Trajectory-based gait pattern shift detection for assistive robotics applications

  • J. PauloEmail author
  • P. Peixoto
  • P. Amorim
Original Research Paper


In the medical field, rehabilitation of the lower limbs is a slow and continuous process, where healthcare professionals have to follow each patient over long periods of time. In conventional rehabilitation, the progression of a patient is assessed by a professional, who analyzes visual tracking data. This assessment is dependent on each professional’s own experience. In this paper, we propose an approach to analyze tracking data, captured by our robotic walker’s gait tracking system, to detect shifts in the gait pattern over time automatically. For this purpose, the system takes in gait tracking data and segments it into gait cycles (heel strike to heel strike). Then, our approach handles each gait cycle considering it as a group of gait parameters that define trajectories in that time frame. From each gait parameter within the cycle, spatiotemporal features are extracted and similarity rates are computed using autoencoders. These spatiotemporal features and similarity rates are fused in a feature space which is fed to a one-class support vector machine that constructs a model of the observable gait cycle. Each posterior observed gait cycle is checked for shifts, using a set of proposed novelty detection techniques. Experimental tests using a dataset captured using our robotic walker platform revealed a promising performance when detecting if a gait cycle is ‘reference’ or ‘novel’ when compared to a previously trained model of a unique ‘reference’ gait pattern.


Assistive robotics Gait analysis Unsupervised learning Robotic walker 



This work was partially supported by the Portuguese Foundation for Science and Technology (FCT) under the Ph.D. grant with Reference SFRH/BD/88672/2012 with funds from QREN POPH and the European Social Fund from the European Union.


