Gait Variability and Phase Segmentation in Obese and Normal Individuals Using Multi-Location IMUs and Hidden Markov Models Supervised Marginal
Downloads
Obesity is known to disrupt motor control and biomechanics; however, detailed gait alterations in individuals with obesity remain underexplored, particularly in dynamic and real-world walking conditions. This study aims to quantitatively characterize gait differences between individuals with obesity and those of normal weight by analyzing postural and temporal gait parameters. The investigation focuses on pitch, roll, and cadence dynamics using body-worn inertial sensors, with phase transition modeling via Hidden Markov Models. This work proposes a novel framework that integrates multi-location Inertial Measurement Unit (IMU) sensors and a Hidden Markov Model–Supervised Marginal (HMM-SM) approach to detect and classify gait phases with high accuracy, offering practical value for clinical gait assessment and personalized rehabilitation. IMU sensors were placed on the waist, thigh, calf, and heel to record gait data from participants in both obese and normal-weight groups. Gait segmentation and phase modeling were conducted using 4-, 5-, and 8-state HMMs. Quantitative analysis revealed significantly greater postural variability in the obese group during slow walking, with standard deviations in roll and pitch reaching 20.68° and 9.23°, respectively—much higher than the normal-weight group (0.60° and 0.26°). Hidden state transitions from 5-state pitch HMMs showed a very strong effect size for the obese group (Cramér’s V = 0.72) compared to a moderate effect for the normal-weight group (V = 0.33). Similar patterns were observed for roll and cadence. In terms of segmentation accuracy, the 4- and 5-state HMMs outperformed the 8-state model, achieving accuracy levels above 99%, while the 8-state model reached only ~93%. The findings demonstrate that obesity significantly alters gait dynamics, particularly in postural stability and gait phase transitions. The proposed IMU-based HMM-SM framework effectively captures these changes, offering a reliable tool for gait analysis in clinical and biomechanical applications.
[1] J. L. Perez-Lasierra, M. Azpíroz-Puente, J. V. Alfaro-Santafé, A. J. Almenar-Arasanz, J. Alfaro-Santafé, and A. Gómez-Bernal, “Sarcopenia screening based on the assessment of gait with inertial measurement units: a systematic review,” BMC Geriatr, vol. 24, no. 1, Dec. 2024, doi: 10.1186/s12877-024-05475-3.
[2] W. Tao, T. Liu, R. Zheng, and H. Feng, “Gait analysis using wearable sensors,” Feb. 2012. doi: 10.3390/s120202255.
[3] A. Kharb, V. Saini, Y. K. Jain, and S. Dhiman, “A review of gait cycle and its parameters,” 2011. [Online]. Available: www.IJCEM.orgIJCEMwww.ijcem.org
[4] M. B. del Rosario, S. J. Redmond, and N. H. Lovell, “Tracking the evolution of smartphone sensing for monitoring human movement,” Jul. 31, 2015, MDPI AG. doi: 10.3390/s150818901.
[5] R. Monfrini, G. Rossetto, E. Scalona, M. Galli, V. Cimolin, and N. F. Lopomo, “Technological Solutions for Human Movement Analysis in Obese Subjects: A Systematic Review,” Mar. 01, 2023, MDPI. doi: 10.3390/s23063175.
[6] J. B. Dingwell and L. C. Marin, “Kinematic variability and local dynamic stability of upper body motions when walking at different speeds,” J Biomech, vol. 39, no. 3, pp. 444–452, 2006, doi: 10.1016/j.jbiomech.2004.12.014.
[7] G. Prisco et al., “Validity of Wearable Inertial Sensors for Gait Analysis: A Systematic Review,” Jan. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/diagnostics15010036.
[8] S. K. Manna, M. A. Hannan Bin Azhar, and A. Greace, “Optimal locations and computational frameworks of FSR and IMU sensors for measuring gait abnormalities,” Apr. 01, 2023, Elsevier Ltd. doi: 10.1016/j.heliyon.2023.e15210.
[9] Y. He et al., “Accuracy validation of a wearable IMU-based gait analysis in healthy female,” BMC Sports Sci Med Rehabil, vol. 16, no. 1, Dec. 2024, doi: 10.1186/s13102-023-00792-3.
[10] A. Muro-de-la-Herran, B. García-Zapirain, and A. Méndez-Zorrilla, “Gait analysis methods: An overview of wearable and non-wearable systems, highlighting clinical applications,” Feb. 19, 2014. doi: 10.3390/s140203362.
[11] S. Lin et al., “A Review of Gait Analysis Using Gyroscopes and Inertial Measurement Units,” Jun. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/s25113481.
[12] A. Khumar and B. Kumar, “SVM based Multiclass Classifier for Gait phase Classification using Shank IMU Sensor,” 2017.
