Realtime Stress Monitoring And Data Acquisition System Using Electroencephalogram Sensor.

Abstract

Mental stress negatively impacts human health, necessitating early detection for timely intervention. With the advent of wearable stress monitoring devices, real-time remote patient monitoring has become increasingly feasible. This research presents a real-time EEG-based stress monitoring system designed for short-range, localized use. The system captures EEG signals, processes them, and transmits data via Bluetooth to a mobile application, providing immediate feedback within the monitoring range. Unlike cloud-based remote monitoring solutions, this system operates in a proximity environment and does not store data on external servers or facilitate remote physician accessibility. The proposed methodology involves EEG signal acquisition using a ThinkGear ASIC Module (TGAM), signal preprocessing for artifact removal, feature extraction based on frequency domain analysis, and classification of stress levels using threshold-based metrics. The system was tested on seven individuals under various conditions, with EEG parameters analyzed to determine stress levels. Sensitivity analysis was performed to assess the sensor's accuracy in detecting brainwave activity. Results indicate a correlation between stress levels and EEG signal variations, confirming the system's viability for mental health applications. The study contributes to remote health monitoring and lays the groundwork for future advancements in stress assessment tools.