Walking-Age Estimator Based on Gait Parameters Using Kernel Regression
Source abstract
Abstract
Human gait motions differ depending on the age of the person. Previous studies have estimated age categories of walkers or have used age analysis for security or commercial surveillance purposes using images. However, few studies have estimated age from gait parameters alone. We estimated the age of people using kernel regression analysis based on their height, weight, and representative gait parameters, i.e., walking features that are interpretable with relative ease. Samples were obtained from 75 Japanese women aged 20–70 in a database. Through a variable selection based on sensitivity analysis, the established model estimated the ages of the women with a correlation coefficient of 0.78 with their actual ages, and the mean absolute error was 9.99 years. The sensitive variables included the minimum foot clearance, body weight, walking velocity, step width, and stride length. Estimation errors were significantly greater for elderly adults than for young people. Specifically, the mean absolute error for people in their 20s was 7.4 years, whereas that for those over 60 was 13.1 years. The proposed method uses gait parameters that can be measured with wearable devices, such as inertial measurement units; therefore, it offers an accessible approach to estimating a walker’s age with moderate certainty and promoting healthcare awareness in daily life.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Gait Recognition and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science, Tokyo Metropolitan University, Hino 191-0065, Japan
Faculty of Textile Science and Technology, Shinshu University, 3-15-1 Tokida, Ueda 386-8567, Japan
Funding
The Okawa Foundation for Information and Telecommunications
References (63)
Show source-provided references
1. Age-associated differences in the gait pattern changes of older adults during fast-speed and fatigue conditions: Results from the Baltimore longitudinal study of ageing10.1093/ageing/afq113 ↗
2. Age causes a redistribution of joint torques and powers during gait10.1152/jappl.2000.88.5.1804 ↗
3. The effect of aging on gait parameters in able-bodied older subjects: A literature review10.1007/s40520-015-0420-6 ↗
4. Normative spatiotemporal gait parameters in older adults10.1016/j.gaitpost.2011.03.024 ↗
5. Gait variability among healthy adults: Low and high stride-to-stride variability are both a reflection of gait stability10.1159/000235905 ↗
6. The effect of lateral stabilization on walking in young and old ddults10.1109/TBME.2007.901031 ↗
7. Differences in gait parameters at a preferred walking speed in healthy subjects due to age, height and body weight
8. Age-related differences in walking stability10.1093/ageing/32.2.137 ↗
9. Age-related mechanical work expenditure during normal walking: The Baltimore longitudinal study of aging10.1016/j.jbiomech.2009.05.037 ↗
10. A comparison of treadmill and overground walking effects on step cycle asymmetry in young and older individuals10.1123/jab.29.2.188 ↗
11. Effects of age-related gait changes on the biomechanics of slips and falls10.1080/0014013031000139491 ↗
12. Yamaguchi, T., and Masani, K. (2022). Effects of age on dynamic balance measures and their correlation during walking across the adult lifespan. Sci. Rep., 12.10.1038/s41598-022-18382-7 ↗
13. Kuroda, T., Okamoto, S., and Akiyama, Y. (2023). Anterior and mediolateral dynamic gait stabilities attributed to different gait parameters in different age groups. J. Biomech. Sci. Eng., 19.10.1299/jbse.23-00183 ↗
14. Antonelli, M., Caselli, E., and Gastaldi, L. (2024). Comparison of gait smoothness metrics in healthy elderly and young people. Appl. Sci., 14.10.3390/app14020911 ↗
15. Manipulability analysis of anterior and mediolateral dynamic gait stability of young and elderly individuals10.20965/jrm.2024.p1568 ↗
16. Davoudi, M., Salami, F., Putz, C., and Wolf, S.I. (2025). Establishing reference data for electromyographic activity in gait: Age and gender variations. Appl. Sci., 15.10.20944/preprints202502.1541.v1 ↗
17. A new method proposed for realizing human gait pattern recognition: Inspirations for the application of sports and clinical gait analysis10.1016/j.gaitpost.2023.10.019 ↗
18. Kim, M.J., Han, J.H., Shin, W.C., and Hong, Y.S. (2024). Gait pattern identification using gait features. Electronics, 13.10.3390/electronics13101956 ↗
