Monitoring Acoustic Data Streams Using Possibilistic Aggregation and Multi-label Learning

Abstract

This paper introduces a novel procedure for statistical monitoring of acoustic data streams supported by possibilistic aggregation and multi-label learning. The primary goal is to learn improved control limits for the residual control charts due to the objective removal of measurements from the non-healthy state of a patient determined through multi-label learning.The proposed procedure is illustrated with real-life acoustic data collected from smartphones of Bipolar Disorder patient. Multi-label classification enabled to distinguish between different degrees of severity of manic and depressive symptoms, and especially for the mixed state -their simultaneous occurrence.