Physical Activity Recognition Based on a Parallel Approach for an Ensemble of Machine Learning and Deep Learning Classifiers
Human activity recognition (HAR) by wearable sensor devices embedded in the Internet of things (IOT) can play a significant role in remote health monitoring and emergency notification to provide healthcare of higher standards. The purpose of this study is to investigate a human activity recognition...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/14/4713 |
| _version_ | 1797526070415589376 |
|---|---|
| author | Mariem Abid Amal Khabou Youssef Ouakrim Hugo Watel Safouene Chemcki Amar Mitiche Amel Benazza-Benyahia Neila Mezghani |
| author_facet | Mariem Abid Amal Khabou Youssef Ouakrim Hugo Watel Safouene Chemcki Amar Mitiche Amel Benazza-Benyahia Neila Mezghani |
| author_sort | Mariem Abid |
| collection | DOAJ |
| description | Human activity recognition (HAR) by wearable sensor devices embedded in the Internet of things (IOT) can play a significant role in remote health monitoring and emergency notification to provide healthcare of higher standards. The purpose of this study is to investigate a human activity recognition method of accrued decision accuracy and speed of execution to be applicable in healthcare. This method classifies wearable sensor acceleration time series data of human movement using an efficient classifier combination of feature engineering-based and feature learning-based data representation. Leave-one-subject-out cross-validation of the method with data acquired from 44 subjects wearing a single waist-worn accelerometer on a smart textile, and engaged in a variety of 10 activities, yielded an average recognition rate of 90%, performing significantly better than individual classifiers. The method easily accommodates functional and computational parallelization to bring execution time significantly down. |
| first_indexed | 2024-03-10T09:24:56Z |
| format | Article |
| id | doaj.art-a509cce4427046a5b8586e1fa9ad81f3 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:24:56Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a509cce4427046a5b8586e1fa9ad81f32023-11-22T04:54:58ZengMDPI AGSensors1424-82202021-07-012114471310.3390/s21144713Physical Activity Recognition Based on a Parallel Approach for an Ensemble of Machine Learning and Deep Learning ClassifiersMariem Abid0Amal Khabou1Youssef Ouakrim2Hugo Watel3Safouene Chemcki4Amar Mitiche5Amel Benazza-Benyahia6Neila Mezghani7Laboratoire LIO, Centre de Recherche du CHUM, Montreal, QC H2X 0A9, CanadaLaboratoire LIO, Centre de Recherche du CHUM, Montreal, QC H2X 0A9, CanadaLaboratoire LIO, Centre de Recherche du CHUM, Montreal, QC H2X 0A9, CanadaLaboratoire LIO, Centre de Recherche du CHUM, Montreal, QC H2X 0A9, CanadaLICEF Institute, TELUQ University, Montreal, QC G1K 9H6, CanadaINRS, Centre Énergie, Matériaux et Télécommunications, Montreal, QC G1K 9A9, CanadaLR11TIC01, COSIM Lab., University of Carthage SUP’COM, El Ghazala 2083, TunisiaLaboratoire LIO, Centre de Recherche du CHUM, Montreal, QC H2X 0A9, CanadaHuman activity recognition (HAR) by wearable sensor devices embedded in the Internet of things (IOT) can play a significant role in remote health monitoring and emergency notification to provide healthcare of higher standards. The purpose of this study is to investigate a human activity recognition method of accrued decision accuracy and speed of execution to be applicable in healthcare. This method classifies wearable sensor acceleration time series data of human movement using an efficient classifier combination of feature engineering-based and feature learning-based data representation. Leave-one-subject-out cross-validation of the method with data acquired from 44 subjects wearing a single waist-worn accelerometer on a smart textile, and engaged in a variety of 10 activities, yielded an average recognition rate of 90%, performing significantly better than individual classifiers. The method easily accommodates functional and computational parallelization to bring execution time significantly down.https://www.mdpi.com/1424-8220/21/14/4713machine learningdeep learningbig datadata streamsInternet of thingssensor data |
| spellingShingle | Mariem Abid Amal Khabou Youssef Ouakrim Hugo Watel Safouene Chemcki Amar Mitiche Amel Benazza-Benyahia Neila Mezghani Physical Activity Recognition Based on a Parallel Approach for an Ensemble of Machine Learning and Deep Learning Classifiers Sensors machine learning deep learning big data data streams Internet of things sensor data |
| title | Physical Activity Recognition Based on a Parallel Approach for an Ensemble of Machine Learning and Deep Learning Classifiers |
| title_full | Physical Activity Recognition Based on a Parallel Approach for an Ensemble of Machine Learning and Deep Learning Classifiers |
| title_fullStr | Physical Activity Recognition Based on a Parallel Approach for an Ensemble of Machine Learning and Deep Learning Classifiers |
| title_full_unstemmed | Physical Activity Recognition Based on a Parallel Approach for an Ensemble of Machine Learning and Deep Learning Classifiers |
| title_short | Physical Activity Recognition Based on a Parallel Approach for an Ensemble of Machine Learning and Deep Learning Classifiers |
| title_sort | physical activity recognition based on a parallel approach for an ensemble of machine learning and deep learning classifiers |
| topic | machine learning deep learning big data data streams Internet of things sensor data |
| url | https://www.mdpi.com/1424-8220/21/14/4713 |
| work_keys_str_mv | AT mariemabid physicalactivityrecognitionbasedonaparallelapproachforanensembleofmachinelearninganddeeplearningclassifiers AT amalkhabou physicalactivityrecognitionbasedonaparallelapproachforanensembleofmachinelearninganddeeplearningclassifiers AT youssefouakrim physicalactivityrecognitionbasedonaparallelapproachforanensembleofmachinelearninganddeeplearningclassifiers AT hugowatel physicalactivityrecognitionbasedonaparallelapproachforanensembleofmachinelearninganddeeplearningclassifiers AT safouenechemcki physicalactivityrecognitionbasedonaparallelapproachforanensembleofmachinelearninganddeeplearningclassifiers AT amarmitiche physicalactivityrecognitionbasedonaparallelapproachforanensembleofmachinelearninganddeeplearningclassifiers AT amelbenazzabenyahia physicalactivityrecognitionbasedonaparallelapproachforanensembleofmachinelearninganddeeplearningclassifiers AT neilamezghani physicalactivityrecognitionbasedonaparallelapproachforanensembleofmachinelearninganddeeplearningclassifiers |