19. Slemenšek, J., Fister, I., Geršak, J., Bratina, B., van Midden, V.M., Pirtošek, Z., and Šafarič, R. (2023). Human gait activity recognition machine learning methods. Sensors, 23.10.3390/s23020745 ↗
20. Ejaz, N., Khan, S.J., Azim, F., Asif, M., Teuțan, E., Pleșa, A., Păcurar, R., and Stan, S.D. (2024). Automatic gait classification model empowered by machine learning for people with and without osteoporosis using smart walker. Appl. Sci., 14.10.3390/app14093874 ↗
21. Core challenges of social robot navigation: A survey10.1145/3583741 ↗
22. A survey on socially aware robot navigation: Taxonomy and future challenges10.1177/02783649241230562 ↗
23. Support vector machines for automated gait classification10.1109/TBME.2005.845241 ↗
24. Gait-based human age classification using a silhouette model10.1049/iet-bmt.2016.0176 ↗
25. Davis, J.W. (2003, January 9–11). Visual categorization of children and adult walking styles. Proceedings of the Audio- and Video-Based Biometric Person Authentication: 4th International Conference, AVBPA 2003, Guildford, UK.
26. Zhang, D., Wang, Y., and Bhanu, B. (2010, January 23–26). Age classification base on gait using HMM. Proceedings of the 20th International Conference on Pattern Recognition, Istanbul, Turkey.10.1109/ICPR.2010.934 ↗
27. Chuen, B.K.Y., Tee, C., Ong, T.S., and Ong, M.G.K. (2015, January 16–19). A preliminary study of gait-based age estimation techniques. Proceedings of the 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), Hong Kong, China.
28. Kumar, D., and Malhotra, A. (2024, January 15–16). Age estimation from gait patterns using a Convolutional Neural Network and Support Vector Machine hybrid model. Proceedings of the 2024 International Conference on Cybernation and Computation (CYBERCOM), Dehradun, India.
29. Makihara, Y., Okumura, M., Iwama, H., and Yagi, Y. (2011, January 11–13). Gait-based age estimation using a whole-generation gait database. Proceedings of the 2011 International Joint Conference on Biometrics (IJCB), Washington, DC, USA.10.1109/IJCB.2011.6117531 ↗
30. Gait-based human age estimation using age group-dependent manifold learning and regression10.1007/s11042-018-6049-7 ↗
31. Gait-based age estimation using multi-stage convolutional neural network10.1186/s41074-019-0054-2 ↗
32. Ahad, M., Ngo, T., Antar, A., Ahmed, M., Hossain, T., Muramatsu, D., Makihara, Y., Inoue, S., and Yagi, Y. (2020). Wearable sensor-based gait analysis for age and gender estimation. Sensors, 20.10.3390/s20082424 ↗
33. Kuroda, T., Okamoto, S., and Akiyama, Y. (2023, January 10–13). Walking-age estimator based on gait parameters. Proceedings of the 2023 IEEE 12th Global Conference on Consumer Electronics (GCCE), Nara, Japan.10.1109/GCCE59613.2023.10315529 ↗
34. Annotation generation from IMU-based human whole-body motions in daily life behavior10.1109/THMS.2019.2960630 ↗
35. A wearable activity recognition device using air-pressure and IMU sensors10.1109/ACCESS.2018.2890004 ↗
36. Learning sensor interdependencies for IMU-to-segment assignment10.1109/ACCESS.2021.3105801 ↗
37. Overview of Lifelogging: Current Challenges and Advances10.1109/ACCESS.2021.3073469 ↗
38. Huang, M., and Garcia, A. (2023). Dataset and system design for orthopedic walker fall detection and activity logging using motion classification. Appl. Sci., 13.10.3390/app132011379 ↗
39. Oh, H., and Yoo, J. (2025). Real-time detection of at-risk movements using smartwatch IMU sensors. Appl. Sci., 15.10.3390/app15041842 ↗
40. Effects of walking speed and age on the directional stride regularity and gait variability in treadmill walking10.1007/s12206-016-0549-z ↗
41. Inertial sensor based reference gait data for healthy subjects10.1016/j.gaitpost.2011.02.023 ↗
42. Teufl, W., Lorenz, M., Miezal, M., Taetz, B., Fröhlich, M., and Bleser, G. (2019). Towards inertial sensor based mobile gait analysis: Event-detection and spatio-temporal parameters. Sensors, 19.10.3390/s19225006 ↗
43. Verification of the effectiveness of sensitivity analysis as a variable selection in support vector regression—analysis of factors affecting prefectural all-cause mortality rates
44. Kobayashi, Y., Hida, N., Nakajima, K., Fujimoto, M., and Mochimaru, M. (2025, February 01). AIST Gait Database 2019. Available online: https://unit.aist.go.jp/harc/ExPART/GDB2019.html.
