https://orcid.org/0000-0003-3056-7000
Abstract
Hands-and-knees crawling, an effective rehabilitation method for children with motor impairments, requires precise phase detection for optimizing assistive devices. However, research on phase detection in human crawling remains limited. The research explores whether multijoint kinematic synergy (KS) features provide better accuracy than traditional time-domain (TD) features. Nine healthy adults participated in the study, where accelerometers and pressure sensors were used to capture motion and pressure data during crawling. The data were preprocessed and used to define four distinct phases of crawling, and kinematic synergy features were extracted using singular value decomposition-based principal component analysis (PCA). Machine learning models, including classification and regression trees (CART), K-nearest neighbors (KNN), and error-correcting output codes support vector machines (ECOC-SVM), were trained to recognize the crawling phases. Their performance was compared to that of traditional time-domain features. The phase recognition method based on multijoint kinematic synergies achieved an average accuracy of 89.37%. Specifically, the accuracy for CART was 88.41%, for KNN was 85.51%, and for ECOC-SVM was 94.20%. In comparison, the phase recognition using traditional time-domain features yielded lower accuracy, with overall accuracies of 75.36% for CART, 76.09% for KNN, and 85.51% for ECOC-SVM. The findings demonstrate that using multijoint kinematic synergy features significantly improves the accuracy of crawling phase recognition compared to traditional time-domain features. These recognized phases can be used to interpret the user's intent, which can then be integrated into exoskeleton control systems. In particular, high-level control systems can detect this intent and communicate it to lower-level systems, enabling precise motion commands. This integration holds promise for improving rehabilitation outcomes, especially for patients with conditions like cerebral palsy.
Issue Section:
Research Papers
Topics:
Algorithms,
Kinematics,
Knee,
Machine learning,
Support vector machines,
Pressure,
Errors,
Signals,
Engines,
Motors
References
1.
WHO Multicentre Growth Reference Study Group
, 2006
, “WHO Motor Development Study: Windows of Achievement for Six Gross Motor Development Milestones
,” Acta Paediatr. (Oslo, Norway: 1992), Suppl.
, 450
, pp. 86
–95
.10.1111/j.1651?2227.2006.tb02379.x2.
Xiong
, Q. L.
, Wu
, X. Y.
, Liu
, Y.
, Zhang
, C. X.
, and Hou
, W. S.
, 2021
, “Measurement and Analysis of Human Infant Crawling for Rehabilitation: A Narrative Review
,” Front. Neurol.
, 12
, p. 731374
(in English).10.3389/fneur.2021.7313743.
McEwan
, M. H.
, Dihoff
, R. E.
, and Brosvic
, G. M.
, 1991
, “Early Infant Crawling Experience Is Reflected in Later Motor Skill Development
,” Perceptual Mot. Skills
, 72
(1
), pp. 75
–79
(in English).10.2466/pms.1991.72.1.754.
Cole
, W. G.
, Vereijken
, B.
, Young
, J. W.
, Robinson
, S. R.
, and Adolph
, K. E.
, 2019
, “Use It or Lose It? Effects of Age, Experience, and Disuse on Crawling
,” Dev. Psychobiol.
, 61
(1
), pp. 29
–42
(in English).10.1002/dev.218025.
Crouchman
, M.
, 1986
, “The Effects of Babywalkers on Early Locomotor Development
,” Dev. Med. Child Neurol.
, 28
(6
), pp. 757
–761
(in English).10.1111/j.1469-8749.1986.tb03929.x6.
Yan
, B.
, and Ying
, G. M.
, 2022
, “Effect of Crawling Training on the Cognitive Function of Children With Cerebral Palsy
,” Int. J. Rehabil. Res.
, 45
(2
), pp. 184
–188
.10.1097/MRR.00000000000005267.
Li
, T.
, Chen
, X.
, Cao
, S.
, Zhang
, X.
, and Chen
, X.
