Multiple Instance Dictionary Learning for Beat-to-Beat Heart Rate Monitoring from Ballistocardiograms

TL;DR

This paper introduces DL-FUMI, a multiple instance dictionary learning method for beat-to-beat heart rate estimation from ballistocardiogram signals, effectively capturing individual heartbeat signatures despite alignment uncertainties.

Contribution

The paper presents DL-FUMI, a novel approach that models heartbeat detection as a multiple instance learning problem, improving heartbeat signature characterization from BCG signals.

Findings

DL-FUMI effectively estimates personal heartbeat prototypes.

DL-FUMI outperforms comparison algorithms in heartbeat detection.

The method handles uncertainty in BCG signal alignment.

Abstract

A multiple instance dictionary learning approach, Dictionary Learning using Functions of Multiple Instances (DL-FUMI), is used to perform beat-to-beat heart rate estimation and to characterize heartbeat signatures from ballistocardiogram (BCG) signals collected with a hydraulic bed sensor. DL-FUMI estimates a "heartbeat concept" that represents an individual's personal ballistocardiogram heartbeat pattern. DL-FUMI formulates heartbeat detection and heartbeat characterization as a multiple instance learning problem to address the uncertainty inherent in aligning BCG signals with ground truth during training. Experimental results show that the estimated heartbeat concept found by DL-FUMI is an effective heartbeat prototype and achieves superior performance over comparison algorithms.