Hearables: In-ear Multimodal Data Fusion for Robust Heart Rate Estimation

• DOI: 10.20944/preprints202402.1313.v1
• Publication Date: 2024-03-04T06:16:57Z
• Authors: Marek Zylinski; Amir Nassibi; Edoardo Occhipinti; Adil Malik; Matteo Bermond; Harry J. Davies; Danilo P. Mandic
• Keywords: Sensor Fusion

Ambulatory heart rate (HR) monitors that acquire electrocardiogram (ECG) or/and photoplethysmographm (PPG) signals from the torso, wrists, or ears are notably less accurate in tasks associated with high levels of movement compared to clinical measurements. However, reliable estimation HR can be obtained through data fusion different sensors. These methods especially suitable for multimodal hearable devices, where tracked modalities, including electrical ECG, optical PPG, and sounds (heart tones). Combined information modalities compensate single source limitations. In this paper, we evaluate possible application hearables. We assess simultaneous in-ear ECG recorded on eight subjects while performing 5-minute sitting walking tasks. Our findings show provide a similar level mean absolute error as best single-source but much lower intra-subject variability, during activities. conclude more robust than cardiovascular signal. enhance performance wearable hearables, tracking physical activity.