Format

Send to

Choose Destination
Sensors (Basel). 2018 Feb 24;18(2). pii: E679. doi: 10.3390/s18020679.

Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors.

Author information

1
Research Group for Pattern Recognition, University of Siegen, Hölderlinstr 3, 57076 Siegen, Germany. frederic.li@uni-siegen.de.
2
Research Group for Pattern Recognition, University of Siegen, Hölderlinstr 3, 57076 Siegen, Germany. kimiaki.shirahama@uni-siegen.de.
3
Research Group for Pattern Recognition, University of Siegen, Hölderlinstr 3, 57076 Siegen, Germany. adeel.nisar@uni-siegen.de.
4
Research Group for Pattern Recognition, University of Siegen, Hölderlinstr 3, 57076 Siegen, Germany. lukas.koeping@uni-siegen.de.
5
Research Group for Pattern Recognition, University of Siegen, Hölderlinstr 3, 57076 Siegen, Germany. marcin.grzegorzek@uni-siegen.de.
6
Department of Knowledge Engineering, University of Economics in Katowice, Bogucicka 3, 40-226 Katowice, Poland. marcin.grzegorzek@uni-siegen.de.

Abstract

Getting a good feature representation of data is paramount for Human Activity Recognition (HAR) using wearable sensors. An increasing number of feature learning approaches-in particular deep-learning based-have been proposed to extract an effective feature representation by analyzing large amounts of data. However, getting an objective interpretation of their performances faces two problems: the lack of a baseline evaluation setup, which makes a strict comparison between them impossible, and the insufficiency of implementation details, which can hinder their use. In this paper, we attempt to address both issues: we firstly propose an evaluation framework allowing a rigorous comparison of features extracted by different methods, and use it to carry out extensive experiments with state-of-the-art feature learning approaches. We then provide all the codes and implementation details to make both the reproduction of the results reported in this paper and the re-use of our framework easier for other researchers. Our studies carried out on the OPPORTUNITY and UniMiB-SHAR datasets highlight the effectiveness of hybrid deep-learning architectures involving convolutional and Long-Short-Term-Memory (LSTM) to obtain features characterising both short- and long-term time dependencies in the data.

KEYWORDS:

deep neural networks; evaluation framework; feature learning; human activity recognition; multimodal time series processing

PMID:
29495310
PMCID:
PMC5855052
DOI:
10.3390/s18020679
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center