[13] L. Liu et al., “Ambulatory human gait phase detection using wearable inertial sensors and Hidden Markov model,” Sensors (Switzerland), vol. 21, no. 4, pp. 1–24, Feb. 2021, doi: 10.3390/s21041347.
[14] M. Sánchez-Manchola, L. Arciniegas-Mayag, M. Múnera, M. Bourgain, T. Provot, and C. A. Cifuentes, “Effects of stance control via hidden Markov model-based gait phase detection on healthy users of an active hip-knee exoskeleton,” Front Bioeng Biotechnol, vol. 11, 2023, doi: 10.3389/fbioe.2023.1021525.
[15] M. D. S. Manchola, M. J. P. Bernal, M. Munera, and C. A. Cifuentes, “Gait phase detection for lower-limb exoskeletons using foot motion data from a single inertial measurement unit in hemiparetic individuals,” Sensors (Switzerland), vol. 19, no. 13, Jul. 2019, doi: 10.3390/s19132988.
[16] Y. Wang, Q. Song, T. Ma, N. Yao, R. Liu, and B. Wang, “Research on Human Gait Phase Recognition Algorithm Based on Multi-Source Information Fusion,” Electronics (Switzerland), vol. 12, no. 1, Jan. 2023, doi: 10.3390/electronics12010193.
[17] G. Ng and J. Andrysek, “Hidden Markov model-based similarity measure (HMM-SM) for gait quality assessment of lower-limb prosthetic users using inertial sensor signals,” J Neuroeng Rehabil, vol. 22, no. 1, Dec. 2025, doi: 10.1186/s12984-025-01638-4.
[18] S. Sharif Bidabadi, I. Murray, and G. Y. F. Lee, “Validation of foot pitch angle estimation using inertial measurement unit against marker-based optical 3D motion capture system,” Biomed Eng Lett, vol. 8, no. 3, pp. 283–290, Aug. 2018, doi: 10.1007/s13534-018-0072-5.
[19] J. Taborri, S. Rossi, E. Palermo, F. Patanè, and P. Cappa, “A novel HMM distributed classifier for the detection of gait phases by means of a wearable inertial sensor network,” Sensors (Switzerland), vol. 14, no. 9, pp. 16212–16234, Sep. 2014, doi: 10.3390/s140916212.
[20] S. Lee, C. Park, E. Ha, J. Hong, S. H. Kim, and Y. Kim, “Determination of Spatiotemporal Gait Parameters Using a Smartphone’s IMU in the Pocket: Threshold-Based and Deep Learning Approaches,” Sensors, vol. 25, no. 14, p. 4395, Jul. 2025, doi: 10.3390/s25144395.
[21] L. Tang, M. Shushtari, and A. Arami, “IMU-Based Real-Time Estimation of Gait Phase Using Multi-Resolution Neural Networks,” Sensors, vol. 24, no. 8, Apr. 2024, doi: 10.3390/s24082390.
[22] R. Stenger, H. H. Pour, J. Teich, A. Hein, and S. Fudickar, “Gait Parameters Estimation from Sensor-Belt IMU Data,” Jul. 30, 2024. doi: 10.36227/techrxiv.172235876.62229016/v1.
[23] T. Liu, Y. Inoue, and K. Shibata, “Development of a wearable sensor system for quantitative gait analysis,” Measurement (Lond), vol. 42, no. 7, pp. 978–988, Aug. 2009, doi: 10.1016/j.measurement.2009.02.002.
[24] V. S., H. A.S, and J. S. Sundar, “CHI-SQUARE TESTS: A QUICK GUIDE FOR HEALTH RESEARCHERS,” Int J Adv Res (Indore), vol. 12, no. 10, pp. 1214–1222, Oct. 2024, doi: 10.21474/IJAR01/19746.
[25] M. L. McHugh, “The Chi-square test of independence,” Biochem Med (Zagreb), vol. 23, no. 2, pp. 143–149, 2013, doi: 10.11613/BM.2013.018.
[26] A. Phinyomark, R. N. Khushaba, and E. Scheme, “Feature extraction and selection for myoelectric control based on wearable EMG sensors,” Sensors (Switzerland), vol. 18, no. 5, May 2018, doi: 10.3390/s18051615.
[27] W. Caesarendra and T. Tjahjowidodo, “A review of feature extraction methods in vibration-based condition monitoring and its application for degradation trend estimation of low-speed slew bearing,” Dec. 01, 2017, MDPI AG. doi: 10.3390/machines5040021.
