Fatigue is a common symptom in many chronic diseases, such as multiple sclerosis and psychiatric disorders. Currently, the progress of a patient’s fatigue needs to be monitored manually and is time consuming. Together with the ETH AI Center, I explored the feasibility of automated fatigue monitoring with machine learning using non-intrusive wearable devices. The fully implemented data pipeline, composed of intensive preprocessing and deep learning models, is able to accurately predict both physical and mental fatigue and resulted in the publication shown below.
Publication: https://arxiv.org/abs/2401.05437
Repository: https://github.com/Yahnnosh/Sensor-Based-Modeling-of-Fatigue-Using-Transformer-Model
Portfolio 