, 2019
, “Human Hands-and-Knees Crawling Movement Analysis Based on Time-Varying Synergy and Synchronous Synergy Theories
,” Math. Biosci. Eng.: MBE
, 16
(4
), pp. 2492
–2513
.10.3934/mbe.20191258.
Chengxiang
, L.
, Xiang
, C.
, Xu
, Z.
, Xun
, C.
, and De
, W.
, 2023
, “Muscle Synergy Analysis of Eight Inter-Limb Coordination Modes During Human Hands-Knees Crawling Movement
,” Front. Neurosci.
, 17
, p. 1135646
.10.3389/fnins.2023.11356469.
Bell
, M. A.
, and Fox
, N. A.
, 1996
, “Crawling Experience Is Related to Changes in Cortical Organization During Infancy: Evidence From EEG Coherence
,” Dev. Psychobiol.
, 29
(7
), pp. 551
–561
(in English).10.1002/(SICI)1098-2302(199611)29:7<551::AID-DEV1>3.0.CO;2-T10.
Yi
, L.
, and Zhang
, L. F.
, 2013
, “The Effect of Crawling Training on Lower Limb Function in Stroke Patients With Hemiplegia
,” China Pract. Med.
, 8
(22
), pp. 261
–262
.10.3969/j.issn.1672-6731.2017.05.00411.
FitCrawl
, 2023
, “Your Total Body Workout
,” FitCrawl, Sydney, Australia, https://www.crawlfit.com.au/12.
Ghazi
, M. A.
, Nash
, M. D.
, Fagg
, A. H.
, Ding
, L.
, Kolobe
, T. H. A.
, and Miller
, D. P.
, 2016
, “Novel Assistive Device for Teaching Crawling Skills to Infants
,” Field and Service Robotics: Results of the 10th International Conference
, D. S.
Wettergreen
and T. D.
Barfoot
, eds., Springer International Publishing
, Cham, Switzerland
, pp. 593
–605
.13.
Jiang
, J. G.
, Wang
, C. C.
, and Zhang
, W. J.
, 2020
, “Design and Analysis of a Parallel-Driven Rehabilitation Robot for Children With Cerebral Palsy
,” Mech. Eng.
, 12
, pp. 1
–3 + 6
.10.3390/machines1108078714.
Kukreja
, V.
, Kumar
, D.
, and Kaur
, A.
, 2021
, “Deep Learning in Human Gait Recognition: An Overview
,” 2021 International Conference on Advance Computing and Innovative Technologies in Engineering
(ICACITE
), Noida, India, March 4--5, pp. 9
–13
.10.1109/ICACITE51222.2021.940461115.
Buchanan
, T. S.
, Lloyd
, D. G.
, Manal
, K.
, and Besier
, T. F.
, 2004
, “Neuromusculoskeletal Modeling: Estimation of Muscle Forces and Joint Moments and Movements From Measurements of Neural Command
,” J. Appl. Biomech.
, 20
(4
), pp. 367
–395
.10.1123/jab.20.4.36716.
Huang
, L.
, Zheng
, J.
, and Hu
, H.
, 2022
, “Online Gait Phase Detection in Complex Environment Based on Distance and Multi-Sensors Information Fusion Using Inertial Measurement Units
,” Int. J. Soc. Rob.
, 14
(2
), pp. 413
–428
.10.1007/s12369-021-00794-617.
Zhu
, L.
, Wang
, Z.
, Ning
, Z.
, Zhang
, Y.
, Liu
, Y.
, Cao
, W.
, Wu
, X.
, and Chen
, C.
, 2020
, “A Novel Motion Intention Recognition Approach for Soft Exoskeleton Via IMU
,” Electronics
, 9
(12
), p. 2176
.10.3390/electronics912217618.
Zhang
, Z.
, Wang
, Z.
, Lei
, W.
, and Gu
, W.
, 2022
, “Gait Phase Recognition of Lower Limb Exoskeleton System Based on the Integrated Network Model
,” Biomed. Signal Process. Control
, 76
, p. 103693
.10.1016/j.bspc.2022.10369319.
