English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Nowadays, Hearth Rate (HR) monitoring is a key feature of almost allwrist-worn devices exploiting photoplethysmography (PPG) sensors. However, armmovements affect the performance of PPG-based HR tracking. This issue isusually addressed by fusing the PPG signal with data produced by inertialmeasurement units. Thus, deep learning algorithms have been proposed, but theyare considered too complex to deploy on wearable devices and lack theexplainability of results. In this work, we present a new deep learning model,PULSE, which exploits temporal convolutions and multi-head cross-attention toimprove sensor fusion's effectiveness and achieve a step towardsexplainability. We evaluate the performance of PULSE on three publiclyavailable datasets, reducing the mean absolute error by 7.56% on the mostextensive available dataset, PPG-DaLiA. Finally, we demonstrate theexplainability of PULSE and the benefits of applying attention modules to PPGand motion data.

Multi-Head Cross-Attentional PPG and Motion Signal Fusion for Heart Rate Estimation