TY - JOUR U1 - Zeitschriftenartikel, wissenschaftlich - begutachtet (reviewed) A1 - Biagetti, Giorgio A1 - Crippa, Paolo A1 - Falaschetti, Laura A1 - Focante, Edoardo A1 - Martínez Madrid, Natividad A1 - Seepold, Ralf A1 - Turchetti, Claudio T1 - Machine learning and data fusion techniques applied to physical activity classification using photoplethysmographic and accelerometric signals JF - Procedia computer science N2 - 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. KW - machine learning KW - data fusion KW - activity classification KW - decision tree KW - kNN KW - photoplethysmography KW - PPG KW - acceleration Y1 - 2020 UN - https://nbn-resolving.org/urn:nbn:de:bsz:rt2-opus4-29772 SN - 1877-0509 SS - 1877-0509 U6 - https://doi.org/10.1016/j.procs.2020.09.178 DO - https://doi.org/10.1016/j.procs.2020.09.178 VL - 176 SP - 3103 EP - 3111 S1 - 9 PB - Elsevier CY - Amsterdam ER -