Liu
, D.-X.
, Wu
, X.
, Du
, W.
, Wang
, C.
, and Xu
, T.
, 2016
, “Gait Phase Recognition for Lower-Limb Exoskeleton With Only Joint Angular Sensors
,” Sensors
, 16
(10
), p. 1579
.10.3390/s1610157920.
Kyeong
, S.
, Feng
, J.
, Ryu
, J. K.
, Park
, J. J.
, Lee
, K. H.
, and Kim
, J.
, 2022
, “Surface Electromyography Characteristics for Motion Intention Recognition and Implementation Issues in Lower-Limb Exoskeletons
,” Int. J. Control, Autom. Syst.
, 20
(3
), pp. 1018
–1028
.10.1007/s12555-020-0934-321.
Gao
, F.
, Tian
, T.
, Yao
, T.
, and Zhang
, Q.
, 2021
, “Human Gait Recognition Based on Multiple Feature Combination and Parameter Optimization Algorithms
,” Comput. Intell. Neurosci.
, 2021
(1
), p. 6693206
.10.1155/2021/669320622.
Su
, B.
, Smith
, C.
, and Farewik
, E. G.
, 2020
, “Gait Phase Recognition Using Deep Convolutional Neural Network With Inertial Measurement Units
,” Biosensors-Basel
, 10
(9
), p. 109
.10.3390/bios1009010923.
Xing
, H.
, and Zhang
, R.
, 2022
, “Gait Recognition for Exoskeleton Robots Based on Improved KNN-DAGSVM Fusion Algorithm
,” 37th Youth Academic Annual Conference of Chinese Association of Automation
(YAC
), Beijing, China, Nov. 19–20, pp. 364
–369
.10.1109/YAC57282.202224.
Yan
, H.
, and Li
, Z.
, 2022
, “Optimization Algorithm of Gait Recognition Based on EMG Signal
,” IEEE Second International Conference on Data Science and Computer Application
(ICDSCA
), Dalian, China, Oct. 28–30, pp. 1405
–1408
.10.1109/ICDSCA56264.202225.
Fangzheng
, W.
, Lei
, Y.
, and Jiang
, X.
, 2019
, “Recognition of the Gait Phase Based on New Deep Learning Algorithm Using Multisensor Information Fusion
,” Sens. Mater.
, 31
(10
), p. 3041
.10.18494/SAM.2019.249326.
Svonko
, G.
, Renato
, B.
, Mario
, M.
, Serena
, P.
, Salvatore
, C. R.
, and Marco
, D. N. A.
, 2023
, “Predicting Physical Activity Levels From Kinematic Gait Data Using Machine Learning Techniques
,” Eng. Appl. Artif. Intell.
, 123
(Pt. C
), p. 106487
.10.1016/j.engappai.2023.10648727.
Wang
, J.
, Wang
, Z.
, Zhao
, H.
, and Qiu
, S.
, 2016
, “Human Motion Phase Segmentation Based on Three New Features
,” IEEE 20th International Conference on Computer Supported Cooperative Work in Design
(CSCWD
), Nanchang, China, May 4--6, pp. 647
–652
.10.1109/CSCWD.2016.756594828.
Abhayasinghe
, N.
, and Murray
, I.
, 2014
, “Human Gait Phase Recognition Based on Thigh Movement Computed Using IMUs
,” 2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing
(ISSNIP
), Singapore, Apr. 21–24, pp. 1
–4
.10.1109/ISSNIP.2014.682760429.
Lai
, Y. C.
, Liao
, H. Y. M.
, Lin
, C. C.
, Chen
, J. R.
, and Luo
, Y. F. P.
, 2009
, “A Local Feature-Based Human Motion Recognition Framework
,” IEEE International Symposium on Circuits and Systems
, Taipei, Taiwan, May 24–27, pp. 722
–725
.10.1109/ISCAS.2009.511785030.
