Role of machine learning in gait analysis: a review

References

• Dolatabadi E, Taati B, Mihailidis A. An automated classification of pathological gait using unobtrusive sensing technology. IEEE Trans Neural Syst Rehabil Eng. 2017;25(12):2336–2346.
   PubMed Web of Science ®Google Scholar
• Lai DTH, Begg RK, Palaniswami M. Computational intelligence in gait research: a perspective on current applications and future challenges. IEEE Trans Inf Technol Biomed. 2009;13(5):687–701.
   PubMedGoogle Scholar
• Paulo J, Peixoto P, Amorim P. Trajectory-based gait pattern shift detection for assistive robotics applications. Intel Serv Robot. 2019;12(3):255–264.
   Web of Science ®Google Scholar
• Kutilek P, Hozman J. Prediction of lower extremities movement using characteristics of angle-angle diagrams and artificial intelligence. Proceedings of the 3rd International Conference on E-Health and Bioengineering – EHB; 2011.
   Google Scholar
• Farah JD, Baddour N, Lemaire ED. Design, development, and evaluation of a local sensor-based gait phase recognition system using a logistic model decision tree for orthosis-control. J Neuroeng Rehabil. 2019;16(1):22.
   PubMed Web of Science ®Google Scholar
• Begg R, Kamruzzaman J. Neural networks for detection and classification of walking pattern changes due to ageing. Aust Phys Eng Sci Med. 2006;29(2):188–195.
   PubMedGoogle Scholar
• Lau HY, Tong KY, Zhu H. Support vector machine for classification of walking conditions using miniature kinematic sensors. Med Biol Eng Comput. 2008;46(6):563–573.
   PubMed Web of Science ®Google Scholar
• Souza AM, Stemmer MR. Extraction and classification of human body parameters for gait analysis. J Control Autom Electr Syst. 2018;29(5):586–604.
   Web of Science ®Google Scholar
• Hyeon-Min S, Sangmin L. Multi-channel electromyography pattern classification using deep belief networks for enhanced user experience. J Central South Univ. 2015;22(5):1801–1808.
   Web of Science ®Google Scholar
• Wei W, McElroy C, Dey S. Action understanding and movement error identification for the treatment of patients with Parkinson’s disease. IEEE International Conference on Healthcare Informatics; 2018.
   Google Scholar
• Leightley D, McPhee JS, Yap MH. Automated analysis and quantification of human mobility using a depth sensor. IEEE J Biomed Health Inform. 2017;21(4):939–948.
   PubMed Web of Science ®Google Scholar
• Arosha Senanayake SMN, Malik OA, Iskandar PM, et al. A knowledge-based intelligent framework for anterior cruciate ligament rehabilitation monitoring. Appl Soft Comput. 2014;20:127–141.
   Web of Science ®Google Scholar
• Gestel LV, Laet TD, Lello ED, et al. Probabilistic gait classification in children with cerebral palsy: a Bayesian approach. Res Dev Disabil. 2011;32(6):2542–2552.
   PubMed Web of Science ®Google Scholar
• Mu T, Pataky TC, Findlow AH, et al. Automated nonlinear feature generation and classification of foot pressure lesions. IEEE Trans Inf Technol Biomed. 2010;14(2):418–424.
   PubMedGoogle Scholar
• Pla A, Mordvanyuk N, Lopez M, et al. Bag-of-steps: predicting lower-limb fracture rehabilitation length. Neurocomputing. 2017;268:109–115.
   Web of Science ®Google Scholar
• Yoo TK, Kim SK, Choi SB, et al. Interpretation of movement during stair ascent for predicting severity and prognosis of knee osteoarthritis in elderly women using support vector machine. Proceedings of International Conference of the IEEE EMBS; 2013. p. 192–196.
   Google Scholar
• Xiong B, Zeng N, Li H, et al. Intelligent prediction of human lower extremity joint moment: an artificial neural network approach. IEEE Access Spec Sect Data Enab Intell Dig Health. 2019;7:29973–29980.
   Google Scholar
• Zeng W, Ismail SA, Pappas E. Classification of gait patterns in patients with unilateral anterior cruciate ligament deficiency based on phase space reconstruction. Soft Comput. 2020;24(3):1851–1868.
   Web of Science ®Google Scholar
• Alaqtash M, Sarkodie-Gyan T, Yu H, et al. Automatic classification of pathological gait patterns using ground reaction forces and machine learning algorithms. Proceedings of International Conference of the IEEE-EMBS; Boston, MA; 2011. p. 453–457.
   Google Scholar
• Devanne M, Berretti S. Learning shape variations of motion trajectories for gait analysis. 23rd International Conference on Pattern Recognition (ICPR); 2016. p. 895–900.
