Next Article in Journal
Optimal Bands Combination Selection for Extracting Garlic Planting Area with Multi-Temporal Sentinel-2 Imagery
Next Article in Special Issue
Using Privacy Respecting Sound Analysis to Improve Bluetooth Based Proximity Detection for COVID-19 Exposure Tracing and Social Distancing
Previous Article in Journal
Spectral-Coding-Based Compressive Single-Pixel NIR Spectroscopy in the Sub-Millisecond Regime
Previous Article in Special Issue
Activity-Aware Vital Sign Monitoring Based on a Multi-Agent Architecture
Article

Deep Learning for Classifying Physical Activities from Accelerometer Data

1
Department of Science and Industry Systems, University of South-Eastern Norway, Hasbergsvei 36, Krona, 3616 Kongsberg, Norway
2
CAIR, Department of ICT, University of Agder, Jon Lilletunsvei 9, 4879 Grimstad, Norway
3
Department of Sport Science and Physical Education, University of Agder, Universitetsveien 25, 4630 Kristiansand, Norway
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editors: Mario Martínez-Zarzuela and David González Ortega
Sensors 2021, 21(16), 5564; https://doi.org/10.3390/s21165564
Received: 19 June 2021 / Revised: 11 August 2021 / Accepted: 12 August 2021 / Published: 18 August 2021
(This article belongs to the Special Issue Human Activity Detection and Recognition)
Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the two models on two physical movement datasets collected from several volunteers who carried tri-axial accelerometer sensors. The first dataset is from the UCI machine learning repository, which contains 14 different activities-of-daily-life (ADL) and is collected from 16 volunteers who carried a single wrist-worn tri-axial accelerometer. The second dataset includes ten other ADLs and is gathered from eight volunteers who placed the sensors on their hips. Our experiment results show that the RNN model provides accurate performance compared to the state-of-the-art methods in classifying the fundamental movement patterns with an overall accuracy of 84.89% and an overall F1-score of 82.56%. The results indicate that our method provides the medical doctors and trainers a promising way to track and understand a patient’s physical activities precisely for better treatment. View Full-Text
Keywords: classification; deep learning; health; machine learning; accelerometer data; sensors; physical activity; feed-forward neural network; DNN; recurrent neural network; RNN; UCI classification; deep learning; health; machine learning; accelerometer data; sensors; physical activity; feed-forward neural network; DNN; recurrent neural network; RNN; UCI
Show Figures

Figure 1

MDPI and ACS Style

Nunavath, V.; Johansen, S.; Johannessen, T.S.; Jiao, L.; Hansen, B.H.; Berntsen, S.; Goodwin, M. Deep Learning for Classifying Physical Activities from Accelerometer Data. Sensors 2021, 21, 5564. https://doi.org/10.3390/s21165564

AMA Style

Nunavath V, Johansen S, Johannessen TS, Jiao L, Hansen BH, Berntsen S, Goodwin M. Deep Learning for Classifying Physical Activities from Accelerometer Data. Sensors. 2021; 21(16):5564. https://doi.org/10.3390/s21165564

Chicago/Turabian Style

Nunavath, Vimala, Sahand Johansen, Tommy S. Johannessen, Lei Jiao, Bjørge H. Hansen, Sveinung Berntsen, and Morten Goodwin. 2021. "Deep Learning for Classifying Physical Activities from Accelerometer Data" Sensors 21, no. 16: 5564. https://doi.org/10.3390/s21165564

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop