High accuracy human activity recognition using machine learning and wearable devices’ raw signals
Human activity recognition (HAR) is vital in a wide range of real-life applications such as health monitoring of olderly people, abnormal behaviour detection and smart home management. HAR systems can employ smart human-computer interfaces and be parts of active, intelligent surveillance systems. Th...
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Taylor & Francis Group
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/55facb38a4bf488ba8967f3251c30402 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:55facb38a4bf488ba8967f3251c30402 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:55facb38a4bf488ba8967f3251c304022021-11-11T14:23:43ZHigh accuracy human activity recognition using machine learning and wearable devices’ raw signals2475-18392475-184710.1080/24751839.2021.1987706https://doaj.org/article/55facb38a4bf488ba8967f3251c304022021-11-01T00:00:00Zhttp://dx.doi.org/10.1080/24751839.2021.1987706https://doaj.org/toc/2475-1839https://doaj.org/toc/2475-1847Human activity recognition (HAR) is vital in a wide range of real-life applications such as health monitoring of olderly people, abnormal behaviour detection and smart home management. HAR systems can employ smart human-computer interfaces and be parts of active, intelligent surveillance systems. The increasing use of high-tech mobile and wearable devices, such as smart phones, smart watches and smart bands, can be the key elements in building high accuracy models, as they can provide a tremendous number of signals. This research aims to develop and test a machine learning (ML) model, which can successfully recognize a performed activity using raw signals obtained by wearable devices. Photoplethysmography – Daily Life Activities (PPG-DaLiA) dataset contains data related to 15 individuals wearing physiological and motion sensors. PPG-DaLiA was used as an input to a custom data segmentation model to obtain the respective training and testing dataset. Overall, 23 ML well-established models were employed. The weighted and the fine k-nearest neighbours, the fine Gaussian support vector machines and the bagged trees were the algorithms that achieved the best performance with a very high accuracy level.Antonios PapaleonidasAnastasios Panagiotis PsathasLazaros IliadisTaylor & Francis Grouparticlehuman activity recognitionmachine learningmulti-class classificationwearablesdata segmentationTelecommunicationTK5101-6720Information technologyT58.5-58.64ENJournal of Information and Telecommunication, Vol 0, Iss 0, Pp 1-17 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
human activity recognition machine learning multi-class classification wearables data segmentation Telecommunication TK5101-6720 Information technology T58.5-58.64 |
| spellingShingle |
human activity recognition machine learning multi-class classification wearables data segmentation Telecommunication TK5101-6720 Information technology T58.5-58.64 Antonios Papaleonidas Anastasios Panagiotis Psathas Lazaros Iliadis High accuracy human activity recognition using machine learning and wearable devices’ raw signals |
| description |
Human activity recognition (HAR) is vital in a wide range of real-life applications such as health monitoring of olderly people, abnormal behaviour detection and smart home management. HAR systems can employ smart human-computer interfaces and be parts of active, intelligent surveillance systems. The increasing use of high-tech mobile and wearable devices, such as smart phones, smart watches and smart bands, can be the key elements in building high accuracy models, as they can provide a tremendous number of signals. This research aims to develop and test a machine learning (ML) model, which can successfully recognize a performed activity using raw signals obtained by wearable devices. Photoplethysmography – Daily Life Activities (PPG-DaLiA) dataset contains data related to 15 individuals wearing physiological and motion sensors. PPG-DaLiA was used as an input to a custom data segmentation model to obtain the respective training and testing dataset. Overall, 23 ML well-established models were employed. The weighted and the fine k-nearest neighbours, the fine Gaussian support vector machines and the bagged trees were the algorithms that achieved the best performance with a very high accuracy level. |
| format |
article |
| author |
Antonios Papaleonidas Anastasios Panagiotis Psathas Lazaros Iliadis |
| author_facet |
Antonios Papaleonidas Anastasios Panagiotis Psathas Lazaros Iliadis |
| author_sort |
Antonios Papaleonidas |
| title |
High accuracy human activity recognition using machine learning and wearable devices’ raw signals |
| title_short |
High accuracy human activity recognition using machine learning and wearable devices’ raw signals |
| title_full |
High accuracy human activity recognition using machine learning and wearable devices’ raw signals |
| title_fullStr |
High accuracy human activity recognition using machine learning and wearable devices’ raw signals |
| title_full_unstemmed |
High accuracy human activity recognition using machine learning and wearable devices’ raw signals |
| title_sort |
high accuracy human activity recognition using machine learning and wearable devices’ raw signals |
| publisher |
Taylor & Francis Group |
| publishDate |
2021 |
| url |
https://doaj.org/article/55facb38a4bf488ba8967f3251c30402 |
| work_keys_str_mv |
AT antoniospapaleonidas highaccuracyhumanactivityrecognitionusingmachinelearningandwearabledevicesrawsignals AT anastasiospanagiotispsathas highaccuracyhumanactivityrecognitionusingmachinelearningandwearabledevicesrawsignals AT lazarosiliadis highaccuracyhumanactivityrecognitionusingmachinelearningandwearabledevicesrawsignals |
| _version_ |
1718438937317343232 |