Acquisition of real time EMG signals to accommodate the needs of medical assistive device

The "Acquisition of Real-Time EMG Signals for Medical Assistive Devices" project seeks to bridge the gap between traditional diagnostic approaches for neuromuscular disorders and modern, data-driven technologies. With the growing need for continuous, real-time monitoring of muscle activity, wearable devices that assess muscle performance without frequent hospital visits have become increasingly important. At the heart of our solution is the EMG sensor, which records electrical signals produced by muscle contractions during various activities. A significant challenge in processing these signals is the presence of noise, stemming from external electrical sources or factors such as skin resistance and movement artifacts. To enhance signal quality, we employ Python-based digital signal processing techniques, including band-pass filtering and Fast Fourier Transform (FFT), ensuring reliable feature extraction. The refined EMG data is then analyzed using a Random Forest classifier, which identifies neuromuscular abnormalities such as muscular dystrophy, myopathy, and neuropathy. This real-time analytical approach facilitates early disease detection, allowing clinicians to make timely decisions and improving patient management through proactive intervention and rehabilitation strategies.