A ballistocardiogram dataset with reference sensor signals in long-term natural sleep environments

Abstract

Abstract To facilitate unobtrusive and continuous sleep monitoring and promote intelligent sleep quality assessment, we present a dataset that includes multiple nights of continuous ballistocardiogram (BCG) data collected using piezoelectric film sensors from 32 subjects in their regular sleep environments. Besides, the referenced heart rate and respiratory data are also recorded by reference sensors to validate the accuracy of the cardiac and respiratory components extracted from the BCG signals. The dataset serves as a foundation for research on unobtrusive vital sign monitoring based on BCG signals, offering data support for the evaluation and optimization of sleep quality.