Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Aug 29;23(17):7493.
doi: 10.3390/s23177493.

Deep Learning in the Recognition of Activities of Daily Living Using Smartwatch Data

Ariany F Cavalcante  1 , Victor H de L Kunst  1 , Thiago de M Chaves  1 , Júlia D T de Souza  1 , Isabela M Ribeiro  1 , Jonysberg P Quintino  2 , Fabio Q B da Silva  1 , André L M Santos  1 , Veronica Teichrieb  1 , Alana Elza F da Gama  1   3
Affiliations

Deep Learning in the Recognition of Activities of Daily Living Using Smartwatch Data

Ariany F Cavalcante et al. Sensors (Basel). .

Abstract

The recognition of human activities (HAR) using wearable device data, such as smartwatches, has gained significant attention in the field of computer science due to its potential to provide insights into individuals' daily activities. This article aims to conduct a comparative study of deep learning techniques for recognizing activities of daily living (ADL). A mapping of HAR techniques was performed, and three techniques were selected for evaluation, along with a dataset. Experiments were conducted using the selected techniques to assess their performance in ADL recognition, employing standardized evaluation metrics, such as accuracy, precision, recall, and F1-score. Among the evaluated techniques, the DeepConvLSTM architecture, consisting of recurrent convolutional layers and a single LSTM layer, achieved the most promising results. These findings suggest that software applications utilizing this architecture can assist smartwatch users in understanding their movement routines more quickly and accurately.

Keywords: human activity recognition; neural networks; smartwatch; wearable sensor data.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
HAR architecture based on CNN [15].
Figure 2
Figure 2
Improved DeepConvLSTM architecture [25].
Figure 3
Figure 3
Sliding window representation.
See this image and copyright information in PMC

References

    1. World Health Organization . Global Status Report on Physical Activity 2022. World Health Organization; Geneva, Switzerland: 2022.
    1. Sallis J.F., Bull F., Guthold R., Heath G.W., Inoue S., Kelly P., Oyeyemi A.L., Perez L.G., Richards J., Hallal P.C. Progress in physical activity over the Olympic quadrennium. Lancet. 2016;388:1325–1336. doi: 10.1016/S0140-6736(16)30581-5. - DOI - PubMed
    1. Cheatham S.W., Stull K.R., Fantigrassi M., Motel I. The efficacy of wearable activity tracking technology as part of a weight loss program: A systematic review. J. Sports Med. Phys. Fitness. 2018;58:534–548. - PubMed
    1. Reeder B., David A. Health at hand: A systematic review of smart watch uses for health and wellness. J. Biomed. Inform. 2016;63:269–276. doi: 10.1016/j.jbi.2016.09.001. - DOI - PubMed
    1. Foster K.R., Torous J. The opportunity and obstacles for smartwatches and wearable sensors. IEEE Pulse. 2019;10:22–25. doi: 10.1109/MPULS.2018.2885832. - DOI - PubMed

LinkOut - more resources