Recognition of motion patterns using accelerometers for ataxic gait assessment

Abstract

The recognition of motion patterns belongs to very important research areas related to neurology, rehabilitation, and robotics. It is based on modern sensor technologies and general mathematical methods, multidimensional signal processing, and machine learning. The present paper is devoted to the detection of features associated with accelerometric data acquired by 31 time-synchronized sensors located at different parts of the body. Experimental data sets were acquired from 25 individuals diagnosed as healthy controls and ataxic patients. The proposed method includes the application of the discrete Fourier transform for the estimation of the mean power in selected frequency bands and the use of these features for data segments classification. The study includes a comparison of results obtained from signals recorded at different positions. Evaluations are based on classification accuracy and cross-validation errors estimated by support vector machine, Bayesian, nearest neighbours (k-NN], and neural network (NN) methods. Results show that highest accuracies of 77.1%, 78.9%, 89.9%, 98.0%, and 98.5% were achieved by NN method for signals acquired from the sensors on the feet, legs, uplegs, shoulders, and head/spine, respectively, recorded in 201 signal segments. The entire study is based on observations in the clinical environment and suggests the importance of augmented reality to decisions and diagnosis in neurology.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

References

  1. 1.

    Allseits E, Kim K, Bennett C, Gailey R, Gaunaurd I, Agrawal V (2018) A novel method for estimating knee angle using two leg-mounted gyroscopes for continuous monitoring with mobile health devices. Sensors 18:2759:1–2759:17

    Google Scholar 

  2. 2.

    Almaslukh B, Artoli A, Al-Muhtadi J (2018) A robust deep learning approach for position-independent smartphone-based human activity recognition. Sensors 18(11):3726

    Google Scholar 

  3. 3.

    Alvarez D, Alvarez J, Gonzalez R, Lopez A (2015) Upper limb joint angle measurement in occupational health. Comput Methods Biomech Biomed Eng 19(2):1–12

    Google Scholar 

  4. 4.

    Antoniades A, Spyrou L, Martin-Lopez D, Valentin A, Alarcon G, Sanei S, Took C (2017) Detection of interictal discharges with convolutional neural networks using discrete ordered multichannel intracranial EEG. IEEE Trans Neural Syst Rehabil Eng 25(12):2285–2294

    Google Scholar 

  5. 5.

    Baumann T, Hao T, He Y, Shoda R (2017) Perception neuron unity handbook, 027th edn. Noitom Technology Co. Ltd, St Miami

    Google Scholar 

  6. 6.

    Buckley C, Alcock L, McArdle R, Rehman R, Din S, Mazzà C, Yarnall AJ, Rochester L (2019) The role of movement analysis in diagnosing and monitoring neurodegenerative conditions: insights from gait and postural control. MDPI Br Sci 19:34:1–34:21

    Google Scholar 

  7. 7.

    Buckley E, Mazza C, McNeill A (2018) A systematic review of the gait characteristics associated with Cerebellar Ataxia. Gait Posture 60:154–163

    Google Scholar 

  8. 8.

    Caliandro P, Conte C, Iacovelli C, Tatarelli A, Castiglia S, Reale G, Serrao M (2019) Exploring risk of falls and dynamic unbalance in cerebellar ataxia by inertial sensor assessment. Sensors 19(24):5571:1–5571:9

    Google Scholar 

  9. 9.

    Caramia C, Torricelli D, Schmid M, Munoz-Gonzalez A, Gonzalez-Vargas J, Grandas F, Pons J (2018) IMU-based classification of Parkinson’s disease from gait: a sensitivity analysis on sensor location and feature selection. IEEE J Biomed Health Inf 22(6):1765–1774

    Google Scholar 

  10. 10.

    Chambon S, Galtier M, Arnal P, Wainrib G, Gramfort A (2018) A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series. IEEE Trans Neural Syst Rehabil Eng 26(4):758–769

    Google Scholar 

  11. 11.

