生物医学工程学杂志

生物医学工程学杂志

偏瘫步态障碍的自动识别和分析

查看全文

本文利用微软公司研发的体感周边外设(Kinect)获取偏瘫患者的步行轨迹数据,在此基础上实现了偏瘫步态的自动识别,并对识别特征的重要性进行了排序。首先,研究设立了试验组和对照组,两组受试者按要求分别完成规定的范式动作,经由 Kinect 实时获取受试者的步行轨迹数据。从获取的数据中可提取步态识别特征:步速、步幅、质心的移动范围(上下和左右方向)。然后,利用贝叶斯分类算法对这些特征构成的样本集进行分类学习,实现偏瘫步态的自动识别。最后,利用随机森林算法确定每个特征的重要性,通过对每个特征的重要性进行排序,可为病情诊断提供参考。本文研究结果表明,基于贝叶斯算法的分类准确率为 96%;使用随机森林算法确定的特征重要性排序为步速、步幅、质心左右偏移距离、质心上下偏移距离,而步速与步幅、步速与质心左右偏移距离的组合是偏瘫步态分析诊断的重要依据。本文研究结果或可为偏瘫步态的智能诊断提供新的思路和参考。

In this paper, the research has been conducted by the Microsoft kinect for windows v2 for obtaining the walking trajectory data from hemiplegic patients, based on which we achieved automatic identification of the hemiplegic gait and sorted the significance of identified features. First of all, the experimental group and two control groups were set up in the study. The three groups of subjects respectively completed the prescribed standard movements according to the requirements. The walking track data of the subjects were obtained straightaway by Kinect, from which the gait identification features were extracted: the moving range of pace, stride and center of mass (up and down and left and right). Then, the bayesian classification algorithm was utilized to classify the sample set of these features so as to automatically recognize the hemiplegia gait. Finally, the random forest algorithm was used to identify the significance of each feature, providing references for the diagnose of disease by ranking the importance of each feature. This thesis states that the accuracy of classification approach based on bayesian algorithm reaches 96%; the sequence of significance based on the random forest algorithm is step speed, stride, left-right moving distance of the center of mass, and up-down moving distance of the center of mass. The combination of step speed and stride, and the combination of step speed and center of mass moving distance are important reference for analyzing and diagnosing of the hemiplegia gait. The results may provide creative mind and new references for the intelligent diagnosis of hemiplegia gait.

关键词: 体感设备 Kinect; 偏瘫步态; 模式识别; 贝叶斯分类; 随机森林

Key words: Kinect; hemiplegia gait; automatic identification; Bayesian classification; random forest

登录后 ,请手动点击刷新查看全文内容。 没有账号,
登录后 ,请手动点击刷新查看图表内容。 没有账号,
1. Ferrarello F, Bianchi V A, Baccini M, et al. Tools for observational gait analysis in patients with stroke: a systematic review. Phys Ther, 2013, 93(12): 1673-1685.
2. Toro B, Nester C, Farren P. A review of observational gait assessment in clinical practice. Physiotherapy Theory and Practice, 2003, 19(3): 137-149.
3. Frenkel T S, Giladi N, Peretz C, et al. Effect of gait speed on gait rhythmicity in parkinson’s disease:variability of stride time and swing time respond differently. J Neuroeng Rehabil, 2005, 2(1): 23-27.
4. Clark R A, Pua Y H, Fortin K, et al. Validity of the microsoft kinect for assessment of postural control. Gait Posture, 2012, 36(3): 372-377.
5. Yeung L F, Cheng K C, Fong C H, et al. Evaluation of the microsoft kinect as a clinical assessment tool of bodysway. Gait Posture, 2014, 40(4): 532-538.
6. Eltoukhy M, Kuenze C, Andersen M S, et al. Prediction of ground reaction forces for Parkinson’s disease patients using a kinect-driven musculoskeletal gait analysis model. Med Eng Phys, 2017, 50: 75-82.
7. Peng Yinghu, Zhang Zhifeng, Gao Yongchang, et al. Concurrent prediction of ground reaction forces and moments and tibiofemoral contact forces during walking using musculoskeletal modelling. Med Eng Phys, 2018, 52: 31-40.
8. Chen Zhenxian, Zhang Zhifeng, Wang Ling, et al. Evaluation of a subject-specific musculoskeletal modelling framework for load prediction in total knee arthroplasty. Med Eng Phys, 2016, 38(8): 708-716.
9. Dolatabadi E, Taati B, Mihailidis A. Concurrent validity of the Microsoft Kinect for Windows v2 for measuring spatiotemporal gait parameters. Med Eng Phys, 2016, 38(9): 952-958.
10. Latorre J, Llorens R, Colomer C, et al. Reliability and comparison of kinect-based methods for estimating spatiotemporal gait parameters of healthy and post-stroke individuals. J Biomech, 2018, 72(27): 268-273.
11. Eltoukhy M M, Kuenze C, Oh J, et al. Microsoft kinect can distinguish differences in over-ground gait between older persons with and without parkinson’s disease. Med Eng Phys, 2017, 44(44): 1-7.
12. Rizzo A, Cukor J, Gerardi M, et al. Virtual reality exposure for PTSD due to military combat and terrorist attacks. Journal of Contemporary Psychotherapy, 2015, 45(4): 255-264.
13. Jack D, Boian R, Merians A S, et al. Virtual reality-enhanced stroke rehabilitation// IEEE Transactions on Neural Systems and Rehabilitation Engineering, IEEE, 2001, 9(3): 308-318.
14. Badler N I. Virtual humans for animation, ergonomics and simulation//IEEE Nonrigid and Articulated Motion Workshop, IEEE, 1997: 28-36.
15. Winter D A. Biomechanics and motor control of human movement: 4th Edition. Canada: John Wiley & Sons, 2009: 327-330.
16. Lafond D, Duarte M, Prince F. Comparison of three methods to estimate the center of mass during balance assessment. J Biomech, 2004, 37(9): 1421-1426.
17. Shotton J, Fitz A, Cook M, et al. Machine learning for computer vision. Berlin: Springer, 2013: 1297-1304.
18. Galna B, Barry G, Jackson D, et al. Accuracy of the microsoft kinect sensor for measuring movement in people with parkin-son’s disease. Gait Posture, 2014, 43(39): 1062-1068.
19. Obdrzalek S, Kurillo G, Ofli F, et al. Accuracy and robustness of kinect pose estimation in the context of coaching of elderly population//2012 Annual International Conference of the IEEE EMBS, San Diego, USA: IEEE, 2012. DOI: 10.1109/EMBC.2012.6346149.