  1. 1.
    Harper S (2014) Ageing societies. Routledge, LondonCrossRefGoogle Scholar
  2. 2.
    WHO \(|\) Rehabilitation in health systemsGoogle Scholar
  3. 3.
    Bloch F, Thibaud M, Dugué B, Brèque C, Rigaud AS, Kemoun G (2010) Episodes of falling among elderly people: a systematic review and meta-analysis of social and demographic pre-disposing characteristics. Clinics 65(9):895CrossRefGoogle Scholar
  4. 4.
    Chou CH, Hwang CL, Wu YT (2012) Effect of exercise on physical function, daily living activities, and quality of life in the frail older adults: a meta-analysis. Arch Phys Med Rehabil 93(2):237CrossRefGoogle Scholar
  5. 5.
    Granger CV, Albrecht GL, Hamilton BB (1979) Outcome of comprehensive medical rehabilitation: measurement by PULSES profile and the Barthel index. Arch Phys Med Rehabil 60(4):145Google Scholar
  6. 6.
    Baker R (2006) Gait analysis methods in rehabilitation. J NeuroEng Rehabil 3(1):1CrossRefGoogle Scholar
  7. 7.
    Iosa M, Cereatti A, Merlo A, Campanini I, Paolucci S, Cappozzo A (2014) Assessment of waveform similarity in clinical gait data: the linear fit method. BioMed Res Int 2014:1–7CrossRefGoogle Scholar
  8. 8.
    Paulo J, Peixoto P, Nunes UJ (2017) ISR-AIWALKER: robotic walker for intuitive and safe mobility assistance and gait analysis. IEEE Trans Hum Mach Syst 47:1110–1122CrossRefGoogle Scholar
  9. 9.
    Paulo J, Asvadi A, Peixoto P, Amorim P (2017) Human gait pattern changes detection system: a multimodal vision-based and novelty detection learning approach. Biocybern Biomed Eng 37(4):701CrossRefGoogle Scholar
  10. 10.
    Perry J, Davids JR et al (1992) Gait analysis: normal and pathological function. J Pediatr Orthop 12(6):815CrossRefGoogle Scholar
  11. 11.
    Öberg T, Karsznia A, Öberg K (1993) Basic gait parameters: reference data for normal subjects, 10–79 years of age. J Rehabil Res Dev 30:210Google Scholar
  12. 12.
    Oberg T, Karsznia A, Oberg K (1994) Joint angle parameters in gait: reference data for normal subjects, 10–79 years of age. J Rehabil Res Dev 31(3):199Google Scholar
  13. 13.
    Melis EH, Torres-Moreno R, Barbeau H, Lemaire ED (1999) Analysis of assisted-gait characteristics in persons with incomplete spinal cord injury. Spinal Cord 37(6):430CrossRefGoogle Scholar
  14. 14.
    Martins M, Elias A, Cifuentes C, Alfonso M, Frizera A, Santos C, Ceres R (2014) Assessment of walker-assisted gait based on principal component analysis and wireless inertial sensors. Rev Bras Eng Bioméd 30(3):220CrossRefGoogle Scholar
  15. 15.
    Mezghani N, Husse S, Boivin K, Turcot K, Aissaoui R, Hagemeister N, De Guise JA (2008) Automatic classification of asymptomatic and osteoarthritis knee gait patterns using kinematic data features and the nearest neighbor classifier. IEEE Trans Biomed Eng 55(3):1230CrossRefGoogle Scholar
  16. 16.
    Djuric-Jovicic MD, Jovicic NS, Radovanovic SM, Stankovic ID, Popovic MB, Kostic VS (2014) Automatic identification and classification of freezing of gait episodes in Parkinson’s disease patients. IEEE Trans Neural Syst Rehabil Eng 22(3):685CrossRefGoogle Scholar
  17. 17.
    Cola G, Avvenuti M, Vecchio A, Yang GZ, Lo B (2015) An on-node processing approach for anomaly detection in gait. IEEE Sens J 15(11):6640CrossRefGoogle Scholar
  18. 18.
    Gardner AB, Krieger AM, Vachtsevanos G, Litt B (2006) One-class novelty detection for seizure analysis from intracranial EEG. J Mach Learn Res 7(Jun):1025MathSciNetzbMATHGoogle Scholar
  19. 19.
    Clifton L, Clifton DA, Watkinson PJ, Tarassenko L (2011) In: 2011 federated conference on computer science and information systems (FedCSIS). IEEE, pp 125–131Google Scholar
  20. 20.
    Pimentel MA, Clifton DA, Tarassenko L (2013) In: 2013 IEEE international workshop on machine learning for signal processing (MLSP). IEEE, pp 1–6Google Scholar
  21. 21.
    Pimentel MA, Clifton DA, Clifton L, Tarassenko L (2014) A review of novelty detection. Signal Process 99:215CrossRefGoogle Scholar
  22. 22.
    Solberg HE, Lahti A (2005) Detection of outliers in reference distributions: performance of Horn’s algorithm. Clin Chem 51(12):2326CrossRefGoogle Scholar
  23. 23.
    Angiulli F, Pizzuti C (2002) In: European conference on principles of data mining and knowledge discovery. Springer, pp 15–27Google Scholar
  24. 24.
    Diaz I, Hollmén J (2002) In: Proceedings of the 2002 international joint conference on neural networks, 2002. IJCNN’02, vol 3. IEEE, pp 2070–2075Google Scholar
  25. 25.
    Tax DM, Duin RP (1999) Support vector domain description. Pattern Recognit Lett 20(11):1191CrossRefGoogle Scholar
  26. 26.
    Schölkopf B, Platt JC, Shawe-Taylor J, Smola AJ, Williamson RC (2001) Estimating the support of a high-dimensional distribution. Neural Comput 13(7):1443CrossRefzbMATHGoogle Scholar
  27. 27.
    Hinton GE (1989) Connectionist learning procedures. Artif intell 40(1):185CrossRefGoogle Scholar
  28. 28.
    Meirovitch Y, Bennequin D, Flash T (2016) Geometrical invariance and smoothness maximization for task-space movement generation. IEEE Trans Robot 32(4):837. CrossRefGoogle Scholar
  29. 29.
    Kosinski RJ (2008) A literature review on reaction time, vol 10. Clemson University, ClemsonGoogle Scholar
  30. 30.
    Müller M (2007) Dynamic time warping. In: Information retrieval for music and motion. Springer, Berlin, pp 69–84.
  31. 31.
    Park SH, Goo JM, Jo CH (2004) Receiver operating characteristic (ROC) curve: practical review for radiologists. Korean J Radiol 5(1):11CrossRefGoogle Scholar
  32. 32.
    Harato K, Nagura T, Matsumoto H, Otani T, Toyama Y, Suda Y (2008) A gait analysis of simulated knee flexion contracture to elucidate knee-spine syndrome. Gait Posture 28(4):687. CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Electrical and Computer Engineering, Institute of Systems and RoboticsUniversity of CoimbraCoimbraPortugal
  2. 2.Rehabilitation Medicine Center of the Centro Region, Rovisco PaisCoimbraPortugal

Personalised recommendations