45. Age-independent and age-dependent sex differences in gait pattern determined by principal component analysis10.1016/j.gaitpost.2016.01.021 ↗
46. G*Power 3: A flexible statistical power analysis program for the social, behavioral, and biomedical sciences10.3758/BF03193146 ↗
47. Al Bochi, A., Delfi, G., and Dutta, T. (2021). A scoping review on minimum foot clearance: An exploration of level-ground clearance in individuals with abnormal gait. Int. J. Environ. Res. Public Health, 18.10.3390/ijerph181910289 ↗
48. Minimum toe clearance events in divided attention treadmill walking in older and young adults: A cross-sectional study10.1186/s12984-015-0052-2 ↗
49. Factors affecting minimum foot flearance in the elderly walking: A multiple regression analysis10.4236/ojtr.2015.34015 ↗
50. Carter, S., and Saghafi, A. (J. Appl. Biomech., 2025). An exploration of the effects of gait speed and joint movements on minimum toe clearance across the lifespan: A cross-sectional study, J. Appl. Biomech., ahead of print.10.1123/jab.2024-0288 ↗
51. The effects of age on medio-lateral stability during normal and narrow base walking10.1016/j.gaitpost.2008.02.009 ↗
52. A systematic review of the effect of ageing and falls history on minimum foot clearance characteristics during level walking10.1016/j.gaitpost.2010.07.010 ↗
53. Inai, T., Kobayashi, Y., Huang, C., Fujita, K., Fujimoto, M., Nihey, F., Yamamoto, A., Nakajima, K., Nakahara, K., and Kutsuzawa, G. (2023). Identification of characteristics of foot position and angle during swing phase in fallers using principal component analysis. Front. Bioeng. Biotechnol., 11.10.3389/fbioe.2023.1117884 ↗
54. Combined effects of age and gender on gait symmetry and regularity assessed by autocorrelation of trunk acceleration10.1186/1743-0003-11-109 ↗
55. Gender differences in three dimensional gait analysis data from 98 healthy Korean adults10.1016/j.clinbiomech.2003.10.003 ↗
56. Pedestrian gait analysis using automated computer vision techniques
57. Saxe, R.C., Kappagoda, S., and Mordecai, D.K.A. (2020). Classification of pathological and normal gait: A survey. arXiv.
58. Multimodal gait recognition for neurodegenerative diseases10.1109/TCYB.2021.3056104 ↗
59. Effect of severity of knee osteoarthritis on the variability of gait parameters10.1016/j.jelekin.2011.07.011 ↗
60. Gait variability and motor control in people with knee osteoarthritis10.1016/j.gaitpost.2015.07.063 ↗
61. Effect of different types of footwear on gait pattern—A scoping review
62. Riglet, L., Nicol, F., Leonard, A., Eby, N., Claquesin, L., Orliac, B., Ornetti, P., Laroche, D., and Gueugnon, M. (2023). The use of embedded IMU insoles to assess gait parameters: A validation and test-retest reliability study. Sensors, 23.10.3390/s23198155 ↗
63. Napier, C., Willy, R.W., Hannigan, B.C., McCann, R., and Menon, C. (2021). The effect of footwear, running speed, and location on the validity of two commercially available inertial measurement units during running. Front. Sport. Act. Living, 3.10.3389/fspor.2021.643385 ↗