This study investigates the intricate relationships between demographic factors and human motion patterns, employing a feature-based analysis to find variations across different population segments. By examining a diverse range of demographic variables, such as age, gender, socioeconomic status, and cultural background, we aim to identify how these factors shape and influence human movement characteristics.For this work, data is collected through wearable sensors and features are extracted form data. To find the outcomes of this study, statisticalanalysis was conducted to predict the effect of demographic factors on gender basis. The aim of this study is to provide a comprehensive understanding of the demographic influences on human motion, which can have implications for various fields, including urban planning, healthcare, and security
Introduction
Human motion is a complex reflection of biological, psychological, and social factors, closely tied to individual identity and environment. Demographics like age, gender, socioeconomic status, and culture significantly influence movement patterns, which are important for applications in healthcare, rehabilitation, urban planning, security, and robotics. Advances in wearable sensors and motion tracking allow detailed analysis of gait and physical activities, aiding in clinical diagnosis and personalized treatment.
Research highlights differences in gait related to age and cultural background, with wearable technologies playing a key role in monitoring mobility and fall risk, especially in older adults. Quantitative gait assessment facilitates effective medical interventions, while rehabilitation robotics and AI enhance motion analysis and recovery.
The study involved 51 healthy adults performing varied movements while sensors recorded data from multiple body parts. Extracted features such as gait speed and joint angles were normalized for analysis. Statistical results showed gender differences, with males generally exhibiting higher median motion values, though some females had notably high values. Age comparisons revealed that younger individuals had greater variability in movement, while older adults showed more constrained motion patterns. However, ANOVA tests indicated no statistically significant differences across age groups for key motion features.
Conclusion
This work is used to assess the effect of demographic factors on motion features and the statistical analysis contribute to establish the relation between motion feature on two constraints age and gender.The results indicate the clear distinction in motion features for male and female participants. Similarly,when compared on age bases for young, middle and old age participants, the results showclear difference in motion features. In future, work can be extended to establish the similar relations for different races and further more parameters and tests can be included to make the system more predictable.
References
[1] J. S. McPhee, D. French, D. Jackson, J. Nazroo, N. Pendleton, and H. Degens, “Physical activity in older age: perspectives for healthy ageing and frailty,” Biogerontology, vol. 17, no. 3. Springer Science+Business Media, p. 567, Mar. 02, 2016. doi: 10.1007/s10522-016-9641-0.
[2] K. K. Qin, Y. Ren, W. Shao, B. Lake, F. Privitera, and F. D. Salim, “Multiple-level Point Embedding for Solving Human Trajectory Imputation with Prediction,” ACM Transactions on Spatial Algorithms and Systems, vol. 9, no. 2, p. 1, Feb. 2023, doi: 10.1145/3582427.
[3] S. Hanisch, E. Muschter, A. Hatzipanayioti, S. Li, and T. Strufe, “Understanding Person Identification Through Gait,” Proceedings on Privacy Enhancing Technologies, vol. 2023, no. 1, p. 177, Jan. 2023, doi: 10.56553/popets-2023-0011.
[4] M. H. Zaki and T. Sayed, “Using automated walking gait analysis for the identification of pedestrian attributes,” Transportation Research Part C Emerging Technologies, vol. 48, p. 16, Sep. 2014, doi: 10.1016/j.trc.2014.08.004.
[5] F. Roggio et al., “Technological advancements in the analysis of human motion and posture management through digital devices,” World Journal of Orthopedics, vol. 12, no. 7. Springer Science+Business Media, p. 467, Jul. 15, 2021. doi: 10.5312/wjo.v12.i7.467.
[6] C. Lind, F. Abtahi, and M. Forsman, “Wearable Motion Capture Devices for the Prevention of Work-Related Musculoskeletal Disorders in Ergonomics—An Overview of Current Applications, Challenges, and Future Opportunities,” Sensors, vol. 23, no. 9. Multidisciplinary Digital Publishing Institute, p. 4259, Apr. 25, 2023. doi: 10.3390/s23094259.
[7] T. Andrade, B. Cancela, and J. Gama, “Mining Human Mobility Data to Discover Locations and Habits,” arXiv (Cornell University), Jan. 2019, doi: 10.48550/arxiv.1909.11406.
[8] L. Brognara, P. Palumbo, B. Grimm, and L. Palmerini, “Assessing Gait in Parkinson’s Disease Using Wearable Motion Sensors: A Systematic Review,” Diseases, vol. 7, no. 1. Multidisciplinary Digital Publishing Institute, p. 18, Feb. 05, 2019. doi: 10.3390/diseases7010018.
