Multimodal Gait Analysis Using IMU and EMG Sensors with HMM Classification to Differentiate Obese and Normal Body Types

Suto Setiyadi; Muhammad Ridho Rosa; Nigel Bryan Tang; Muhammad Sabiq Al Muttaqin; Muhammad Rafi Haykal Gumelar

doi:10.56741/jnest.v4i03.1272

Multimodal Gait Analysis Using IMU and EMG Sensors with HMM Classification to Differentiate Obese and Normal Body Types

Authors

Suto Setiyadi Telkom University https://orcid.org/0009-0007-4093-3832
Muhammad Ridho Rosa Telkom University https://orcid.org/0000-0003-4941-0644
Nigel Bryan Tang Telkom University
Muhammad Sabiq Al Muttaqin Telkom University
Muhammad Rafi Haykal Gumelar Telkom University

DOI:

https://doi.org/10.56741/jnest.v4i03.1272

Keywords:

Gait Analysis, Electromyography (EMG), Inertial Measurement Unit (IMU), Obese, Hidden Markov Model (HMM), Wearable Sensor

Abstract

Gait analysis is essential for diagnosing movement disorders and monitoring rehabilitation progress; conventional methods are often costly and complex. This study aims to differentiate gait characteristics between individuals with obesity and those with normal body composition using a multimodal approach that integrates Inertial Measurement Unit (IMU) and electromyography (EMG) sensors. Data were collected from ten male participants (five classified as obese and five with normal body composition). IMU sensors were used to measure acceleration, angular velocity, and step count, while EMG sensors recorded muscle activity from the tibialis anterior and gastrocnemius muscles. We developed a real-time acquisition using ESP32 microcontrollers and Bluetooth Low Energy (BLE), and gait phase classification was performed using the Hidden Markov Model (HMM). Using heel-mounted sensors, the average step detection error ranged from 2.5% to 3.6%. IMU signals from obese participants indicated a shift in dominant gait phase from Initial Contact during slow walking to Loading Response during fast walking, with relative errors up to 27%. In contrast, participants with normal body composition exhibited more diverse and accurate phase distributions. EMG-based analysis provided more precise segmentation (with error rates as low as 0.47%). It revealed distinct muscle activation patterns: gastrocnemius activity was dominant during the Midswing or Midstance phases, while tibialis anterior activity peaked during Initial Contact, Initial Swing, or Loading Response. These findings suggest body composition significantly affects gait stability, phase transitions, and muscle activation patterns. Future work should explore advanced machine learning algorithms such as Long Short-Term Memory (LSTM) or Convolutional Neural Networks (CNN), integrate pressure sensors, and validate the system in real-world environments to enhance accuracy and reliability.

Downloads

Download data is not yet available.

Author Biographies

Suto Setiyadi, Telkom University

Suto Setiyadi obtained his Bachelor of Engineering (S.T.) degree from Telkom University in 2021 and subsequently received his Master of Engineering (M.T.) degree from the same university in 2023. His research activities began at the Microprocessor and Interface Laboratory and the Electronics Laboratory. After completing his undergraduate studies, he worked as a research assistant at Bandung Techno Park. Following his master's graduation, he continued his academic career as a lecturer and researcher at the School of Electrical Engineering, Telkom University, Indonesia.

He authorises the textbook Sensor and Actuator with the Cases of Implementation (Tel-U Press, 2022). His primary research interests include biomedical applications of computer vision and embedded systems.

Muhammad Ridho Rosa, Telkom University

Muhammad Ridho Rosa is a lecturer and researcher at Telkom University, Indonesia. He earned his bachelor’s degree in electrical engineering and continued his advanced research in adaptive control systems and multi-agent systems. His research interests include embedded systems, wireless sensors, biomedical signal analysis—particularly EMG and IMU signals—and the application of machine learning in human movement analysis and rehabilitation. He is also actively involved in the development of adaptive control systems for agent formation and EMG-based wearable devices to support therapy and patient monitoring. His works have been published in reputable international journals and conferences, and he has engaged in collaborative research with international institutions, including the University of Groningen, the Netherlands. Through a multidisciplinary approach, he continues to develop efficient portable technologies for healthcare applications and intelligent rehabilitation systems.

