# Robust heartbeat detection using multimodal recordings and ECG quality assessment with signal amplitudes dispersion

arXiv: https://arxiv.org/abs/2105.10046 · HTML: https://mlsanity.com/paper/2105.10046/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2021.

## Built on by (most cited first, 2 of 2)

- [Rethinking Multimodality: Optimizing Multimodal Deep Learning for Biomedical Signal Classification](https://mlsanity.com/paper/2508.00963/) (2025)
- [Explainable Deep Neural Network for Multimodal ECG Signals: Intermediate vs Late Fusion](https://mlsanity.com/paper/2508.11666/) (2025)

## Abstract (arXiv)

Method: In this study, a new method is introduced for distinguishing noise-free segments of ECG from noisy segments that use sample amplitude dispersion with an adoptive threshold for variance of samples amplitude and a method which uses compatibility of detected beats in ECG and some of the other signals which are related to the heart activity such as BP, arterial pressure (ART) and pulmonary artery pressure (PAP). A prioritization is applied in other pulsatile signals based on the amplitude and clarity of the peaks on them, and a fusion strategy is employed for segments on which ECG is noisy and other available signals in the data, which contain peaks corresponding to R peak of the ECG, are scored in three steps scoring function.