Early detection of symptoms is of utmost importance in identifying diseases at an earlier stage. Integrating continuous health monitoring into private spaces, such as vehicles, holds great potential for detecting diseases at an earlier stage. This, in turn, allows for better treatment options. Considering that the average person spends approximately 43 minutes per day in a vehicle, implementing an in-vehicle sensor system presents a unique opportunity to seamlessly incorporate medical check-ups into our daily mobility. This project aims to find what percentage of the driving time is suitable for a reliable heart rate analysis. This can determine if it is possible to use travel time for accurate heart rate analysis
This project aims to integrate a health monitoring system into a car, utilizing multiple sensors to measure the electrocardiogram (ECG), photoplethysmogram (PPG), and remote PPG (rPPG). Additionally, the sensor system will be integrated into the existing CAN-BUS system and consider in-build sensors. The recorded data will be combined with sensor fusion approach using neural network structure, analyzed, and the reference heart rate compared with the calculated heart rate. The goal is to determine the usable recording time for analysis and improve the used algorithms for artifact detection and sensor fusion.