[9] A. Mannini and A. M. Sabatini, “Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers,” Sensors, vol. 10, no. 2, p. 1154, Feb. 2010, doi: 10.3390/s100201154.
[10] L. Donisi, G. Cesarelli, A. Coccia, M. Panigazzi, E. Capodaglio, and G. D’Addio, “Work-Related Risk Assessment According to the Revised NIOSH Lifting Equation: A Preliminary Study Using a Wearable Inertial Sensor and Machine Learning,” Sensors, vol. 21, no. 8, p. 2593, Apr. 2021, doi: 10.3390/s21082593.
[11] R. P. Tsachor and T. Shafir, “How Shall I Count the Ways? A Method for Quantifying the Qualitative Aspects of Unscripted Movement With Laban Movement Analysis,” Frontiers in Psychology, vol. 10, Mar. 2019, doi: 10.3389/fpsyg.2019.00572.
[12] G. Rau, C. Disselhorst?Klug, and R. Schmidt, “Movement biomechanics goes upwards: from the leg to the arm,” Journal of Biomechanics, vol. 33, no. 10. Elsevier BV, p. 1207, Oct. 01, 2000. doi: 10.1016/s0021-9290(00)00062-2.
[13] S. Pedell, A. Borda, A. Keirnan, and N. Aimers, “Combining the Digital, Social and Physical Layer to Create Age-Friendly Cities and Communities,” International Journal of Environmental Research and Public Health, vol. 18, no. 1, p. 325, Jan. 2021, doi: 10.3390/ijerph18010325.
[14] I. Requelo-Rodríguez, A. Castro-Méndez, A. M. Jiménez?Cebrián, M. L. González-Elena, I. C. Palomo-Toucedo, and M. Pabón?Carrasco, “Assessment of Selected Spatio-Temporal Gait Parameters on Subjects with Pronated Foot Posture on the Basis of Measurements Using OptoGait. A Case-Control Study,” Sensors, vol. 21, no. 8, p. 2805, Apr. 2021, doi: 10.3390/s21082805.
[15] A. Saboor et al., “Latest Research Trends in Gait Analysis Using Wearable Sensors and Machine Learning: A Systematic Review,” IEEE Access, vol. 8. Institute of Electrical and Electronics Engineers, p. 167830, Jan. 01, 2020. doi: 10.1109/access.2020.3022818.
[16] S. Yamada et al., “Quantitative Gait Feature Assessment on Two-Dimensional Body Axis Projection Planes Converted from Three-Dimensional Coordinates Estimated with a Deep Learning Smartphone App,” Sensors, vol. 23, no. 2, p. 617, Jan. 2023, doi: 10.3390/s23020617.
[17] Q. Zhang et al., “Wearable Triboelectric Sensors Enabled Gait Analysis and Waist Motion Capture for IoT?Based Smart Healthcare Applications,” Advanced Science, vol. 9, no. 4, Nov. 2021, doi: 10.1002/advs.202103694.
[18] T. Bao et al., “A global bibliometric and visualized analysis of gait analysis and artificial intelligence research from 1992 to 2022,” Frontiers in Robotics and AI, vol. 10, Nov. 2023, doi: 10.3389/frobt.2023.1265543.
[19] W. Tao, T. Liu, R. Zheng, and H.-T. Feng, “Gait Analysis Using Wearable Sensors,” Sensors, vol. 12, no. 2. Multidisciplinary Digital Publishing Institute, p. 2255, Feb. 16, 2012. doi: 10.3390/s120202255.
[20] S. Gupta, V. Aggarwal. MS Patterh, L. Singh, “Analysis of Foetal Phonocardiography and Clinical Outcomes: A Data-Driven Analysis Using IISc Database”, International Research Journal of Modernization in Engineering Technology and Science, Volume:07, Issue:03, March-2025, pp-7864-7867. doi.10.56726/IRJMETS70309.
[21] S. Gupta, V. Aggarwal, M. Patterh, and L. Singh, “Quantitative Analysis of Electrohysterogram Features for Pregnancy Monitoring,” International Research Journal of Innovations in Engineering and Technology (IRJIET) vol 9 (4), pp 12-15, April-2025, doi:doi.org/10.47001/IRJIET/2025.904002, ISSN (online): 2581-3048.
[22] S. Gupta, V. Aggarwal, M. Patterh, and L. Singh, “Automated Feature Extraction and Classification of Foetal Phonocardiogram Signals Using Time-Frequency Analysis and Machine Learning,” International Journal of Engineering Research And Development (IJERD) e- ISSN: 2278-067X, p-ISSN: 2278-800X, vol. 21 (4) April 2025, PP 227-232.
[23] https://physionet.org/content/accelerometry-walk-climb-drive/1.0.0/