Computer Vision and Machine Learning-Based Gait Pattern Recognition for Flat Fall Prediction

被引:25
作者
Chen, Biao [1 ]
Chen, Chaoyang [2 ]
Hu, Jie [1 ]
Sayeed, Zain [2 ]
Qi, Jin [1 ]
Darwiche, Hussein F. [2 ]
Little, Bryan E. [2 ]
Lou, Shenna [3 ]
Darwish, Muhammad [3 ]
Foote, Christopher [3 ]
Palacio-Lascano, Carlos [3 ]
机构
[1] Shanghai Jiao Tong Univ, State Key Lab Mech Syst & Vibrat, Shanghai 200240, Peoples R China
[2] Detroit Med Ctr, Orthopaed Surg & Sports Med, Detroit, MI 48201 USA
[3] South Texas Hlth Syst McAllen Dept Trauma, Mcallen, TX 78503 USA
基金
中国国家自然科学基金;
关键词
machine learning; gait; pattern recognition; convolutional neural network; support vector machine; long short-time memory; k nearest neighbor; fall recognition; CONVOLUTIONAL NEURAL-NETWORKS; STIFF-KNEE GAIT; NONFATAL FALLS; OLDER-ADULTS; CLASSIFICATION; IMPROVEMENT; QUALITY; KERNEL; CNN;
D O I
10.3390/s22207960
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Background: Gait recognition has been applied in the prediction of the probability of elderly flat ground fall, functional evaluation during rehabilitation, and the training of patients with lower extremity motor dysfunction. Gait distinguishing between seemingly similar kinematic patterns associated with different pathological entities is a challenge for the clinician. How to realize automatic identification and judgment of abnormal gait is a significant challenge in clinical practice. The long-term goal of our study is to develop a gait recognition computer vision system using artificial intelligence (AI) and machine learning (ML) computing. This study aims to find an optimal ML algorithm using computer vision techniques and measure variables from lower limbs to classify gait patterns in healthy people. The purpose of this study is to determine the feasibility of computer vision and machine learning (ML) computing in discriminating different gait patterns associated with flat-ground falls. Methods: We used the Kinect (R) Motion system to capture the spatiotemporal gait data from seven healthy subjects in three walking trials, including normal gait, pelvic-obliquity-gait, and knee-hyperextension-gait walking. Four different classification methods including convolutional neural network (CNN), support vector machine (SVM), K-nearest neighbors (KNN), and long short-term memory (LSTM) neural networks were used to automatically classify three gait patterns. Overall, 750 sets of data were collected, and the dataset was divided into 80% for algorithm training and 20% for evaluation. Results: The SVM and KNN had a higher accuracy than CNN and LSTM. The SVM (94.9 +/- 3.36%) had the highest accuracy in the classification of gait patterns, followed by KNN (94.0 +/- 4.22%). The accuracy of CNN was 87.6 +/- 7.50% and that of LSTM 83.6 +/- 5.35%. Conclusions: This study revealed that the proposed AI machine learning (ML) techniques can be used to design gait biometric systems and machine vision for gait pattern recognition. Potentially, this method can be used to remotely evaluate elderly patients and help clinicians make decisions regarding disposition, follow-up, and treatment.
引用
收藏
页数:22
相关论文
共 89 条
[1]   Hip circumduction is not a compensation for reduced knee flexion angle during gait [J].
Akbas, Tunc ;
Prajapati, Sunil ;
Ziemnicki, David ;
Tamma, Poornima ;
Gross, Sarah ;
Sulzer, James .
JOURNAL OF BIOMECHANICS, 2019, 87 :150-156
[2]  
Alaskar H, 2018, INT J ADV COMPUT SC, V9, P486
[3]   Evaluation of the Pose Tracking Performance of the Azure Kinect and Kinect v2 for Gait Analysis in Comparison with a Gold Standard: A Pilot Study [J].
Albert, Justin Amadeus ;
Owolabi, Victor ;
Gebel, Arnd ;
Brahms, Clemens Markus ;
Granacher, Urs ;
Arnrich, Bert .
SENSORS, 2020, 20 (18) :1-22
[4]   AN INTRODUCTION TO KERNEL AND NEAREST-NEIGHBOR NONPARAMETRIC REGRESSION [J].
ALTMAN, NS .
AMERICAN STATISTICIAN, 1992, 46 (03) :175-185
[5]   Review of deep learning: concepts, CNN architectures, challenges, applications, future directions [J].
Alzubaidi, Laith ;
Zhang, Jinglan ;
Humaidi, Amjad J. ;
Al-Dujaili, Ayad ;
Duan, Ye ;
Al-Shamma, Omran ;
Santamaria, J. ;
Fadhel, Mohammed A. ;
Al-Amidie, Muthana ;
Farhan, Laith .
JOURNAL OF BIG DATA, 2021, 8 (01)
[6]   Analysis of gait synchrony and balance in neurodevelopmental disorders using computer vision techniques [J].
Ardalan, Adel ;
Yamane, Natasha ;
Rao, Ashwini K. ;
Montes, Jacqueline ;
Goldman, Sylvie .
HEALTH INFORMATICS JOURNAL, 2021, 27 (04)
[7]   Preventing falls: the use of machine learning for the prediction of future falls in individuals without history of fall [J].
Bargiotas, Ioannis ;
Wang, Danping ;
Mantilla, Juan ;
Quijoux, Flavien ;
Moreau, Albane ;
Vidal, Catherine ;
Barrois, Remi ;
Nicolai, Alice ;
Audiffren, Julien ;
Labourdette, Christophe ;
Bertin-Hugaul, Francois ;
Oudre, Laurent ;
Buffat, Stephane ;
Yelnik, Alain ;
Ricard, Damien ;
Vayatis, Nicolas ;
Vidal, Pierre-Paul .
JOURNAL OF NEUROLOGY, 2023, 270 (02) :618-631
[8]  
Boser B. E., 1992, Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, P144, DOI 10.1145/130385.130401
[9]   The direct costs of fatal and non-fatal falls among older adults - United States [J].
Burns, Elizabeth R. ;
Stevens, Judy A. ;
Lee, Robin .
JOURNAL OF SAFETY RESEARCH, 2016, 58 :99-103
[10]   A method to differentiate the causes of stiff-knee gait in stroke patients [J].
Campanini, I. ;
Merlo, A. ;
Damiano, B. .
GAIT & POSTURE, 2013, 38 (02) :165-169