[28] V. Suvorkin, M. Garcia-Fernandez, G. González-Casado, M. Li, and A. Rovira-Garcia, “Assessment of Noise of MEMS IMU Sensors of Different Grades for GNSS/IMU Navigation,” Sensors, vol. 24, no. 6, Mar. 2024, doi: 10.3390/s24061953.
[29] A. M. Sabatini, “Estimating three-dimensional orientation of human body parts by inertial/magnetic sensing,” Feb. 2011. doi: 10.3390/s110201489.
[30] A. J. L. H. R. V. Sebastian O.H. Madgwick, Estimation of IMU and MARG orientation using a gradient descent algorithm. IEEE, 2011.
[31] J. S. Sheu, W. C. Jheng, and C. H. Hsiao, “Implementation of a three-dimensional pedometer automatic accumulating walking or jogging motions in arbitrary placement,” Int J Antennas Propag, vol. 2014, 2014, doi: 10.1155/2014/372814.
[32] R. A. Brindle, J. B. Taylor, C. Rajek, A. Weisbrod, and K. R. Ford, “Association Between Temporal Spatial Parameters and Overuse Injury History in Runners: A Systematic Review and Meta-analysis,” Feb. 01, 2020, Springer. doi: 10.1007/s40279-019-01207-5.
[33] C. Voisard, N. de l’Escalopier, D. Ricard, and L. Oudre, “Automatic gait events detection with inertial measurement units: healthy subjects and moderate to severe impaired patients,” J Neuroeng Rehabil, vol. 21, no. 1, Dec. 2024, doi: 10.1186/s12984-024-01405-x.
[34] A. Yamashita et al., “Harmonization of resting-state functional MRI data across multiple imaging sites via the separation of site differences into sampling bias and measurement bias,” PLoS Biol, vol. 17, no. 4, 2019, doi: 10.1371/journal.pbio.3000042.
[35] J. Rekant, S. Rothenberger, and A. Chambers, “Obesity-Specific Considerations for Assessing Gait with Inertial Measurement Unit-Based vs. Optokinetic Motion Capture,” Sensors, vol. 24, no. 4, Feb. 2024, doi: 10.3390/s24041232.
[36] C. W. Frames et al., “Dynamical properties of postural control in obese community-dwelling older adults,” Sensors (Switzerland), vol. 18, no. 6, Jun. 2018, doi: 10.3390/s18061692.
[37] M. Pau, P. Capodaglio, B. Leban, M. Porta, M. Galli, and V. Cimolin, “Kinematics adaptation and inter-limb symmetry during gait in obese adults,” Sensors, vol. 21, no. 17, Sep. 2021, doi: 10.3390/s21175980.
[38] B. Bogen, R. Moe-Nilssen, M. K. Aaslund, and A. H. Ranhoff, “Muscle Strength as a Predictor of Gait Variability after Two Years in Community-Living Older Adults,” Journal of Frailty and Aging, vol. 9, no. 1, pp. 23–29, Jan. 2020, doi: 10.14283/jfa.2019.24.
[39] M. Reina-Bueno et al., “Effect of foot orthoses and shoes in parkinson’s disease patients: A prisma systematic review,” Nov. 01, 2021, MDPI. doi: 10.3390/jpm11111136.
[40] A. L. Simon, V. Lugade, K. Bernhardt, A. N. Larson, and K. Kaufman, “Assessment of stability during gait in patients with spinal deformity—A preliminary analysis using the dynamic stability margin,” Gait Posture, vol. 55, pp. 37–42, Jun. 2017, doi: 10.1016/j.gaitpost.2017.03.036.
[41] T. E. Lockhart, C. W. Frames, R. Soangra, and A. Lieberman, “Effects of Obesity and Fall Risk on Gait and Posture of Community-Dwelling Older Adults.”
[42] O. Hue et al., “Body weight is a strong predictor of postural stability,” Gait Posture, vol. 26, no. 1, pp. 32–38, Jun. 2007, doi: 10.1016/j.gaitpost.2006.07.005.
[43] G. Ng, A. Gouda, and J. Andrysek, “Quantifying Asymmetric Gait Pattern Changes Using a Hidden Markov Model Similarity Measure (HMM-SM) on Inertial Sensor Signals,” Sensors, vol. 24, no. 19, Oct. 2024, doi: 10.3390/s24196431.
[44] G. Ng and J. Andrysek, “Hidden Markov model-based similarity measure (HMM-SM) for gait quality assessment of lower-limb prosthetic users using inertial sensor signals,” J Neuroeng Rehabil, vol. 22, no. 1, Dec. 2025, doi: 10.1186/s12984-025-01638-4.
Copyright (c) 2025 Suto Setiyadi, Husneni Mukhtar , Willy Anugrah Cahyadi, Diyah Widiyasari, Mohamad Ramdhani, Nigel Bryan Tang (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