To
, C. S.
, Kirsch
, R. F.
, Kobetic
, R.
, and Triolo
, R. J.
, 2005
, “Simulation of a Functional Neuromuscular Stimulation Powered Mechanical Gait Orthosis With Coordinated Joint Locking
,” IEEE Trans. Neural Syst. Rehabil. Eng.
, 13
(2
), pp. 227
–235
(in English).10.1109/TNSRE.2005.84738431.
Dejnabadi
, H.
, Jolles
, B. M.
, and Aminian
, K.
, 2008
, “A New Approach for Quantitative Analysis of Inter-Joint Coordination During Gait
,” IEEE Trans. Biomed. Eng.
, 55
(2
), pp. 755
–764
.10.1109/TBME.2007.90103432.
Safavynia
, S.
, Torres-Oviedo
, G.
, and Ting
, L.
, 2011
, “Muscle Synergies: Implications for Clinical Evaluation and Rehabilitation of Movement
,” Top. Spinal Cord Injury Rehabil.
, 17
(1
), pp. 16
–24
.10.1310/sci1701-1633.
Ting
, L. H.
, and McKay
, J. L.
, 2007
, “Neuromechanics of Muscle Synergies for Posture and Movement
,” Curr. Opin. Neurobiol.
, 17
(6
), pp. 622
–628
.10.1016/j.conb.2008.01.00234.
Tresch
, M. C.
, Saltiel
, P.
, and Bizzi
, E.
, 1999
, “The Construction of Movement by the Spinal Cord
,” Nat. Neurosci.
, 2
(2
), pp. 162
–167
.10.1038/572135.
Shuaijie
, W.
, YiChung
, P.
, and Tanvi
, B.
, 2021
, “Kinematic Synergies in Over-Ground Slip Recovery Outcomes: Distinct Strategies or a Single Strategy?
,” Gait Posture
, 95
, pp. 270
–276
.10.1016/j.gaitpost.2021.01.02536.
Yusuke
, S.
, Dai
, O.
, Keita
, H.
, and ShinIchi
, I.
, 2022
, “Kinetic Interjoint Coordination in Lower Limbs During Gait in Patients With Hemiparesis
,” Biomechanics
, 2
(3
), pp. 466
–477
.10.3390/biomechanics203003637.
Burns
, M. K.
, Patel
, V.
, Florescu
, I.
, Pochiraju
, K. V.
, and Vinjamuri
, R.
, 2017
, “Low-Dimensional Synergistic Representation of Bilateral Reaching Movements
,” Front. Bioeng. Biotechnol.
, 5
, p. 2
(in English).10.3389/fbioe.2017.0000238.
Troje
, N. F.
, 2002
, “Decomposing Biological Motion: A Framework for Analysis and Synthesis of Human Gait Patterns
,” J. Vision
, 2
(5
), pp. 371
–387
(in English).10.1167/2.5.239.
Gentner
, R.
, and Classen
, J.
, 2006
, “Modular Organization of Finger Movements by the Human Central Nervous System
,” Neuron
, 52
(4
), pp. 731
–742
(in English).10.1016/j.neuron.2006.09.03840.
Yang
, J.
, Lu
, Z.
, Chen
, S.
, Liu
, C.
, and Zhao
, H.
, 2024
, “Continuous Knee Joint Angle Prediction With Surface EMG
,” Biomed. Signal Process. Control
, 95
, p. 106354
.10.1016/j.bspc.2024.10635441.
Li
, X.
, and Chen
, L.
, 2021
, “Kinematic Compatibility Recognition and Angle Tracking Control for Lower Limb Exoskeleton
,” Fifth International Conference on Robotics and Automation Sciences
(ICRAS
), IEEE, Wuhan, China, June 11–13, pp. 150
–154
.10.1109/ICRAS52289.2021.947628742.
Schwartz
, E.
, Guidry
, K.
, Lee
, A.
, Dinh
, D.