Nigel Bryan Tang, Telkom University

Nigel Bryan Tang is an undergraduate student in the Electrical Engineering program at Telkom University, Indonesia. He is currently active as a laboratory assistant in the Microprocessor and Interface Laboratory, where he is involved in practical sessions, technical assistance, and the development of microcontroller-based and embedded system projects. His interests include hardware programming, embedded systems, and sensor integration for Internet of Things (IoT) and automation applications.

Muhammad Sabiq Al Muttaqin, Telkom University

Muhammad Sabiq Al Muttaqin is an undergraduate student in the Electrical Engineering program at Telkom University, Indonesia. He is currently active as a laboratory assistant in the Microprocessor and Interface Laboratory, where he assists in practical sessions and provides technical support. His research interests focus on Printed Circuit Board (PCB) design.. He is actively involved in projects related to the design of efficient and environmentally friendly electronic systems, with a particular interest in hardware integration for smart energy systems.

Muhammad Rafi Haykal Gumelar, Telkom University

Muhammad Rafi Haykal Gumelar is an undergraduate student in the Electrical Engineering program at Telkom University, Indonesia. He is currently a laboratory assistant in the Microprocessor and Interface Laboratory, where he is involved in hands-on laboratory sessions and provides technical assistance. His research interests are on embedded systems and hardware programming, particularly in developing microcontroller-based applications and sensor integration. He actively participates in various academic and technical projects related to automation, the Internet of Things (IoT), and hardware-based control systems.

References

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. DOI: https://doi.org/10.3390/diagnostics15010036

M. C. Schall, H. Chen, and L. Cavuoto, “Wearable inertial sensors for objective kinematic assessments: A brief overview,” J Occup Environ Hyg, vol. 19, no. 9, pp. 501–508, 2022, doi: 10.1080/15459624.2022.2100407. DOI: https://doi.org/10.1080/15459624.2022.2100407

H. Prasanth et al., “Wearable sensor-based real-time gait detection: A systematic review,” Apr. 02, 2021, MDPI AG. doi: 10.3390/s21082727. DOI: https://doi.org/10.3390/s21082727

S. Scataglini, L. Dellaert, L. Meeuwssen, E. Staeljanssens, and S. Truijen, “The difference in gait pattern between adults with obesity and adults with a normal weight, assessed with 3D-4D gait analysis devices: a systematic review and meta-analysis,” 2025. DOI: https://doi.org/10.1038/s41366-024-01659-4

A. K. Fitch and H. E. Bays, “Obesity definition, diagnosis, bias, standard operating procedures (SOPs), and telehealth: An Obesity Medicine Association (OMA) Clinical Practice Statement (CPS) 2022,” Obesity Pillars, vol. 1, Mar. 2022, doi: 10.1016/j.obpill.2021.100004. DOI: https://doi.org/10.1016/j.obpill.2021.100004

N. H. Phelps et al., “Worldwide trends in underweight and obesity from 1990 to 2022: a pooled analysis of 3663 population-representative studies with 222 million children, adolescents, and adults,” The Lancet, vol. 403, no. 10431, pp. 1027–1050, Mar. 2024, doi: 10.1016/S0140-6736(23)02750-2. DOI: https://doi.org/10.1016/S0140-6736(23)02750-2

N. Malesevic, I. Svensson, G. Hägglund, and C. Antfolk, “An Integrated Approach for Real-Time Monitoring of Knee Dynamics with IMUs and Multichannel EMG,” Sensors, vol. 23, no. 21, p. 8955, Nov. 2023, doi: 10.3390/s23218955. DOI: https://doi.org/10.3390/s23218955

