Skip to main content

Advertisement

SpringerLink
Log in

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

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

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.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Pettigrew LC, Jankovic J (1985) Hemidystonia: a report of 22 patients and a review of the literature. J Neurol Neurosurg Psych 48(7):650–657

    Article  CAS  Google Scholar 

  2. Gm D, EIu T (2007) Quantitative indices of gait in patients with psychogenic and organic dysbasia. Zhurnal Nevrol Psikh Imeni Korsakova 107(7):4

    Google Scholar 

  3. Neckel ND, Blonien N, Nichols D et al (2008) Abnormal joint torque patterns exhibited by chronic stroke subjects while walking with a prescribed physiological gait pattern. J Neuroeng Rehab 5:19

    Article  Google Scholar 

  4. Henrik SJ, Nakayama H, Raaschou HO et al (1995) Recovery of walking function in stroke patients: the copenhagen stroke study. Arch Phys Med Rehabil 76(1):27–32

    Article  Google Scholar 

  5. Toro B, Nester C, Farren P (2003) A review of observational gait assessment in clinical practice. Phys Theory Pract 19:137–149

    Article  Google Scholar 

  6. Wade DT, Langton-Hewer R, Wood VA, Skilbeck CE, Ismail HM (1983) The hemiplegic arm after stroke: measurement and recovery. J Neurol Neurosur Psych 46(6):521–524

    Article  CAS  Google Scholar 

  7. Pizzi A, Carlucci G, Falsini C, Lunghi F, Verdesca S, Grippo A (2007) Gait in hemiplegia: evaluation of clinical features with the Wisconsin Gait Scale. J Rehabil Med 39(2):170–174

    Article  Google Scholar 

  8. Frenkel-Toledo S, Giladi N, Peretz C et al (2005) Effect of gait speed on gait rhythmicity in Parkinson’s disease: variability of stride time and swing time respond differently. J NeuroEng Rehab 2:23–30

    Article  Google Scholar 

  9. McGinley JL, Baker R, Wolfe R, Morris ME (2009) The reliability of three-dimensional kinematic gait measurements: a systematic review. Gait Posture 29(3):360–369

    Article  Google Scholar 

  10. Zijlstra W, Hof AL (2003) Assessment of spatio-temporal gait parameters from trunk accelerations during human walking. Gait Posture 18(2):1–10

    Article  Google Scholar 

  11. Gouwanda D, Gopalai AA (2015) A robust real-time gait event detection using wireless gyroscope and its application on normal and altered gaits. Med Eng Phys 37(2):219–225

    Article  Google Scholar 

  12. Krzak JJ, Corcos DM, Damiano DL, Graf A, Hedeker D, Smith PA, Harris GF (2015) Kinematic foot types in youth with equinovarus secondary to hemiplegia. Gait Posture 41(2):402–408

    Article  Google Scholar 

  13. Ferrarello F, Bianchi VAM, Baccini M et al (2013) Tools for observational gait analysis in patients with stroke: a systematic review. Phys Ther 93(12):1673–1685

    Article  Google Scholar 

  14. Tao W, Liu T, Zheng R, Feng H (2012) Gait analysis using wearable sensors. Sensors 12(2):2255–2283

    Article  Google Scholar 

  15. Liu T, Inoue Y, Shibata K (2009) Development of a wearable sensor system for quantitative gait analysis. Measurement 42(7):978–988

    Article  Google Scholar 

  16. Winter DA (1995) Human balance and posture control during standing and walking. Gait Posture 3(4):193–214

    Article  Google Scholar 

  17. Pfister A, West AM, Bronner S, Noah JA (2014) Comparative abilities of Microsoft Kinect and Vicon 3D motion capture for gait analysis. J Med Eng Technol 38(5):274–280

    Article  Google Scholar 

  18. Clark RA, Pua Y-H, Fortin K, Ritchie C, Webster KE, Denehy L, Bryant AL (2012) Validity of the Microsoft Kinect for assessment of postural control. Gait Posture 36(3):372–377

    Article  Google Scholar 

  19. Galna B, Barry G, Jackson D et al (2014) Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson’s disease. Gait Posture 39(4):1062–1068

    Article  Google Scholar 

  20. Eltoukhy M, Kuenze C, Oh J et al (2017) Microsoft Kinect can distinguish differences in over-ground gait between older persons with and without Parkinson’s disease. Med Eng Phys 44:1–17

    Article  Google Scholar 

  21. Eltoukhy M, Kuenze C, Andersen MS et al (2017) Prediction of ground reaction forces for Parkinson’s disease patients using a Kinect-driven musculoskeletal gait analysis model. Med Eng Phys 50:75–82

    Article  Google Scholar 

  22. Prochazka A, Vysata O, Valis M (2015) Bayesian classification and analysis of gait disorders using image and depth sensors of microsoft kinect. Digit Signal Process 47:169–177