    Chen P, Kuang Y, Li J (2016) Human motion capture algorithm based on inertial sensors. J Sens 2016:4343,797:1–4343,797:15

    Google Scholar 

  12. 12.

    Chen Y, Shen C (2017) Performance analysis of smartphone-sensor behavior for human activity recognition. IEEE Access 5:3095–3110

    Google Scholar 

  13. 13.

    D’Ambrosio A, Pagani E, Riccitelli G, Colombo B, Rodegher M, Falini A, Comi G, Filippi M, Rocca M (2017) Cerebellar contribution to motor and cognitive performance in multiple sclerosis: an MRI sub-regional volumetric analysis. Mult Scler 23(9):1194–1203

    Google Scholar 

  14. 14.

    Diener H, Dichgans J, Bacher M, Guschlbauer B (1984) Characteristic alterations of long-loop ”reflexes” in patients with Friedreich’s disease and late atrophy of the cerebellar anterior lobe. J Neurol Neurosurg Psych 47(7):679–685

    Google Scholar 

  15. 15.

    Din S, Hickey A, Hurwitz N, Mathers J, Rochester L, Godfrey A (2016) Measuring gait with an accelerometer-based wearable: influence of device location, testing protocol and age. Physiol Meas 37:1785–1797

    Google Scholar 

  16. 16.

    Ebara T, Azuma R, Shoji N, Matsukawa T, Yamada Y, Akiyama T, Kurihara T, Yamada S (2017) Reliability of smartphone-based gait measurements for quantification of physical activity/inactivity levels. J Occup Health 59(6):506–512

    Google Scholar 

  17. 17.

    Ellis K, Kerr J, Godbole S, Lanckriet G, Wing D, Marshall S (2014) A random forest classifier for the prediction of energy expenditure and type of physical activity from wrist and hip accelerometers. Physiol Meas 35(11):2191–2203

    Google Scholar 

  18. 18.

    Fuentes D, Gonzalez-Abril L, Angulo C, Orteg J (2012) Online motion recognition using an accelerometer in a mobile device. Expert Syst Appl 39(3):2461–2465

    Google Scholar 

  19. 19.

    Ghislieri M, Gastaldi L, Pastorelli S, Tadano S, Agostini V (2019) Wearable inertial sensors to assess standing balance: a systematic review. Sensors 19:4075:1–4075:25

    Google Scholar 

  20. 20.

    Goldsztein G (2017) Modeling walking with an inverted pendulum not constrained to the sagittal plane. Numerical simulations and asymptotic expansions. Appl Math 8:57–76

    Google Scholar 

  21. 21.

    Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, Cambridge

    Google Scholar 

  22. 22.

    Grimaldi G, Manto M (2010) Neurological tremor: sensors, signal processing and emerging applications. MDPI Sens 10:1399–1422

    Google Scholar 

  23. 23.

    Hasegawa N, Shah V, Carlson-Kuhta P, Nutt J, Horak F, Mancini M (2019) How to select balance measures sensitive to Parkinsons disease from body worn inertial sensors separating the trees from the forest. Sensors 19:3320:1–3320:18

    Google Scholar 

  24. 24.

    Hong F, You S, Wei M, Zhang Y, Guo Z (2016) OMGRA: motion gesture recognition via accelerometer. MDPI Sens 16:530:1–531:25

    Google Scholar 

  25. 25.

    Hošťálková E, Vyšata O, Procházka A (2007) Multi-dimensional biomedical image de-noising using Haar transform. In: Proceedings of the 15th international conference on digital signal processing. IEEE, Cardiff, UK, pp 175–179

  26. 26.

    Ishikawa M, Yamada S, Yamamoto K, Aoyagi Y (2019) Gait analysis in a component timed-up-and-go test using a smartphone application. J Neurol Sci 398:45–49

    Google Scholar 

  27. 27.

    Joukov V, Bonnet V, Karg M, Venture G, Kulic D (2018) Rhythmic extended Kalman filter for gait rehabilitation motion estimation and segmentation. IEEE Trans Neural Syst Rehabil Eng 26(2):407–418

    Google Scholar 

  28. 28.

