energy expenditure during resting conditions remained below$0.2 \text{kcal} / \min$, while active hand movements resulted in energy levels in the range of$1.2-2.8 \text{kcal} / \min$, demonstrating clear separation between rest and activity states. Validation using Bland–Altman analysis indicated that the majority of estimation errors lay within acceptable agreement limits, confirming the reliability of the proposed energy tracking approach for wearable applications.