Volltext-Downloads (blau) und Frontdoor-Views (grau)

Machine learning and data fusion techniques applied to physical activity classification using photoplethysmographic and accelerometric signals

  • The evaluation of the effectiveness of different machine learning algorithms on a publicly available database of signals derived from wearable devices is presented with the goal of optimizing human activity recognition and classification. Among the wide number of body signals we choose a couple of signals, namely photoplethysmographic (optically detected subcutaneous blood volume) and tri-axis acceleration signals that are easy to be simultaneously acquired using commercial widespread devices (e.g. smartwatches) as well as custom wearable wireless devices designed for sport, healthcare, or clinical purposes. To this end, two widely used algorithms (decision tree and k-nearest neighbor) were tested, and their performance were compared to two new recent algorithms (particle Bernstein and a Monte Carlo-based regression) both in terms of accuracy and processing time. A data preprocessing phase was also considered to improve the performance of the machine learning procedures, in order to reduce the problem size and a detailed analysis of the compression strategy and results is also presented.

Download full text files

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author of HS ReutlingenMartínez Madrid, Natividad
URN:urn:nbn:de:bsz:rt2-opus4-29772
DOI:https://doi.org/10.1016/j.procs.2020.09.178
ISSN:1877-0509
Erschienen in:Procedia computer science
Publisher:Elsevier
Place of publication:Amsterdam
Document Type:Journal article
Language:English
Publication year:2020
Tag:PPG; acceleration; activity classification; data fusion; decision tree; kNN; machine learning; photoplethysmography
Volume:176
Page Number:9
First Page:3103
Last Page:3111
DDC classes:004 Informatik
Open access?:Ja
Licence (German):License Logo  Creative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International