A. Patoz, A. F. Menéndez, and D. Malatesta, “The effect of severe obesity on three-dimensional ground reaction force signals during walking,” Clinical Biomechanics, vol. 107, Jul. 2023, doi: 10.1016/j.clinbiomech.2023.106042. DOI: https://doi.org/10.1016/j.clinbiomech.2023.106042

J. S. Li, T. Y. Tsai, M. M. Clancy, G. Li, C. L. Lewis, and D. T. Felson, “Weight loss changed gait kinematics in individuals with obesity and knee pain,” Gait Posture, vol. 68, pp. 461–465, Feb. 2019, doi: 10.1016/j.gaitpost.2018.12.031. DOI: https://doi.org/10.1016/j.gaitpost.2018.12.031

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. DOI: https://doi.org/10.3390/s24041232

V. Agostini, L. Gastaldi, V. Rosso, M. Knaflitz, and S. Tadano, “A wearable magneto-inertial system for gait analysis (H-gait): Validation on normalweight and overweight/obese young healthy adults,” Sensors (Switzerland), vol. 17, no. 10, Oct. 2017, doi: 10.3390/s17102406. DOI: https://doi.org/10.3390/s17102406

S. Haufe, I. U. Isaias, F. Pellegrini, and C. Palmisano, “Gait Event Prediction Using Surface Electromyography in Parkinsonian Patients,” Bioengineering, vol. 10, no. 2, Feb. 2023, doi: 10.3390/bioengineering10020212. DOI: https://doi.org/10.3390/bioengineering10020212

W. Maktouf et al., “The influence of obesity and fat distribution on ankle muscle coactivation during gait,” PLoS One, vol. 19, no. 3 March, Mar. 2024, doi: 10.1371/journal.pone.0294692.

A. Makino et al., “Ground reaction force and electromyograms of lower limb muscles during fast walking,” Front Sports Act Living, vol. 4, 2022, doi: 10.3389/fspor.2022.1055302. DOI: https://doi.org/10.3389/fspor.2022.1055302

F. Pennoni, F. Bartolucci, and S. Pandofi, “Variable Selection for Hidden Markov Models with Continuous Variables and Missing Data,” J Classif, Nov. 2024, doi: 10.1007/s00357-023-09457-9. DOI: https://doi.org/10.1007/s00357-023-09457-9

J. Van Den Broeck, S. A. Cunningham, R. Eeckels, and K. Herbst, “Data cleaning: Detecting, diagnosing, and editing data abnormalities,” 2005. doi: 10.1371/journal.pmed.0020267. DOI: https://doi.org/10.1371/journal.pmed.0020267

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. DOI: https://doi.org/10.1155/2014/372814

X. Li, J. Liu, Y. Huang, D. Wang, and Y. Miao, “Human Motion Pattern Recognition and Feature Extraction: An Approach Using Multi-Information Fusion,” Micromachines (Basel), vol. 13, no. 8, Aug. 2022, doi: 10.3390/mi13081205. DOI: https://doi.org/10.3390/mi13081205

P. Podder, M. M. Hasan, M. R. Islam, and M. Sayeed, “Design and Implementation of Butterworth, Chebyshev-I and Elliptic Filter for Speech Signal Analysis,” 2014. DOI: https://doi.org/10.5120/17195-7390

M. Shouran and E. Elgamli, “Design and Implementation of Butterworth Filter,” Int J Innov Res Sci Eng Technol, 2020, [Online]. Available: www.ijirset.com

A. Ghasemi and S. Zahediasl, “Normality tests for statistical analysis: A guide for non-statisticians,” Int J Endocrinol Metab, vol. 10, no. 2, pp. 486–489, 2012, doi: 10.5812/ijem.3505. DOI: https://doi.org/10.5812/ijem.3505

