Cargando…
Automatic Detection of Dyspnea in Real Human–Robot Interaction Scenarios
A respiratory distress estimation technique for telephony previously proposed by the authors is adapted and evaluated in real static and dynamic HRI scenarios. The system is evaluated with a telephone dataset re-recorded using the robotic platform designed and implemented for this study. In addition...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10490721/ https://www.ncbi.nlm.nih.gov/pubmed/37688044 http://dx.doi.org/10.3390/s23177590 |
_version_ | 1785103906141896704 |
---|---|
author | Alvarado, Eduardo Grágeda, Nicolás Luzanto, Alejandro Mahu, Rodrigo Wuth, Jorge Mendoza, Laura Stern, Richard M. Yoma, Néstor Becerra |
author_facet | Alvarado, Eduardo Grágeda, Nicolás Luzanto, Alejandro Mahu, Rodrigo Wuth, Jorge Mendoza, Laura Stern, Richard M. Yoma, Néstor Becerra |
author_sort | Alvarado, Eduardo |
collection | PubMed |
description | A respiratory distress estimation technique for telephony previously proposed by the authors is adapted and evaluated in real static and dynamic HRI scenarios. The system is evaluated with a telephone dataset re-recorded using the robotic platform designed and implemented for this study. In addition, the original telephone training data are modified using an environmental model that incorporates natural robot-generated and external noise sources and reverberant effects using room impulse responses (RIRs). The results indicate that the average accuracy and AUC are just 0.4% less than those obtained with matched training/testing conditions with simulated data. Quite surprisingly, there is not much difference in accuracy and AUC between static and dynamic HRI conditions. Moreover, the beamforming methods delay-and-sum and MVDR lead to average improvement in accuracy and AUC equal to 8% and 2%, respectively, when applied to training and testing data. Regarding the complementarity of time-dependent and time-independent features, the combination of both types of classifiers provides the best joint accuracy and AUC score. |
format | Online Article Text |
id | pubmed-10490721 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-104907212023-09-09 Automatic Detection of Dyspnea in Real Human–Robot Interaction Scenarios Alvarado, Eduardo Grágeda, Nicolás Luzanto, Alejandro Mahu, Rodrigo Wuth, Jorge Mendoza, Laura Stern, Richard M. Yoma, Néstor Becerra Sensors (Basel) Article A respiratory distress estimation technique for telephony previously proposed by the authors is adapted and evaluated in real static and dynamic HRI scenarios. The system is evaluated with a telephone dataset re-recorded using the robotic platform designed and implemented for this study. In addition, the original telephone training data are modified using an environmental model that incorporates natural robot-generated and external noise sources and reverberant effects using room impulse responses (RIRs). The results indicate that the average accuracy and AUC are just 0.4% less than those obtained with matched training/testing conditions with simulated data. Quite surprisingly, there is not much difference in accuracy and AUC between static and dynamic HRI conditions. Moreover, the beamforming methods delay-and-sum and MVDR lead to average improvement in accuracy and AUC equal to 8% and 2%, respectively, when applied to training and testing data. Regarding the complementarity of time-dependent and time-independent features, the combination of both types of classifiers provides the best joint accuracy and AUC score. MDPI 2023-09-01 /pmc/articles/PMC10490721/ /pubmed/37688044 http://dx.doi.org/10.3390/s23177590 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Alvarado, Eduardo Grágeda, Nicolás Luzanto, Alejandro Mahu, Rodrigo Wuth, Jorge Mendoza, Laura Stern, Richard M. Yoma, Néstor Becerra Automatic Detection of Dyspnea in Real Human–Robot Interaction Scenarios |
title | Automatic Detection of Dyspnea in Real Human–Robot Interaction Scenarios |
title_full | Automatic Detection of Dyspnea in Real Human–Robot Interaction Scenarios |
title_fullStr | Automatic Detection of Dyspnea in Real Human–Robot Interaction Scenarios |
title_full_unstemmed | Automatic Detection of Dyspnea in Real Human–Robot Interaction Scenarios |
title_short | Automatic Detection of Dyspnea in Real Human–Robot Interaction Scenarios |
title_sort | automatic detection of dyspnea in real human–robot interaction scenarios |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10490721/ https://www.ncbi.nlm.nih.gov/pubmed/37688044 http://dx.doi.org/10.3390/s23177590 |
work_keys_str_mv | AT alvaradoeduardo automaticdetectionofdyspneainrealhumanrobotinteractionscenarios AT gragedanicolas automaticdetectionofdyspneainrealhumanrobotinteractionscenarios AT luzantoalejandro automaticdetectionofdyspneainrealhumanrobotinteractionscenarios AT mahurodrigo automaticdetectionofdyspneainrealhumanrobotinteractionscenarios AT wuthjorge automaticdetectionofdyspneainrealhumanrobotinteractionscenarios AT mendozalaura automaticdetectionofdyspneainrealhumanrobotinteractionscenarios AT sternrichardm automaticdetectionofdyspneainrealhumanrobotinteractionscenarios AT yomanestorbecerra automaticdetectionofdyspneainrealhumanrobotinteractionscenarios |