, Levin
, M. F.
, and Demers
, M.
, 2022
, “Clinical Motor Coordination Tests in Adult Neurology: A Scoping Review
,” Physiother. Can.
, 74
(4
), pp. 387
–395
(in English).10.3138/ptc-2021-002543.
Xiong
, Q.
, Wan
, J.
, Liu
, Y.
, Wu
, X.
, Jiang
, S.
, Xiao
, N.
, and Hou
, W.
, 2024
, “Reduced Corticospinal Drive to Antagonist Muscles of Upper and Lower Limbs During Hands-and-Knees Crawling in Infants With Cerebral Palsy: Evidence From Intermuscular EMG-EMG Coherence
,” Behav. Brain Res.
, 457
, p. 114718
.10.1016/j.bbr.2023.11471844.
Xiong
, Q. L.
, Hou
, W. S.
, Xiao
, N.
, Chen
, Y. X.
, Yao
, J.
, Zheng
, X. L.
, Liu
, Y.
, and Wu
, X. Y.
, 2018
, “Motor Skill Development Alters Kinematics and Co-Activation Between Flexors and Extensors of Limbs in Human Infant Crawling
,” IEEE Trans. Neural Syst. Rehabil. Eng.
, 26
(4
), pp. 780
–787
.10.1109/TNSRE.2017.278582145.
Robertson
, D. G. E.
, and Dowling
, J. J.
, 2003
, “Design and Responses of Butterworth and Critically Damped Digital Filters
,” J. Electromyogr. Kinesiol.
, 13
(6
), pp. 569
–573
.10.1016/S1050-6411(03)00080-446.
Widmann
, A.
, Schröger
, E.
, and Maess
, B.
, 2015
, “Digital Filter Design for Electrophysiological Data—A Practical Approach
,” J. Neurosci. Methods
, 250
, pp. 34
–46
.10.1016/j.jneumeth.2014.08.00247.
Sun
, M.
, Lan
, L.
, Zhu
, C.-G.
, and Lei
, F.
, 2023
, “Cubic Spline Interpolation With Optimal End Conditions
,” J. Comput. Appl. Math.
, 425
, p. 115039
.10.1016/j.cam.2022.11503948.
Li
, X.
, Liu
, J.
, Huang
, Y.
, Wang
, D.
, and Miao
, Y.
, 2022
, “Human Motion Pattern Recognition and Feature Extraction: An Approach Using Multi-Information Fusion
,” Micromachines (Basel)
, 13
(8
), p. 1205
(in English).10.3390/mi1308120549.
Samuel
, O. W.
, Zhou
, H.
, Li
, X.
, Wang
, H.
, Zhang
, H.
, Sangaiah
, A. K.
, and Li
, G.
, 2018
, “Pattern Recognition of Electromyography Signals Based on Novel Time Domain Features for Amputees' Limb Motion Classification
,” Comput. Electr. Eng.
, 67
, pp. 646
–655
.10.1016/j.compeleceng.2017.04.00350.
Tkach
, D.
, Huang
, H.
, and Kuiken
, T. A.
, 2010
, “Study of Stability of Time-Domain Features for Electromyographic Pattern Recognition
,” J. NeuroEng. Rehabil.
, 7
(1
), p. 21
.10.1186/1743-0003-7-2151.
Berk
, R. A.
, 2016
, “Classification and Regression Trees (CART)
,” Statistical Learning From a Regression Perspective
, R. A.
Berk
, ed., Springer International Publishing
, Cham, Switzerland
, pp. 129
–186
.52.
Eltanani
, S.
, Scheper
, T. O.
, and Dawes
, H.
, 2021
, “K-Nearest Neighbor Algorithm: Proposed Solution for Human Gait Data Classification
,” IEEE Symposium on Computers and Communications
(ISCC
), Athens, Greece, Sept. 5--8, pp. 1
–5
.10.1109/ISCC53001.2021.963145453.
Liu
, Q.
, Sun
, W.