L. R. Rabiner, “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition,” 1989. DOI: https://doi.org/10.1016/B978-0-08-051584-7.50027-9

A. Mannini and A. M. Sabatini, “Gait phase detection and discrimination between walking-jogging activities using hidden Markov models applied to foot motion data from a gyroscope,” Gait Posture, vol. 36, no. 4, pp. 657–661, Sep. 2012, doi: 10.1016/j.gaitpost.2012.06.017. DOI: https://doi.org/10.1016/j.gaitpost.2012.06.017

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. DOI: https://doi.org/10.3390/s21041347

T. Bacri, G. D. Berentsen, J. Bulla, and B. Støve, “Computational issues in parameter estimation for hidden Markov models with template model builder,” J Stat Comput Simul, vol. 93, no. 18, pp. 3421–3457, 2023, doi: 10.1080/00949655.2023.2226788. DOI: https://doi.org/10.1080/00949655.2023.2226788

F. J. Ochando, A. Cantero, J. I. Guerrero, and C. León, “Data Acquisition for Condition Monitoring in Tactical Vehicles: On-Board Computer Development,” Sensors, vol. 23, no. 12, Jun. 2023, doi: 10.3390/s23125645. DOI: https://doi.org/10.3390/s23125645

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. DOI: https://doi.org/10.3390/s25113481

L. K. Ramasamy, F. Khan, M. Shah, B. V. V. S. Prasad, C. Iwendi, and C. Biamba, “Secure Smart Wearable Computing through Artificial Intelligence-Enabled Internet of Things and Cyber-Physical Systems for Health Monitoring,” Sensors, vol. 22, no. 3, Feb. 2022, doi: 10.3390/s22031076. DOI: https://doi.org/10.3390/s22031076

M. Seynaeve, D. Mantini, and T. T. de Beukelaar, “Electrophysiological Approaches to Understanding Brain–Muscle Interactions During Gait: A Systematic Review,” May 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/bioengineering12050471. DOI: https://doi.org/10.1101/2024.02.27.582247

M. Goršič, B. Dai, and D. Novak, “Load position and weight classification during carrying gait using wearable inertial and electromyographic sensors,” Sensors (Switzerland), vol. 20, no. 17, pp. 1–14, Sep. 2020, doi: 10.3390/s20174963. DOI: https://doi.org/10.3390/s20174963

W. Tao, T. Liu, R. Zheng, and H. Feng, “Gait analysis using wearable sensors,” Feb. 2012. doi: 10.3390/s120202255. DOI: https://doi.org/10.3390/s120202255

H. S. Lee, J. H. Lee, and H. S. Kim, “Activities of ankle muscles during gait analyzed by simulation using the human musculoskeletal model,” J Exerc Rehabil, vol. 15, no. 2, pp. 229–234, Apr. 2019, doi: 10.12965/jer.1938054.027. DOI: https://doi.org/10.12965/jer.1938054.027

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

G. G. Samatas and T. P. Pachidis, “Inertial Measurement Units (IMUs) in Mobile Robots over the Last Five Years: A Review,” Feb. 01, 2022, MDPI. doi: 10.3390/designs6010017. DOI: https://doi.org/10.3390/designs6010017

Z. Song, Z. Cao, Z. Li, J. Wang, and Y. Liu, “Inertial Motion Tracking on Mobile and Wearable Devices: Recent Advancements and Challenges,” 2021. DOI: https://doi.org/10.26599/TST.2021.9010017

S. Komarizadehasl, B. Mobaraki, H. Ma, J. A. Lozano-Galant, and J. Turmo, “Development of a low-cost system for the accurate measurement of structural vibrations,” Sensors, vol. 21, no. 18, Sep. 2021, doi: 10.3390/s21186191. DOI: https://doi.org/10.3390/s21186191

A. M. Sabatini, “Estimating three-dimensional orientation of human body parts by inertial/magnetic sensing,” Feb. 2011. doi: 10.3390/s110201489. DOI: https://doi.org/10.3390/s110201489

A. J. L. H. R. V. Sebastian O.H. Madgwick, Estimation of IMU and MARG orientation using a gradient descent algorithm. IEEE, 2011.

