Analyzing entropy features in time-series data for pattern recognition in neurological conditions

Yushan Huang, Yuchen Zhao, Alexander Capstick, Francesca Palermo, Hamed Haddadi, Payam M. Barnaghi

Abstract: Highlights•Time-series analysis method for neurology using information theory.•Incorporated entropy features to extract versatile high-level attributes.•Tested scalability on three datasets, one from our dementia healthcare platform.•Improved recall, F1 score, and accuracy by up to 13.08 percentage points over existing baselines.•Efficiency improved by reducing parameters 3.10x on epilepsy and heart datasets.