Recognizing Physical Activity of Older People from Wearable Sensors and Inconsistent Data
The physiological monitoring of older people using wearable sensors has shown great potential in improving their quality of life and preventing undesired events related to their health status. Nevertheless, creating robust predictive models from data collected unobtrusively in home environments can...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-02-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/4/880 |
_version_ | 1798006349407191040 |
---|---|
author | Aimilia Papagiannaki Evangelia I. Zacharaki Gerasimos Kalouris Spyridon Kalogiannis Konstantinos Deltouzos John Ellul Vasileios Megalooikonomou |
author_facet | Aimilia Papagiannaki Evangelia I. Zacharaki Gerasimos Kalouris Spyridon Kalogiannis Konstantinos Deltouzos John Ellul Vasileios Megalooikonomou |
author_sort | Aimilia Papagiannaki |
collection | DOAJ |
description | The physiological monitoring of older people using wearable sensors has shown great potential in improving their quality of life and preventing undesired events related to their health status. Nevertheless, creating robust predictive models from data collected unobtrusively in home environments can be challenging, especially for vulnerable ageing population. Under that premise, we propose an activity recognition scheme for older people exploiting feature extraction and machine learning, along with heuristic computational solutions to address the challenges due to inconsistent measurements in non-standardized environments. In addition, we compare the customized pipeline with deep learning architectures, such as convolutional neural networks, applied to raw sensor data without any pre- or post-processing adjustments. The results demonstrate that the generalizable deep architectures can compensate for inconsistencies during data acquisition providing a valuable alternative. |
first_indexed | 2024-04-11T12:53:21Z |
format | Article |
id | doaj.art-e78dc76304484af19cb5f91466f97c44 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-11T12:53:21Z |
publishDate | 2019-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-e78dc76304484af19cb5f91466f97c442022-12-22T04:23:09ZengMDPI AGSensors1424-82202019-02-0119488010.3390/s19040880s19040880Recognizing Physical Activity of Older People from Wearable Sensors and Inconsistent DataAimilia Papagiannaki0Evangelia I. Zacharaki1Gerasimos Kalouris2Spyridon Kalogiannis3Konstantinos Deltouzos4John Ellul5Vasileios Megalooikonomou6Department of Computer Engineering and Informatics, University of Patras, 26504 Patras, GreeceDepartment of Computer Engineering and Informatics, University of Patras, 26504 Patras, GreeceDepartment of Computer Engineering and Informatics, University of Patras, 26504 Patras, GreeceDepartment of Computer Engineering and Informatics, University of Patras, 26504 Patras, GreeceDepartment of Computer Engineering and Informatics, University of Patras, 26504 Patras, GreeceDepartment of Neurology, University Hospital of Patras, 26504 Patras, GreeceDepartment of Computer Engineering and Informatics, University of Patras, 26504 Patras, GreeceThe physiological monitoring of older people using wearable sensors has shown great potential in improving their quality of life and preventing undesired events related to their health status. Nevertheless, creating robust predictive models from data collected unobtrusively in home environments can be challenging, especially for vulnerable ageing population. Under that premise, we propose an activity recognition scheme for older people exploiting feature extraction and machine learning, along with heuristic computational solutions to address the challenges due to inconsistent measurements in non-standardized environments. In addition, we compare the customized pipeline with deep learning architectures, such as convolutional neural networks, applied to raw sensor data without any pre- or post-processing adjustments. The results demonstrate that the generalizable deep architectures can compensate for inconsistencies during data acquisition providing a valuable alternative.https://www.mdpi.com/1424-8220/19/4/880activity recognitionsupport vector machine (SVM) classificationdeep learningconvolutional neural networkswearable devicesphysiological monitoring |
spellingShingle | Aimilia Papagiannaki Evangelia I. Zacharaki Gerasimos Kalouris Spyridon Kalogiannis Konstantinos Deltouzos John Ellul Vasileios Megalooikonomou Recognizing Physical Activity of Older People from Wearable Sensors and Inconsistent Data Sensors activity recognition support vector machine (SVM) classification deep learning convolutional neural networks wearable devices physiological monitoring |
title | Recognizing Physical Activity of Older People from Wearable Sensors and Inconsistent Data |
title_full | Recognizing Physical Activity of Older People from Wearable Sensors and Inconsistent Data |
title_fullStr | Recognizing Physical Activity of Older People from Wearable Sensors and Inconsistent Data |
title_full_unstemmed | Recognizing Physical Activity of Older People from Wearable Sensors and Inconsistent Data |
title_short | Recognizing Physical Activity of Older People from Wearable Sensors and Inconsistent Data |
title_sort | recognizing physical activity of older people from wearable sensors and inconsistent data |
topic | activity recognition support vector machine (SVM) classification deep learning convolutional neural networks wearable devices physiological monitoring |
url | https://www.mdpi.com/1424-8220/19/4/880 |
work_keys_str_mv | AT aimiliapapagiannaki recognizingphysicalactivityofolderpeoplefromwearablesensorsandinconsistentdata AT evangeliaizacharaki recognizingphysicalactivityofolderpeoplefromwearablesensorsandinconsistentdata AT gerasimoskalouris recognizingphysicalactivityofolderpeoplefromwearablesensorsandinconsistentdata AT spyridonkalogiannis recognizingphysicalactivityofolderpeoplefromwearablesensorsandinconsistentdata AT konstantinosdeltouzos recognizingphysicalactivityofolderpeoplefromwearablesensorsandinconsistentdata AT johnellul recognizingphysicalactivityofolderpeoplefromwearablesensorsandinconsistentdata AT vasileiosmegalooikonomou recognizingphysicalactivityofolderpeoplefromwearablesensorsandinconsistentdata |