A Robust Algorithm for respiration rate monitoring during cognitive load using PPG Signals

The project introduces a new method for respiration rate (RR) monitoring, utilizing the OB1203 PPG biosensor module and a custom signal processing algorithm. Traditional methods often involve manual intervention or wearable straps, posing challenges, particularly in emergencies. In contrast, the PPG-based system offers a contactless and user-friendly approach, particularly in pandemics. The RR monitoring method includes data acquisition, noise filtering, and feature extraction for systolic peak detection, with real-time RR display for seamless monitoring. The algorithm's validation used the BIDMC dataset & CAPNOBASE Dataset for calibration and validation, comparing with impedance respiratory signals. Results showcase a superior performance of the proposed algorithm, as evidenced by low RMSE values of 0.8 and 1.2 for BIDMC, and CAPNOBASE datasets, respectively. Additionally, the project explores the RR-cognitive load correlation. Through a study involving tasks with varying mental effort, we contribute to cognitive load assessment. This innovative approach holds promise for vital sign monitoring efficiency, especially in emergencies, and cognitive load assessment in clinical and healthcare settings.