    Kim H, Hong N, Kim M, Yoon S, Yu H, Kong H, Kim S, Chai Y, Choi H, Choi J, Lee K, Kim S, Kim H (2019) Application of a perception neuron system in simulation-based surgical training. MDPI J Clin Med 8:124:1–124:14

    Google Scholar 

  29. 29.

    Krishna R, Pathirana P, Horne M, Power L, Szmulewicz D (2019) Quantitative assessment of cerebellar ataxia, through automated limb functional tests. J Neuroeng Rehabil 16:31:1–31:15

    Google Scholar 

  30. 30.

    Kusumoputro B, Lina B (2016) Infrared face recognition system using cross entropy error function based ensemble backpropagation neural networks. IJCTE 8:161–166

    Google Scholar 

  31. 31.

    Li H, Trocan M (2018) Deep learning of smartphone sensor data for personal health assistance. Microelectron J 88:164–172

    Google Scholar 

  32. 32.

    López A, Ferrero F, Postolache O (2019) An affordable method for evaluation of ataxic disorders based on electrooculography. MDPI Sens 19(17):3756:1–3756:16

    Google Scholar 

  33. 33.

    Marsden JF (2018) Chapter 17—Cerebellar ataxia. In: Day BL, Lord SR (eds) Balance, gait, and falls, handbook of clinical neurology, vol 159. Elsevier, Amsterdam, pp 261–281

    Google Scholar 

  34. 34.

    Nguyen N, Phan D, Pathirana P, Horne M, Power L, Szmulewicz D (2018) Quantification of axial abnormality due to cerebellar ataxia with inertial measurements. Sensors 18(9):2791:1–2791:15

    Google Scholar 

  35. 35.

    Ohashi H, Al-Naser M, Ahmed S, Nakamura K, Sato T, Dengel A (2018) Attributes importance for zero-shot pose-classification based on wearable sensors. MDPI Sens 18(8):2485:1–2485:17

    Google Scholar 

  36. 36.

    Petersen N, Christensen L, Morita H, Sinkjaer T, Nielsen J (1998) Evidence that a transcortical pathway contributes to stretch reflexes in the tibialis anterior muscle in man. J Physiol 512(1):267–276

    Google Scholar 

  37. 37.

    Phan D, Nhan N, Pathirana P, Horne M, Power L, Szmulewicz D (2019) Quantitative assessment of ataxic gait using inertial sensing at different walking speeds. In: IEEE engineering in medicine and biology, EMBC, pp 4600–4603

  38. 38.

    Procházka A, Charvátová H, Vaseghi S, Vyšata O (2018) Machine learning in rehabilitation assessment for thermal and heart rate data processing. IEEE Trans Neural Syst Rehabil Eng 26(6):1209–1214

    Google Scholar 

  39. 39.

    Procházka A, Charvátová H, Vyšata O, Kopal J, Chambers J (2017) Breathing analysis using thermal and depth imaging camera video records. MDPI Sens 17:1408:1–1408:10

    Google Scholar 

  40. 40.

    Procházka A, Schatz M, Centonze F, Kuchyňka J, Vyšata O, Vališ M (2016) Extraction of breathing features using MS Kinect for sleep stage detection. Signal Image Video Process 10(7):1278–1286

    Google Scholar 

  41. 41.

    Procházka A, Vyšata O, Charvátová H, Vališ M (2019) Motion symmetry evaluation using accelerometers and energy distribution. Symmetry 11:871:1–871:13

    Google Scholar 

  42. 42.

    Procházka A, Vyšata O, Vališ M, Tupa O, Schatz M, Mařík V (2015) Bayesian classification and analysis of gait disorders using image and depth sensors of Microsoft Kinect. Digit Signal Process 47(12):169–177

    MathSciNet  Google Scholar 

  43. 43.

