| Description: |
On its surface human behaviour in the real world appears complex, and highly different from one moment to the next. The log of behavioral episodes captured on the smartphone touchscreen can span multiple years, enabling the discovery of hidden behavioral structures. Recent work in our laboratory suggest that day-to-day smartphone interactions are strongly shaped by diurnal and multi-day rhythms. Still, predicting the discrete behavioral time series remains a challenge, and meeting this challenge is key to developing a new generation of passive behavioral anomaly detectors such as to flag severe neurological diseases. In this workgroup we shall explore the different frameworks to predict the time series of real-world smartphone behaviour. |