K. Daunoraviciene, J. Ziziene, J. Pauk, G. Juskeniene, and J. Raistenskis, “EMG based analysis of gait symmetry in healthy children,” Sensors, vol. 21, no. 17, Sep. 2021, doi: 10.3390/s21175983. DOI: https://doi.org/10.3390/s21175983

V. Agostini, M. Ghislieri, S. Rosati, G. Balestra, and M. Knaflitz, “Surface Electromyography Applied to Gait Analysis: How to Improve Its Impact in Clinics?,” Front Neurol, vol. 11, Sep. 2020, doi: 10.3389/fneur.2020.00994. DOI: https://doi.org/10.3389/fneur.2020.00994

S. Negi, S. Sharma, and N. Sharma, “FSR and IMU sensors-based human gait phase detection and its correlation with EMG signal for different terrain walk,” Sensor Review, vol. 41, no. 3, pp. 235–245, 2020, doi: 10.1108/SR-10-2020-0249. DOI: https://doi.org/10.1108/SR-10-2020-0249

WHO, Obesity : preventing and managing the global epidemic : report of a WHO consultation. World Health Organization, 2000.

G. Santicchi et al., “Validation of Step Detection and Distance Calculation Algorithms for Soccer Performance Monitoring,” Sensors, vol. 24, no. 11, Jun. 2024, doi: 10.3390/s24113343. DOI: https://doi.org/10.3390/s24113343

G. Pacini Panebianco, M. C. Bisi, R. Stagni, and S. Fantozzi, “Analysis of the performance of 17 algorithms from a systematic review: Influence of sensor position, analysed variable and computational approach in gait timing estimation from IMU measurements,” Gait Posture, vol. 66, pp. 76–82, Oct. 2018, doi: 10.1016/j.gaitpost.2018.08.025. DOI: https://doi.org/10.1016/j.gaitpost.2018.08.025

W. Niswander and K. Kontson, “Evaluating the impact of imu sensor location and walking task on accuracy of gait event detection algorithms,” Sensors, vol. 21, no. 12, Jun. 2021, doi: 10.3390/s21123989. DOI: https://doi.org/10.3390/s21123989

J. Runhaar, B. W. Koes, S. Clockaerts, and S. M. A. Bierma-Zeinstra, “A systematic review on changed biomechanics of lower extremities in obese individuals: A possible role in development of osteoarthritis,” Obesity Reviews, vol. 12, no. 12, pp. 1071–1082, Dec. 2011, doi: 10.1111/j.1467-789X.2011.00916.x. DOI: https://doi.org/10.1111/j.1467-789X.2011.00916.x

L. Koinis, M. Maharaj, P. Natarajan, R. D. Fonseka, V. Fernando, and R. J. Mobbs, “Exploring the Influence of BMI on Gait Metrics: A Comprehensive Analysis of Spatiotemporal Parameters and Stability Indicators,” Sensors, vol. 24, no. 19, Oct. 2024, doi: 10.3390/s24196484. DOI: https://doi.org/10.3390/s24196484

W. Maktouf et al., “The influence of obesity and fat distribution on ankle muscle coactivation during gait,” PLoS One, vol. 19, no. 3 March, Mar. 2024, doi: 10.1371/journal.pone.0294692. DOI: https://doi.org/10.1371/journal.pone.0294692

T. A. Kuiken, M. M. Lowery, and N. S. Stoykov, “The effect of subcutaneous fat on myoelectric signal amplitude and cross-talk,” Prosthet Orthot Int, vol. 27, no. 1, pp. 48–54, 2003, doi: 10.3109/03093640309167976. DOI: https://doi.org/10.3109/03093640309167976