   Google Scholar
• Begg RK, Palaniswami M, Owen B. Support vector machines for automated gait classification. IEEE Trans Biomed Eng. 2005;52(5):828–838.
   PubMed Web of Science ®Google Scholar
• Costa A, Ianez E, Ubeda A, et al. Decoding the attentional demands of gait through EEG gamma band features. PLoS One. 2016;11(4):e0154136.
   PubMed Web of Science ®Google Scholar
• Goh SK, Abbass HA, Tan KC, et al. Spatio-spectral representation learning for electroencephalographic gait-pattern classification. IEEE Trans Neural Syst Rehabil Eng. 2018;26(9):1858–1867.
   PubMed Web of Science ®Google Scholar
• Paulo J, Peixoto P, Nunes UJ. ISR-AIWALKER: robotic walker for intuitive and safe mobility assistance and gait analysis. IEEE Trans Hum Mach Syst. 2017;47(6):1110–1122.
   Web of Science ®Google Scholar
• Liu DX, Du W, Wu X, et al. Deep rehabilitation gait learning for modelling knee joints of lower limb exoskeleton. Proceedings of IEEE International Conference on Robotics and Biomimetics; 2016. p. 1058–1063.
   Google Scholar
• Thongsook A, Nunthawarasilp T, Kraypet P, et al. C4.5 decision tree against neural network on gait phase recognition for lower limp exoskeleton. First International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics (ICA-SYMP); 2019. p. 69–72.
   Google Scholar
• Guo G, Guffey K, Chen W, et al. Classification of normal and pathological gait in young children based on foot pressure data. Neuroinformatics. 2017;15(1):13–24.
   PubMed Web of Science ®Google Scholar
• Williams G, Lai D, Schache A, et al. Classification of gait disorders following traumatic brain injury. J Head Trauma Rehabil. 2015;30(2):E13–E23.
   PubMed Web of Science ®Google Scholar
• Qiu S, Liu L, Wang Z, et al. Body sensor network-based gait quality assessment for clinical decision-support via multi-sensor fusion. IEEE Access Spec Sect Wireless Body Area Netw. 2019;7:59884–59894.
   Google Scholar
• Huang R, Peng Z, Cheng H, et al. Learning-based walking assistance control strategy for a lower limb exoskeleton with hemiplegia patients. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS); 2018. p. 2280–2285.
   Google Scholar
• Muniz AMS, Manfio EF, Andrade MC, et al. Principal component analysis of vertical ground reaction force: a powerful method to discriminate normal and abnormal gait and assess treatment. Proceedings of International Conference of the IEEE Engineering in Medicine and Biology Society; 2006. p. 2683–2686.
   Google Scholar
• Semwal VB, Chakraborty P, Nandi GC. Less computationally intensive fuzzy logic (type-1)-based controller for humanoid push recovery. Rob Auton Syst. 2015;63:122–135.
   Web of Science ®Google Scholar
• Lai DTH, Levinger P, Begg RK, et al. Identification of patellofemoral pain syndrome using a support vector machine approach. Proceedings of the 29th Annual International Conference of the IEEE EMBS; 2007. p. 3144–3147.
   Google Scholar
• Nair SS, French RM, Laroche D, et al. The application of machine learning algorithms to the analysis of electromyographic patterns from arthritic patients. IEEE Trans Neural Syst Rehabil Eng. 2010;18(2):174–184.
   PubMed Web of Science ®Google Scholar
• Moher D, Liberati A, Tetzlaff J, et al. Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. PLoS Med. 2009;6(7):e1000097.
   PubMed Web of Science ®Google Scholar
• Pham H, Kawanishi M, Narikiyo T. A LLE-HMM-based framework for recognizing human gait movement from EMG. IEEE International Conference on Robotics and Automation (ICRA); 2015. p. 2997–3002.
   Google Scholar
• Lonini L, Gupta A, Kording K, et al. Activity recognition in patients with lower limb impairments: do we need training data from each patient? International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 2016.
   Google Scholar
• Recher F, Banos O, Nikamp CDM, et al. Optimizing activity recognition in stroke survivors for wearable exoskeletons. 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob); 2018. p. 173–178.
   Google Scholar
• Sok P, Xiao T, Azeze Y, et al. Activity recognition for incomplete spinal cord injury subjects using hidden Markov models. IEEE Sens J. 2018;18(15):6369–6374.
   Web of Science ®Google Scholar
• Lau H, Tong K. The reliability of using accelerometer and gyroscope for gait event identification on persons with dropped foot. Gait Posture. 2008;27(2):248–257.
   PubMed Web of Science ®Google Scholar
• Jung JY, Chae MG, Jang IH, et al. A hybrid control method of an exoskeleton robot for intention-driven walking rehabilitation of stroke patients. 9th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI); 2012. p. 58–60.