    Rizzo G, Copetti M, Arcuti S, Martino D, Fontana A, Logroscino G (2016) Accuracy of clinical diagnosis of Parkinson disease: A systematic review and meta-analysis. Neurology 86(3):566–576

    Google Scholar 

  44. 44.

    Roche B, Simon A, Guilmin-Crépon S, Boizeau B, Andriss B, Alberti C, Presedo A, Ilharreborde B, Husson I (2018) Test-retest reliability of an instrumented electronic walkway system (GAITRite) for the measurement of spatio-temporal gait parameters in young patients with Friedreich’s ataxia. Gait Posture 66:45–50

    Google Scholar 

  45. 45.

    Sadouk L, Gadi T (2019) Convolutional neural networks for human activity recognition in time and frequency-domain. Adv Intell Syst Comput 756:485–496

    Google Scholar 

  46. 46.

    Sanei S, Chambers J (2007) EEG signal processing. Wiley, New York

    Google Scholar 

  47. 47.

    Staab W, Hottowitz R, Sohns C, Sohns J, Gilbert F, Menke J, Niklas A, Lotz J (2014) Accelerometer and gyroscope based gait analysis using spectral analysis of patients with osteoarthritis of the knee. J Phys Ther Sci 26:997–1002

    Google Scholar 

  48. 48.

    Stolze H (2002) Typical features of cerebellar ataxic gait. J Neurol Neurosurg Psych 73:310–312

    Google Scholar 

  49. 49.

    Sun B, Wang Y, Banda J (2014) Gait characteristic analysis and identification based on the iphone accelerometer and gyrometer. Sensors 18:17037–17054

    Google Scholar 

  50. 50.

    Voicu R, Dobre C, Bajenaru L, Ciobanu R (2019) Human physical activity recognition using smartphone sensors. MDPI Sens 19:458:1–4581:18

    Google Scholar 

  51. 51.

    Wang J, Chen Y, Hao S, Peng X, Hu L (2019) Deep learning for sensor-based activity recognition: a survey. Pattern Recognit Lett 119:3–11

    Google Scholar 

  52. 52.

    Xu R, Zhou S, Li W (2012) MEMS accelerometer based nonspecific-user hand gesture recognition. IEEE Sens J 12:1166–1173

    Google Scholar 

  53. 53.

    Zilani T, Al-Turjman F, Khan M, Zhao N, Yang X (2020) Monitoring movements of ataxia patient by using UWB technology. MDPI Sens 20:931:1–931:16

    Google Scholar 

Download references

Acknowledgements

This research was supported by grant projects of the Ministry of Health of the Czech Republic (FN HK 00179906) and of the Charles University in Prague, Czech Republic (PROGRES Q40), as well as by the project PERSONMED—Centre for the Development of Personalized Medicine in Age-Related Diseases, Reg. No. CZ.02.1.01-0.0-0.0-17_048-0007441, co-financed by the European Regional Development Fund (ERDF), the governmental budget of the Czech Republic, and grant INTER-ACTION LTAIN19007.

Author information

Affiliations

Authors

Contributions

OD recorded all data and was responsible for their evaluation, AP was responsible for the mathematical and algorithmic tools, OV interpreted results from the neurological point of view, OT contributed to data preprocessing, PC contributed to evaluation of results, and MV was responsible for correct diagnostications of patients. All authors have read and approved the final manuscript.

Corresponding author

Correspondence to Aleš Procházka.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interests regarding the publication of this article.

Ethical approval

All procedures involving human participants were in accordance with the ethical standards of the institutional research committee and with the 1964 Helsinki Declaration and its later amendments.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Dostál, O., Procházka, A., Vyšata, O. et al. Recognition of motion patterns using accelerometers for ataxic gait assessment. Neural Comput & Applic (2020). https://doi.org/10.1007/s00521-020-05103-2

Download citation

Keywords

  • Multidimensional signal analysis
  • Computational intelligence
  • Machine learning
  • Accelerometers
  • Ataxic gait
  • Motion classification