Sanchez Guinea, Alejandro ; Sarabchian, Mehran ; Mühlhäuser, Max (2021)
Image-based Activity Recognition from IMU Data.
19th International Conference on Pervasive Computing and Communications. virtual Conference (22.03.2021-26.03.2021)
doi: 10.1109/PerComWorkshops51409.2021.9430990
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
In this paper we propose an approach to improve the performance of human activity recognition (HAR) from inertial sensors data, based on image processing techniques. Our approach creates image representations of the time-series data to take advantage of the strengths that convolutional neural networks (CNNs) have shown when dealing with image data. We have conducted an evaluation using benchmark datasets that are considered among the most relevant in HAR. Our results show that our approach is able to outperform the state of the art in all cases.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2021 |
| Autor(en): | Sanchez Guinea, Alejandro ; Sarabchian, Mehran ; Mühlhäuser, Max |
| Art des Eintrags: | Bibliographie |
| Titel: | Image-based Activity Recognition from IMU Data |
| Sprache: | Englisch |
| Publikationsjahr: | 25 Mai 2021 |
| Verlag: | IEEE |
| Buchtitel: | 2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops) |
| Reihe: | 18th Conference on Pervasive Computing and Communications Workshops |
| Veranstaltungstitel: | 19th International Conference on Pervasive Computing and Communications |
| Veranstaltungsort: | virtual Conference |
| Veranstaltungsdatum: | 22.03.2021-26.03.2021 |
| DOI: | 10.1109/PerComWorkshops51409.2021.9430990 |
| Kurzbeschreibung (Abstract): | In this paper we propose an approach to improve the performance of human activity recognition (HAR) from inertial sensors data, based on image processing techniques. Our approach creates image representations of the time-series data to take advantage of the strengths that convolutional neural networks (CNNs) have shown when dealing with image data. We have conducted an evaluation using benchmark datasets that are considered among the most relevant in HAR. Our results show that our approach is able to outperform the state of the art in all cases. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Telekooperation |
| Hinterlegungsdatum: | 17 Feb 2022 15:21 |
| Letzte Änderung: | 17 Feb 2022 15:21 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum