Random forest-based classsification and analysis of hemiplegia gait using low-cost depth cameras

被引:20
作者
Luo, Guoliang [1 ]
Zhu, Yean [1 ]
Wang, Rui [1 ]
Tong, Yang [1 ]
Lu, Wei [2 ]
Wang, Haolun [1 ]
机构
[1] E China Jiaotong Univ, Nanchang, Peoples R China
[2] Jiangxi Prov People's Hosp, Nanchang, Peoples R China
基金
中国国家自然科学基金;
关键词
Depth cameras; Microsoft Kinect; Hemiplegia; Gait analysis; Random forest; Motion classification; MICROSOFT KINECT; CONCURRENT VALIDITY; CLASSIFICATION; STROKE;
D O I
10.1007/s11517-019-02079-7
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Hemiplegia is a form of paralysis that typically has the symptom of dysbasia. In current clinical rehabilitations, to measure the level of hemiplegia gaits, clinicians often conduct subject evaluations through observations, which is unreliable and inaccurate. The Microsoft Kinect sensor (MS Kinect) is a widely used, low-cost depth sensor that can be used to detect human behaviors in real time. The purpose of this study is to investigate the usage of the Kinect data for the classification and analysis of hemiplegia gait. We first acquire the gait data by using a MS Kinect and extract a set of gait features including the stride length, gait speed, left/right moving distances, and up/down moving distances. With the gait data of 60 subjects including 20 hemiplegia patients and 40 healthy subjects, we employ a random forest-based classification approach to analyze the importances of different gait features for hemiplegia classification. Thanks to the over-fitting avoidance nature of the random forest approach, we do not need to have a careful control over the percentage of patients in the training data. In our experiments, our approach obtained the averaged classification accuracy of 90.65% among all the combinations of the gait features, which substantially outperformed state-of-the-art methods. The best classification accuracy of our approach is 95.45%, which is superior than all existing methods. Additionally, our approach also correctly reveals the importance of different gait features for hemiplegia classification. Our random forest-based approach outperforms support vector machine-based method and the Bayesian-based method, and can effectively extract gait features of subjects with hemiplegia for the classification and analysis of hemiplegia. Random Forest based Classsification and Analysis of Hemiplegia Gait using Low-cost Depth Cameras. Left: Motion capture with MS Kinect; Top-right: Random Forest Classsification based on the extracted gait features; Bottom-right: Sensitivity and specificity evaluation of the proposed classification approach.
引用
收藏
页码:373 / 382
页数:10
相关论文
共 38 条
[11]  
Dikovski B, 2014, 2014 37TH INTERNATIONAL CONVENTION ON INFORMATION AND COMMUNICATION TECHNOLOGY, ELECTRONICS AND MICROELECTRONICS (MIPRO), P1304, DOI 10.1109/MIPRO.2014.6859769
[12]   Concurrent validity of the Microsoft Kinect for Windows v2 for measuring spatiotemporal gait parameters [J].
Dolatabadi, Elham ;
Taati, Babak ;
Mihailidis, Alex .
MEDICAL ENGINEERING & PHYSICS, 2016, 38 (09) :952-958
[13]  
Dyukova GM, 2007, ZH NEVROL PSIKHIATR, V107, P4
[14]   Prediction of ground reaction forces for Parkinson's disease patients using a kinect-driven musculoskeletal gait analysis model [J].
Eltoukhy, Moataz ;
Kuenze, Christopher ;
Andersen, Michael S. ;
Oh, Jeonghoon ;
Signorile, Joseph .
MEDICAL ENGINEERING & PHYSICS, 2017, 50 :75-82
[15]   Microsoft Kinect can distinguish differences in over-ground gait between older persons with and without Parkinson's disease [J].
Eltoukhy, Moataz ;
Kuenze, Christopher ;
Oh, Jeonghoon ;
Jacopetti, Marco ;
Wooten, Savannah ;
Signorile, Joseph .
MEDICAL ENGINEERING & PHYSICS, 2017, 44 :1-7
[16]   An introduction to ROC analysis [J].
Fawcett, Tom .
PATTERN RECOGNITION LETTERS, 2006, 27 (08) :861-874
[17]   Tools for Observational Gait Analysis in Patients With Stroke: A Systematic Review [J].
Ferrarello, Francesco ;
Bianchi, Valeria Anna Maria ;
Baccini, Marco ;
Rubbieri, Gaia ;
Mossello, Enrico ;
Cavallini, Maria Chiara ;
Marchionni, Niccolo ;
Di Bari, Mauro .
PHYSICAL THERAPY, 2013, 93 (12) :1673-1685
[18]   Effect of gait speed on gait rhythmicity in Parkinson's disease: Variability of stride time and swing time respond differently [J].
Frenkel-Toledo S. ;
Giladi N. ;
Peretz C. ;
Herman T. ;
Gruendlinger L. ;
Hausdorff J.M. .
Journal of NeuroEngineering and Rehabilitation, 2 (1)
[19]   Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson's disease [J].
Galna, Brook ;
Barry, Gillian ;
Jackson, Dan ;
Mhiripiri, Dadirayi ;
Olivier, Patrick ;
Rochester, Lynn .
GAIT & POSTURE, 2014, 39 (04) :1062-1068
[20]   A robust real-time gait event detection using wireless gyroscope and its application on normal and altered gaits [J].
Gouwanda, Darwin ;
Gopalai, Alpha Agape .
MEDICAL ENGINEERING & PHYSICS, 2015, 37 (02) :219-225