    Article  Google Scholar 

  23. Asaeda M, Kuwahara W, Fujita N, Yamasaki T, Adachi N (2018) Validity of motion analysis using the Kinect system to evaluate single leg stance in patients with hip disorders. Gait Posture 62:458–462

    Article  Google Scholar 

  24. Dolatabadi E, Taati B, Mihailidis A (2016) Concurrent validity of the Microsoft Kinect for Windows v2 for measuring spatiotemporal gait parameters. Med Eng Phys 38(9):952–958

    Article  Google Scholar 

  25. Clark RA, Bower K, Mentiplay B, Paterson KL, Pua YH (2013) Concurrent validity of the Microsoft Kinect for assessment of spatiotemporal gait variables. J Biomech 46(15):2722–2725

    Article  Google Scholar 

  26. Clark RA, Vernon S, Mentiplay BF, Miller KJ, McGinley JL, Pua YH, Paterson K, Bower KJ (2015) Instrumenting gait assessment using the Kinect in people living with stroke: reliability and association with balance tests. J NeuroEng Rehab 12(1):15–15

    Article  Google Scholar 

  27. Darby J, Sánchez MB, Butler PB, Loram ID (2016) An evaluation of 3D head pose estimation using the Microsoft Kinect v2. Gait Posture 48:83–88

    Article  Google Scholar 

  28. Ťupa O, Prochazka A, Vysataand O et al (2015) Motion tracking and gait feature estimation for recognising Parkinson’s disease using ms kinect. Biomed Eng Online 14(1):97–97

    Article  Google Scholar 

  29. Yeung LF, Cheng KC, Fong CH et al (2014) Evaluation of the Microsoft Kinect as a clinical assessment tool of body sway. Gait Posture 40(4):532–538

    Article  CAS  Google Scholar 

  30. Liaw A, Wiener M (2002) Classification and regression by randomForest. R News 2(3):18–22

    Google Scholar 

  31. Strobl C, Boulesteix A-L, Augustin T (2007) Unbiased split selection for classification trees based on the Gini Index. Comput Stat Data Anal 52(1):483–501

    Article  Google Scholar 

  32. Salzberg SL (1994) C4.5: Programs for machine learning by J. Ross Quinlan. Morgan Kaufmann Publishers, Inc., 1993. Mach Learn 16(3):235–240. ISSN 1573-0565

    Google Scholar 

  33. Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27(8):861–874

    Article  Google Scholar 

  34. Mason SJ, Graham NE (2002) Areas beneath the relative operating characteristics (ROC) and relative operating levels (ROL) curves: statistical significance and interpretation. Q J R Meteorol Soc 128(584):2145–2166

    Article  Google Scholar 

  35. Begg RK, Palaniswami M, Owen B (2005) Support vector machines for automated gait classification. IEEE Trans Biomed Eng 52(5):828–838

    Article  Google Scholar 

  36. Dikovski B, Madjarov G, Gjorgjevikj D (2014) Evaluation of different feature sets for gait recognition using skeletal data from kinect. In: 2014 37th International Convention on Information and communication technology, Electronics and Microelectronics (MIPRO), pp 1304–1308

  37. Bengio Y, Grandvalet Y (2004) No unbiased estimator of the variance of k-fold cross-validation. J Mach Learn Res 5:1089–1105. https://academic.microsoft.com/paper/1517808374

    Google Scholar 

  38. Buhmann MD (2003) Radial basis functions: theory and implementations. https://academic.microsoft.com/paper/1597405158

Download references

Funding

This work has been supported by the National Science Fund of China (Nos. 61962021, 61602222), the Key R&D Fund of Jiangxi Province (No. 20192BBE50079), and the Nature Science Fund of Jiangxi Province (No. 20171BAB212011).

Author information

Authors and Affiliations

  1. East China Jiaotong University, Nanchang, China

    Guoliang Luo, Yean Zhu, Rui Wang, Yang Tong & Haolun Wang

  2. Jiangxi Provincial People’s Hospital, Nanchang, China

    Wei Lu

Authors
  1. Guoliang Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yean Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rui Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yang Tong
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Wei Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Haolun Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Haolun Wang.

Ethics declarations

The data acquisitions have been conducted in the Rehabilitation Medicine Department of Jiangxi People’s Hospital, approved by the local ethics committee. Each participant also had signed an informed consent form.

Conflict of interest

The authors declare that they have no conflicts of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

(MOV 37.4 MB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Luo, G., Zhu, Y., Wang, R. et al. Random forest–based classsification and analysis of hemiplegia gait using low-cost depth cameras. Med Biol Eng Comput 58, 373–382 (2020). https://doi.org/10.1007/s11517-019-02079-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-019-02079-7

Keywords

Search

Navigation