Non-Contact Human Workload Assessment for Adaptive Intelligent Systems

Heart rate and heart rate variability are important sensor modalities for estimating workload. Estimating workload with contact-based physiological sensors has been researched, however there is a need to estimate workload using non-contact physiological sensors with camera advancements. This study offers a novel approach to this research statement with a comparison between contact and non-contact sensors for workload estimation. Hybrid deep learning architecture has been developed based on data from the Bio-Harness as a contact sensor and data from the VPG as a non-contact sensor. This research can be extended to a variety of applications for adaptive intelligent systems that rely on human-state information. Reliable non-contact monitoring support seamless operations uninhibited by wearable sensors attached to the body.