Detection of Pharyngolaryngeal Activities in Real-World Settings Using Wearable Sensors - Signaux et Images
Conference Papers Year : 2024

Detection of Pharyngolaryngeal Activities in Real-World Settings Using Wearable Sensors

Abstract

Automatic detection and identification of pharyngolaryngeal activities (PLA) such as swallowing, speaking, and coughing, are crucial steps in developing a system for diagnosing dysphagia (swallowing disorders) using high-resolution cervical auscultation (HRCA) signals. Using sensors placed on the throat, HRCA provides clinicians with a non-invasive means of assessing swallowing. This study introduces a new approach based on depthwise CNN and LSTM networks to automatically detect and identify PLA in synchronized accelerometer and microphone signals. This method achieves an Fscore of 88% for swallow detection across seven hours of HRCA signals recorded from 42 healthy subjects under both supervised and ecological conditions. It outperforms state-of-the-art systems in real-world settings. On other activities, the system reaches an Fscore of 93% for phonation and 86% for airway defense mechanisms, making it a promising tool to assist clinicians in the analysis of HRCA signals and a reliable base towards non-invasive assessment of dysphagia.
Fichier principal
Vignette du fichier
EMBC_lila_2024_preprint.pdf (413.36 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04561003 , version 1 (26-04-2024)

Identifiers

  • HAL Id : hal-04561003 , version 1

Cite

Lila Gravellier, Maxime Le Coz, Jérôme Farinas, Julien Pinquier. Detection of Pharyngolaryngeal Activities in Real-World Settings Using Wearable Sensors. 46th annual international conference of the IEEE engineering in medicine and biology society (EMBC 2024), EMBC: Engineering in Medicine and Biology Society, Jul 2024, Orlando (Florida), United States. à paraître. ⟨hal-04561003⟩
368 View
52 Download

Share

More