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
. 2020 Apr 24;20(8):2424.
doi: 10.3390/s20082424.

Wearable Sensor-Based Gait Analysis for Age and Gender Estimation

Md Atiqur Rahman Ahad  1   2 , Thanh Trung Ngo  1 , Anindya Das Antar  3 , Masud Ahmed  2 , Tahera Hossain  4 , Daigo Muramatsu  1 , Yasushi Makihara  1 , Sozo Inoue  4 , Yasushi Yagi  1
Affiliations

Wearable Sensor-Based Gait Analysis for Age and Gender Estimation

Md Atiqur Rahman Ahad et al. Sensors (Basel). .

Abstract

Wearable sensor-based systems and devices have been expanded in different application domains, especially in the healthcare arena. Automatic age and gender estimation has several important applications. Gait has been demonstrated as a profound motion cue for various applications. A gait-based age and gender estimation challenge was launched in the 12th IAPR International Conference on Biometrics (ICB), 2019. In this competition, 18 teams initially registered from 14 countries. The goal of this challenge was to find some smart approaches to deal with age and gender estimation from sensor-based gait data. For this purpose, we employed a large wearable sensor-based gait dataset, which has 745 subjects (357 females and 388 males), from 2 to 78 years old in the training dataset; and 58 subjects (19 females and 39 males) in the test dataset. It has several walking patterns. The gait data sequences were collected from three IMUZ sensors, which were placed on waist-belt or at the top of a backpack. There were 67 solutions from ten teams-for age and gender estimation. This paper extensively analyzes the methods and achieved-results from various approaches. Based on analysis, we found that deep learning-based solutions lead the competitions compared with conventional handcrafted methods. We found that the best result achieved 24.23% prediction error for gender estimation, and 5.39 mean absolute error for age estimation by employing angle embedded gait dynamic image and temporal convolution network.

Keywords: age estimation; gait; gender; recognition; smartphone; wearable sensor.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Setup of the sensor-based human gait data capturing system: (a) Waist-belt (uncovered) having three IMUZ sensors; (b) three axes of a typical IMUZ sensor; (c) Sensors’ attachment at left, right, and center-back position; and (d) Real data collection image, where a subject is wearing a belt, and flat ground, stairs and slope are highlighted in the environment. (This Figure was previously published in [17] as Figure 8. Hence, it is reprinted from [17], Copyright (2015), with permission from Elsevier).
Figure 2
Figure 2
Distribution of subjects in training dataset—by age group and gender. The histogram demonstrates a non-uniform distribution of age groups though the distributions of both sexes are almost equally distributed.
Figure 3
Figure 3
An example of sensor orientation inconsistency: within and among subjects.
Figure 4
Figure 4
An example of three IMUZ sensors in the backpack for the test dataset. The sensors are attached to the top of the backpack.
Figure 5
Figure 5
Distribution of subjects in test dataset—by age group and gender. The histogram demonstrates a much non-uniform distribution of age groups and gender than the training dataset.
Figure 6
Figure 6
Examples of test signal sequences for gyroscope data, and accelerometer data.
Figure 7
Figure 7
Examples of accelerometer data that appear only in testing.
Figure 8
Figure 8
Gender prediction results for the 10 teams.
Figure 9
Figure 9
Top 10 algorithms, irrespective of any team to predict errors for gender estimation. ‘T’ stands for ‘Team’ and ‘A’ stands for ‘Algorithm’.
Figure 10
Figure 10
Comparison of different algorithms by teams in terms of the distribution of prediction error for gender estimation.
Figure 11
Figure 11
Age prediction results by age groups for the 10 teams.
Figure 12
Figure 12
Top 10 algorithms, irrespective of any team for age prediction results by age groups. ‘T’ stands for ‘Team’ and ‘A’ stands for ‘Algorithm’.
Figure 13
Figure 13
Comparison of different algorithms by teams in terms of the distribution of prediction error for age estimation.
See this image and copyright information in PMC

References

    1. Ageing and Health World Health Organization. [(accessed on 10 January 2020)]; Available online: www.who.int/news-room/fact-sheets/detail/ageing-and-health.
    1. Mosa A., Yoo I., Sheets L. A systematic review of healthcare applications for smartphones. BMC Med. Inf. Decis. Mak. 2012;12:67. doi: 10.1186/1472-6947-12-67. - DOI - PMC - PubMed
    1. Ahad M.A.R., Antar A.D., Shahid O. Vision-based Action Understanding for Assistive Healthcare: A Short Review; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops; Long Beach, CA, USA. 16–20 June 2019; pp. 1–11.
    1. Islam S.M.R., Kwak M.D., Kabir H., Hossain M., Kwak K.-S. The Internet of Things for Health Care: A Comprehensive Survey. IEEE Access. 2015;3:678–708. doi: 10.1109/ACCESS.2015.2437951. - DOI
    1. Elkholy A., Makihara Y., Gomaa W., Ahad M.A.R., Yagi Y. Unsupervised GEI-Based Gait Disorders Detection From Different Views; Proceedings of the 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’19); Berlin, Germany. 23–27 July 2019. - PubMed

LinkOut - more resources