   Google Scholar
• Jiang S, Pang Y, Wang D, et al. Gait recognition based on graphene porous network structure pressure sensors for rehabilitation therapy. Proceedings of IEEE International Conference on Electron Devices and Solid State Circuits (EDSSC); 2018.
   Google Scholar
• Nazmi N, Rahman MAA, Ariff MHM. Generalization of ANN model in classifying stance and swing phases of gait using EMG signals. IEEE-EMBS Conference on Biomedical Engineering and Sciences; 2018. p. 461–466.
   Google Scholar
• Lee SI, Ozsecen MY, Toffola LD, et al. Activity detection in uncontrolled free living conditions using a single accelerometer. Proceedings of IEEE International Conference on Wearable and Implantable Body Sensor Networks (BSN); 2015.
   Google Scholar
• Adil S, Anwar T, Jumaily AA. Extreme learning machine based sEMG for drop-foot after stroke detection. Proceedings of International Conference on Information Science and Technology; 2016. p. 18–22.
   Google Scholar
• Cho J, Cho YS, Moon SB, et al. Scoliosis screening through a machine learning based gait analysis test. Int J Precis Eng Manuf. 2018;19(12):1861–1872.
   Web of Science ®Google Scholar
• Cui C, Bian GB, Hou ZG, et al. Simultaneous recognition and assessment of post-stroke hemiparetic gait by fusing kinematic, kinetic, and electrophysiological data. IEEE Trans Neural Syst Rehabil Eng. 2018;26(4):856–864.
   PubMed Web of Science ®Google Scholar
• Zhang Y, Ma Y. Application of supervised machine learning algorithms in the classification of sagittal gait patterns of cerebral palsy children with spastic diplegia. Comput Biol Med. 2019;106:33–39.
   PubMed Web of Science ®Google Scholar
• Sobral H, Ferreira JP, Vieira A, et al. Two new indices to assess gait disturbances applied to anterior cruciate ligament reconstructed knees. Proceedings of IEEE 8th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems; 2018. p. 701–706.
   Google Scholar
• Hortal E, Ubeda A, Ianez E, et al. Using EEG signals to detect the intention of walking initiation and stop. Artif Comput Biol Med (IWINAC). 2015;278–287.
   Google Scholar
• Park S, Park FC, Choi J, et al. EEG-based gait state and gait intention recognition using spatio-spectral convolutional neural network. IEEE International Winter Conference on Brain-Computer Interface (BCI); 2019.
   Google Scholar
• Schutte LM, Narayanan U, Stout JL, et al. An index for quantifying deviations from normal gait. Gait Posture. 2000;11(1):25–31.
   PubMed Web of Science ®Google Scholar
• Ghasemzadeh H, Jafari R, Prabhakaran B. A body sensor network with electromyogram and inertial sensors: multimodal interpretation of muscular activities. IEEE Trans Inf Technol Biomed. 2010;14(2):198–206.
   PubMedGoogle Scholar
• Levinger P, Lai DTH, Begg RK, et al. The application of support vector machines for detecting recovery from knee replacement surgery using spatio-temporal gait parameters. Gait Posture. 2009;29(1):91–96.
   PubMed Web of Science ®Google Scholar
• Alaqtash M, Yu H, Brower R, et al. Application of wearable sensors for human gait analysis using fuzzy computational algorithm. Eng Appl Artif Intell. 2011;24(6):1018–1025.
   Web of Science ®Google Scholar
• Ferreira JP, Vieira A, Ferreira P, et al. Human knee joint walking pattern generation using computational intelligence techniques. Neural Comput Appl. 2018;30(6):1701–1713.
   Web of Science ®Google Scholar
• Dallali H, Knop L, Castelino L, et al. Estimating the multivariable human ankle impedance in dorsi-plantarflexion and inversion-eversion directions using EMG signals and artificial neural networks. Int J Intell Robot Appl. 2017;1(1):19–31.
   Web of Science ®Google Scholar
• Khor KX, Chin PJH, Hisyam AR, et al. Development of CR2-Haptic: a compact and portable rehabilitation robot for wrist and forearm training. EEE Conference on Biomedical Engineering and Sciences (IECBES); 2014.
   Google Scholar
• Luu TP, Lim HB, Hoon KH, et al. Subject specific gait parameters prediction for robotic gait rehabilitation via generalized regression neural network. Proceedings of IEEE International Conference on Robotics and Biomimetics; 2011. p. 914–919.
   Google Scholar
• Gholami M, Ejupi A, Rezaei A, et al. Estimation of knee joint angle using a fabric-based strain sensor and machine learning: a preliminary investigation. 7th IEEE International Conference on Biomedical Robotics and Bio mechatronics (Biorob); 2018. p. 589–594.
   Google Scholar