Detecting freezing of gait with a tri-axial accelerometer in Parkinson’s disease patients


Freezing of gait (FOG) is a common motor symptom of Parkinson’s disease (PD), which presents itself as an inability to initiate or continue gait. This paper presents a method to monitor FOG episodes based only on acceleration measurements obtained from a waist-worn device. Three approximations of this method are tested. Initially, FOG is directly detected by a support vector machine (SVM). Then, classifier’s outputs are aggregated over time to determine a confidence value, which is used for the final classification of freezing (i.e., second and third approach). All variations are trained with signals of 15 patients and evaluated with signals from another 5 patients. Using a linear SVM kernel, the third approach provides 98.7 % accuracy and a geometric mean of 96.1 %. Moreover, it is investigated whether frequency features are enough to reliably detect FOG. Results show that these features allow the method to detect FOG with accuracies above 90 % and that frequency features enable a reliable monitoring of FOG by using simply a waist sensor.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2


  1. 1.

    Andlin-Sobocki P, Jnsson B, Wittchen HU, Olesen J (2005) Cost of disorders of the brain in Europe. Eur J Neurol 12:1–27. doi:10.1111/j.1468-1331.2005.01202.x

    Article  PubMed  Google Scholar 

  2. 2.

    Armstrong RA (2008) Visual signs and symptoms of Parkinson’s disease. Clin Exp Optom 91(2):129–138. doi:10.1111/j.1444-0938.2007.00211.x

    Article  PubMed  Google Scholar 

  3. 3.

    Bächlin M, Plotnik M, Roggen D, Giladi N, Hausdorff JM, Tröster G (2010) A wearable system to assist walking of Parkinson’s disease patients. Methods Inf Med 49(1):88–95. doi:10.3414/ME09-02-0003.

  4. 4.

    Bächlin M, Plotnik M, Roggen D, Maidan I, Hausdorff JM, Giladi N, Troster G (2010) Wearable assistant for Parkinson’s disease patients with the freezing of gait symptom. IEEE Trans Inf Technol Biomed 14(2):436–446. doi:10.1109/TITB.2009.2036165

    Article  PubMed  Google Scholar 

  5. 5.

    Bächlin M, Roggen D, Troster G, Plotnik M, Inbar N, Meidan I, Herman T, Brozgol M, Shaviv E, Giladi N, Hausdorff JM (2009) Potentials of enhanced context awareness in wearable assistants for Parkinson’s disease patients with the freezing of gait syndrome. In: 2009 International Symposium on Wearable Computers (ISWC), pp 123–13. doi:10.1109/ISWC.2009.14

  6. 6.

    Bloem BR, Hausdorff JM, Visser JE, Giladi N (2004) Falls and freezing of gait in Parkinson’s disease: a review of two interconnected, episodic phenomena. Mov Disord 19(8):871–884. doi:10.1002/mds.20115

    Article  PubMed  Google Scholar 

  7. 7.

    Cole BT, Roy SH, Nawab SH (2011) Detecting freezing-of-gait during unscripted and unconstrained activity. In: 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp 5649–5652. doi:10.1109/IEMBS.2011.6091367

  8. 8.

    Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, New York

    Google Scholar 

  9. 9.

    Dauer W, Przedborski S (2003) Parkinson’s disease: mechanisms and models. Neuron 39(6):889–90. doi:10.1016/S0896-6273(03)00568-3.

  10. 10.

    Davie CA (2008) A review of Parkinson’s disease. Br Med Bull 86(1):109–127. doi:10.1093/bmb/ldn013.

  11. 11.

    Djurić-Jovičić M, Jovičić NS, Milovanović I, Radovanović S, Kresojević N, Popović MB (2010) Classification of walking patterns in Parkinson’s disease patients based on inertial sensor data. In: 2010 10th Symposium on Neural Network Applications in Electrical Engineering (NEUREL), pp 3–6. doi:10.1109/NEUREL.2010.5644040

  12. 12.

    Giladi N (2006) Freezing of gait: risk factors and clinical characteristics. Parkinsonism Relat Disord 12(Supplement 2):S52. doi:10.1016/j.parkreldis.2006.05.015

    Article  Google Scholar 

  13. 13.

    Hoehn MM (1967) Parkinsonism: onset, progression, and mortality. Neurology 17:427–442

    CAS  Article  PubMed  Google Scholar 

  14. 14.

    Hou JGG, Lai EC (2007) Non-motor symptoms of Parkinson’s disease. Int J Gerontol 1(2):53–64. doi:10.1016/S1873-9598(08)70024-3.

  15. 15.

    Hughes AJ, Daniel SE, Kilford L, Lees AJ (1992) Accuracy of clinical diagnosis of idiopathic Parkinson’s disease: a clinico-pathological study of 100 cases. J Neurol Neurosurg Psychiatry 55(3):181–184. doi:10.1136/jnnp.55.3.181.

  16. 16.

    Jankovic J (2008) Parkinson’s disease: clinical features and diagnosis. J Neurol Neurosurg Psychiatry 79(4):368–376. doi:10.1136/jnnp.2007.131045.

  17. 17.

    Korczyn AD (2008) Parkinson’s disease. In: E. in Chief: Kris Heggenhougen (ed) International encyclopedia of public health, Academic Press, Oxford, pp 10–17. doi:10.1016/B978-012373960-5.00028-9.

