[ML Seminars] Machine Learning and Wearable Sensors for Mental Health Monitoring
Enrique Garcia-Ceja from Ifi talks about how machine learning can aid mental health monitoring through smartwatches and other wearable devices.
With the current advances of sensor miniaturization, it has
become possible to develop and commercialize devices with outstanding
sensing capabilities such as smartwatches, fitness bracelets, smartphones,
etc. Previous studies have shown the potential of using such devices to
monitor user behavior such as location, mood, activities and so on.
Nowadays, mental health problems are becoming more common worldwide.
Traditional mental health monitoring methods rely on retrospective reports
which are subject to recall bias, time constraints, etc. Given that mental
states can manifest through physiological and behavioral changes, wearable
devices have the potential to be used to sense those signals which can
later, be analyzed using machine learning to predict states. These type of
applications also present several challenges which will be discussed.