Human Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals

Inertial sensors are widely used in the field of human activity recognition (HAR), since this source of information is the most informative time series among non-visual datasets. HAR researchers are actively exploring other approaches and different sources of signals to improve the performance of HA...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mahsa Sadat Afzali Arani, Diego Elias Costa, Emad Shihab
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	human activity recognition (HAR) early fusion 3D-accelerometer (3D-ACC) electrocardiogram (ECG) photoplethysmogram (PPG) Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/52985a7a19c74919903522baac9f6dfa
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:52985a7a19c74919903522baac9f6dfa
record_format	dspace
spelling	oai:doaj.org-article:52985a7a19c74919903522baac9f6dfa2021-11-11T19:02:22ZHuman Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals10.3390/s212169971424-8220https://doaj.org/article/52985a7a19c74919903522baac9f6dfa2021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/6997https://doaj.org/toc/1424-8220Inertial sensors are widely used in the field of human activity recognition (HAR), since this source of information is the most informative time series among non-visual datasets. HAR researchers are actively exploring other approaches and different sources of signals to improve the performance of HAR systems. In this study, we investigate the impact of combining bio-signals with a dataset acquired from inertial sensors on recognizing human daily activities. To achieve this aim, we used the PPG-DaLiA dataset consisting of 3D-accelerometer (3D-ACC), electrocardiogram (ECG), photoplethysmogram (PPG) signals acquired from 15 individuals while performing daily activities. We extracted hand-crafted time and frequency domain features, then, we applied a correlation-based feature selection approach to reduce the feature-set dimensionality. After introducing early fusion scenarios, we trained and tested random forest models with subject-dependent and subject-independent setups. Our results indicate that combining features extracted from the 3D-ACC signal with the ECG signal improves the classifier’s performance F1-scores by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.72</mn><mo>%</mo></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3.00</mn><mo>%</mo></mrow></semantics></math></inline-formula> (from <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>94.07</mn><mo>%</mo></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>96.80</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>83.16</mn><mo>%</mo></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>86.17</mn><mo>%</mo></mrow></semantics></math></inline-formula>) for subject-dependent and subject-independent approaches, respectively.Mahsa Sadat Afzali AraniDiego Elias CostaEmad ShihabMDPI AGarticlehuman activity recognition (HAR)early fusion3D-accelerometer (3D-ACC)electrocardiogram (ECG)photoplethysmogram (PPG)Chemical technologyTP1-1185ENSensors, Vol 21, Iss 6997, p 6997 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	human activity recognition (HAR) early fusion 3D-accelerometer (3D-ACC) electrocardiogram (ECG) photoplethysmogram (PPG) Chemical technology TP1-1185
spellingShingle	human activity recognition (HAR) early fusion 3D-accelerometer (3D-ACC) electrocardiogram (ECG) photoplethysmogram (PPG) Chemical technology TP1-1185 Mahsa Sadat Afzali Arani Diego Elias Costa Emad Shihab Human Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals
description	Inertial sensors are widely used in the field of human activity recognition (HAR), since this source of information is the most informative time series among non-visual datasets. HAR researchers are actively exploring other approaches and different sources of signals to improve the performance of HAR systems. In this study, we investigate the impact of combining bio-signals with a dataset acquired from inertial sensors on recognizing human daily activities. To achieve this aim, we used the PPG-DaLiA dataset consisting of 3D-accelerometer (3D-ACC), electrocardiogram (ECG), photoplethysmogram (PPG) signals acquired from 15 individuals while performing daily activities. We extracted hand-crafted time and frequency domain features, then, we applied a correlation-based feature selection approach to reduce the feature-set dimensionality. After introducing early fusion scenarios, we trained and tested random forest models with subject-dependent and subject-independent setups. Our results indicate that combining features extracted from the 3D-ACC signal with the ECG signal improves the classifier’s performance F1-scores by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.72</mn><mo>%</mo></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3.00</mn><mo>%</mo></mrow></semantics></math></inline-formula> (from <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>94.07</mn><mo>%</mo></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>96.80</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>83.16</mn><mo>%</mo></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>86.17</mn><mo>%</mo></mrow></semantics></math></inline-formula>) for subject-dependent and subject-independent approaches, respectively.
format	article
author	Mahsa Sadat Afzali Arani Diego Elias Costa Emad Shihab
author_facet	Mahsa Sadat Afzali Arani Diego Elias Costa Emad Shihab
author_sort	Mahsa Sadat Afzali Arani
title	Human Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals
title_short	Human Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals
title_full	Human Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals
title_fullStr	Human Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals
title_full_unstemmed	Human Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals
title_sort	human activity recognition: a comparative study to assess the contribution level of accelerometer, ecg, and ppg signals
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/52985a7a19c74919903522baac9f6dfa
work_keys_str_mv	AT mahsasadatafzaliarani humanactivityrecognitionacomparativestudytoassessthecontributionlevelofaccelerometerecgandppgsignals AT diegoeliascosta humanactivityrecognitionacomparativestudytoassessthecontributionlevelofaccelerometerecgandppgsignals AT emadshihab humanactivityrecognitionacomparativestudytoassessthecontributionlevelofaccelerometerecgandppgsignals
_version_	1718431645548150784

Human Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals

Ejemplares similares