PsychNology Journal, Volume 14, Number 2-3, 99 - 115

Human Activity Recognition with Wearable Devices: A Symbolic Approach

Angelo Cenedese, Luca Minetto, Gian Antonio Susto, Matteo Terzi
University of Padua, Italy


ABSTRACT

In the context of activity recognition, wearable devices are nowadays the preferable hardware thanks to their usability, user experience and performances; at the same time, these devices present limitations in terms of computational capability and memory, which force the algorithm design to be at the same time efficient and simple. In this work, we adopt Symbolic Aggregate Approximation (SAX), a symbolic approach for information retrieval in time series data that allows dimensionality and numerosity reduction; SAX is employed here, in combination with 1-Nearest Neighbor classifier, to identify activity phases in continuous repetitive activities from inertial time-series data. The proposed approach is validated on a cross-country skiing dataset and on a daily living activities dataset.

KEYWORDS: Activity Recognition, Machine Learning, Symbolic Aggregate Approximation, Time-Series Learning, Wearable Devices.


CITE AS:
Cenedese A., Minetto L., Susto G.A., Terzi M. (2016). Human Activity Recognition with Wearable Devices: A Symbolic Approach. PsychNology Journal, 14(2-3), 99 - 115. Retrieved [month] [day], [year], from www.psychnology.org.

Download Full Text (.pdf)
Return to
PsychNology Journal Volume 14, Number 2-3