  18. 18.

    Krenz A (2010) The Pathological Role of Synphilin-1 and the Therapeutic Potential of Hsp70 in Models of Parkinson’s Disease Using Viral Vectors. Ph.D. thesis, Universität Tübingen, Wilhelmstr. 32, 72074 Tübingen.

  19. 19.

    Lim I, van Wegen E, de Goede C, Deutekom M, Nieuwboer A, Willems A, Jones D, Rochester L, Kwakkel G (2005) Effects of external rhythmical cueing on gait in patients with Parkinson’s disease: a systematic review. Clin Rehabil 19(7):695–713. doi:10.1191/0269215505cr906oa.

  20. 20.

    Mathers C, Fat DM, Boerma JT (2008) WHO: the Global burden of disease : 2004 update. World Health Organization, Geneva.

  21. 21.

    Moore ST, MacDougall HG, Ondo WG (2008) Ambulatory monitoring of freezing of gait in Parkinson’s disease. J Neurosci Methods 167(2):340–348. doi:10.1016/j.jneumeth.2007.08.023.

  22. 22.

    Niazmand K, Somlai I, Louizi S, Lueth TC (2011) Proof of the accuracy of measuring pants to evaluate the activity of the hip and legs in everyday life. In: Lin JC, Nikita KS, Akan O, Bellavista P, Cao J, Dressler F, Ferrari D, Gerla M, Kobayashi H, Palazzo S, Sahni S, Shen XS, Stan M, Xiaohua J, ZoMaya A, Coulson G (eds) Wireless mobile communication and healthcare, lecture notes of the institute for computer sciences, social informatics and telecommunications engineering. Springer, Berlin Heidelberg, pp 235–244. doi:10.1007/978-3-642-20865-2_30

    Google Scholar 

  23. 23.

    Niazmand K, Tonn K, Zhao Y, Fietzek UM, Schroeteler F, Ziegler K, Ceballos-Baumann AO, Lueth TC (2011) Freezing of gait detection in Parkinson’s disease using accelerometer based smart clothes. In: 2011 IEEE Biomedical Circuits and Systems Conference (BioCAS), pp 201–204. doi:10.1109/BioCAS.2011.6107762

  24. 24.

    Nieuwboer A, Giladi N (2013) Characterizing freezing of gait in Parkinson’s disease: models of an episodic phenomenon. Mov Disord 28(11):1509–1519. doi:10.1002/mds.25683

    Article  PubMed  Google Scholar 

  25. 25.

    Nieuwboer A, Weerdt Wd, Dom R, Lesaffre E (1998) A frequency and correlation analysis of motor deficits in Parkinson patients. Disabil Rehabil 20(4):142–150. doi:10.3109/09638289809166074

    CAS  Article  PubMed  Google Scholar 

  26. 26.

    Parkinson J (2002) An essay on the Shaking Palsy. 1817. J Neuropsychiatry Clin Neurosci 14(2):223–236; discussion 222.

  27. 27.

    Rodríguez-Martín D, Samà A, Pérez-López C, Cabestany J, Català A, Rodríguez-Molinero A (2014) Enhancing FoG Detection By Means of Postural Context Using a Waist Accelerometer. First International Freezing of Gait Congress (IFOG 2014)

  28. 28.

    Rodríguez-Martín D, Samà A, Pérez-López C, Cabestany J, Català A, Rodríguez-Molinero A (2015) Posture Transition Identification on PD Patients Through a SVM-based Technique and a Single Waist-worn Accelerometer. Accepted for publication in Neurocomputing

  29. 29.

    Samà A, Peréz C, Rodríguez-Martin D, Cabestany J, Moreno Aróstegui JM, Rodríguez-Molinero A (2013) A heterogeneous database for movement knowledge extraction in Parkinson’s disease. In: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

  30. 30.

    Samii A, Nutt JG, Ransom BR (2004) Parkinson’s disease. Lancet 363(9423):1783–1793 doi:10.1016/S0140-6736(04)16305-8.

  31. 31.

    Schaafsma JD, Balash Y, Gurevich T, Bartels AL, Hausdorff JM, Giladi N (2003) Characterization of freezing of gait subtypes and the response of each to levodopa in Parkinson’s disease. Eur J Neurol 10(4):391–398. doi:10.1046/j.1468-1331.2003.00611.x

    CAS  Article  PubMed  Google Scholar 

  32. 32.

    Sian J, Gerlach M, Youdim MBH, Riederer P (1999) Parkinson’s disease: a major hypokinetic basal ganglia disorder. J Neural Transm 106:443–476. doi:10.1007/s007020050171

    CAS  Article  PubMed  Google Scholar 

Download references


This work has been performed in the framework of the FP7 project REMPARK ICT-287677, which is funded by the European Community. The author(s) would like to acknowledge the contributions of their colleagues from REMPARK Consortium ( We also like to thank all participants without whom this publication would not have been possible.

Author information



Corresponding author

Correspondence to Claas Ahlrichs.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ahlrichs, C., Samà, A., Lawo, M. et al. Detecting freezing of gait with a tri-axial accelerometer in Parkinson’s disease patients. Med Biol Eng Comput 54, 223–233 (2016).

Download citation


  • Parkinson’s disease
  • Freezing of Gait
  • Machine learning
  • Support vector machines