, Peng
, N.
, Meng
, W.
, and Xie
, S. Q.
, 2024
, “DCNN-SVM-Based Gait Phase Recognition With Inertia, EMG, and Insole Plantar Pressure Sensing
,” IEEE Sens. J.
, 24
(18
), pp. 28869
–28878
.10.1109/JSEN.2024.343588454.
Sun
, B.
, Zhang
, Z.
, Liu
, X.
, Hu
, B.
, and Zhu
, T.
, 2017
, “Self-Esteem Recognition Based on Gait Pattern Using Kinect
,” Gait Posture
, 58
, pp. 428
–432
.10.1016/j.gaitpost.2017.09.00155.
Huang
, B.
, Xiong
, C.
, Chen
, W.
, Liang
, J.
, Sun
, B. Y.
, and Gong
, X.
, 2021
, “Common Kinematic Synergies of Various Human Locomotor Behaviours
,” R. Soc. Open Sci.
, 8
(4
), p. 210161
(in English).10.1098/rsos.21016156.
Nancy
, S.-O.
, and Feldman
, A. G.
, 2003
, “Interjoint Coordination in Lower Limbs During Different Movements in Humans
,” Exp. Brain Res.
, 148
(2
), pp. 139
–149
.10.1007/s00221-002-1212-857.
Tagliabue
, M.
, Ciancio
, A. L.
, Brochier
, T.
, Eskiizmirliler
, S.
, and Maier
, M. A.
, 2015
, “Differences Between Kinematic Synergies and Muscle Synergies During Two-Digit Grasping
,” Front. Human Neurosci.
, 9
, p. 165
.10.3389/fnhum.2015.0016558.
Zheng
, G.
, Qian
, Z.
, Yang
, Q.
, Wei
, C.
, Xie
, L.
, Zhu
, Y.
, and Li
, Y.
, 2008
, “The Combination Approach of SVM and ECOC for Powerful Identification and Classification of Transcription Factor
,” BMC Bioinf.
, 9
(1
), p. 282
.10.1186/1471-2105-9-28259.
Liu
, M.
, Zhang
, D.
, Chen
, S.
, and Xue
, H.
, 2016
, “Joint Binary Classifier Learning for ECOC-Based Multi-Class Classification
,” IEEE Trans. Pattern Anal. Mach. Intell.
, 38
(11
), pp. 2335
–2341
.10.1109/TPAMI.2015.243032560.
Roman
, I.
, Santana
, R.
, Mendiburu
, A.
, and Lozano
, J. A.
, 2021
, “In-Depth Analysis of SVM Kernel Learning and Its Components
,” Neural Comput. Appl.
, 33
(12
), pp. 6575
–6594
.10.1007/s00521-020-05419-z61.
Gao
, F.
, Liu
, G.
, Liang
, F.
, and Liao
, W. H.
, 2020
, “IMU-Based Locomotion Mode Identification for Transtibial Prostheses, Orthoses, and Exoskeletons
,” IEEE Trans. Neural Syst. Rehabil. Eng.
, 28
(6
), pp. 1334
–1343
.10.1109/TNSRE.2020.298715562.
Derlatka
, M.
, and Bogdan
, M.
, 2015
, “Ensemble kNN Classifiers for Human Gait Recognition Based on Ground Reaction Forces
,” Eighth International Conference on Human System Interaction
(HSI
), Warsaw, Poland, June 25--27, pp. 88
–93
.10.1109/HSI.2015.717064863.
Gao
, Q.
, Ding
, X.
, Li
, C.
, and Qi
, Z. T.
, 2023
, “A Gait Recognition of EMG Signal Method Based on Bat Algorithm Optimized KNN
,” Seventh Asian Conference on Artificial Intelligence Technology (ACAIT
), Jiaxing, China, Nov. 10–12, pp. 16
–20
.10.1109/ACAIT60137.2023.10528639Copyright © 2025 by ASME
You do not currently have access to this content.
