Skip to main content
Fig. 1 | BMC Psychiatry

Fig. 1

From: Identifying patient-specific behaviors to understand illness trajectories and predict relapses in bipolar disorder using passive sensing and deep anomaly detection: protocol for a contactless cohort study

Fig. 1

Using deep learning models with data containing different signals. An example of using deep learning models with data containing three different signals. This data, while following a sinus rhythm with low noise (red, green, and blue lines), experiences high noise at the end of the series (solid black line for noise and dashed lines identifying outlier period)

Back to article page