Skip to main content

Advertisement

SpringerLink
Log in

Outlier detection in high-density surface electromyographic signals

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

A Data Descriptor to this article was published on 16 November 2020

Abstract

Recently developed techniques allow the analysis of surface EMG in multiple locations over the skin surface (high-density surface electromyography, HDsEMG). The detected signal includes information from a greater proportion of the muscle of interest than conventional clinical EMG. However, recording with many electrodes simultaneously often implies bad-contacts, which introduce large power-line interference in the corresponding channels, and short-circuits that cause near-zero single differential signals when using gel. Such signals are called ‘outliers’ in data mining. In this work, outlier detection (focusing on bad contacts) is discussed for monopolar HDsEMG signals and a new method is proposed to identify ‘bad’ channels. The overall performance of this method was tested using the agreement rate against three experts’ opinions. Three other outlier detection methods were used for comparison. The training and test sets for such methods were selected from HDsEMG signals recorded in Triceps and Biceps Brachii in the upper arm and Brachioradialis, Anconeus, and Pronator Teres in the forearm. The sensitivity and specificity of this algorithm were, respectively, 96.9 ± 6.2 and 96.4 ± 2.5 in percent in the test set (signals registered with twenty 2D electrode arrays corresponding to a total of 2322 channels), showing that this method is promising.

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
Fig. 5

Similar content being viewed by others

Abbreviations

CC:

Correlation coefficient

CPV:

Cumulative percentage variance

EMG:

Electromyography

EP:

Error probability

HDsEMG:

High-density surface electromyographic signals

KDE:

Kernel density estimator

kNN:

k-Nearest neighbors

LDOF:

Local distance-based outlier factor

LOF:

Local outlier factor

MAD:

Median absolute deviation

MCD:

Minimum covariance determinant estimator

MSD:

Mahalanobis squared distance

MVIC:

Maximum voluntary isometric contraction

OCA:

Overall classification accuracy

PC:

Principal component

PCA:

Principal component analysis

PDE:

Partial differential equation

PLOF:

Probabilistic local outlier factor

RMS:

Root mean square

SD (sd):

Standard deviation

Se:

Sensitivity

Sp:

Specificity

References

  1. Allen DP (2009) A frequency domain hampel filter for blind rejection of sinusoidal interference from electromyograms. J Neurosci Methods 177:303–310

    Article  PubMed  Google Scholar 

  2. Angiulli C, Pizzuti (2002) Fast outliers detection in high dimensional spaces. In: 6th European conference on principles and practice of knowledge discovery in databases (PKDD’02), August 19–23, Helsinki, Finland, pp 15–26.

  3. Barnett V, Lewis T (1994) Outliers in statistical data, 3rd edn. Wiley, New York

    Google Scholar 

  4. Ben-Gal I (2005) Outlier detection. In: Maimon O, Rockach L (eds) Data mining and knowledge discovery handbook: a complete guide for practitioners and researchers. Kluwer Academic Publishers, Boston ISBN 0-387-24435-2

    Google Scholar 

  5. Bertalmio M (2006) Strong-continuation, contrast-invariant inpainting with a third-order optimal PDE. IEEE Trans Image Process 15(7):1934–1938

    Article  PubMed  Google Scholar 

  6. Bilodeau M, Cincera M, Arsenault AB, Gravel D (1997) Normality and stationarity of EMG signals of elbow flexor muscles during ramp and step isometric contractions. J Electromyogr Kinesiol 7(2):87–96

    Article  PubMed  CAS  Google Scholar 

  7. Breunig MM, Kriegel H, Ng RT, Sander J (2000) LOF: identifying density-based local outlier. In: Proceedings of the ACM SIGMOD international conference on management of data, May 14–19, Dallas, TX, USA, pp 93–104

  8. Cateni S, Colla V, Vannucci M (2008) Outlier detection methods for industrial applications. In: Juan Manuel Ramos Arregui (ed) Advances in robotics, automation and control, I-tech education and publishing, pp 265–282

  9. Cateni S, Colla V, Vannucci M (2009) A fuzzy system for combining different outliers detection methods. In: Proceedings of the IASTED international conference on artificial intelligence and applications (AIA 2009), February 16–18, Innsbruck, Austria

  10. Cohen J (1988) Statistical power analysis for the behavioral sciences, 2nd edn. Lawrence Erlbaum Associates, New Jersey

    Google Scholar 

  11. Conover WJ (1980) Practical nonparametric statistics, 2nd edn. Wiley, New York

    Google Scholar 

  12. Croux C, Ruiz-Gazen A (2005) High breakdown estimators for principal components: the projection-pursuit approach revisited. J Multivar Anal 95(1):206–226

    Article  Google Scholar 

  13. Daniels HE (1950) Rank correlation and population models. J R Stat Soc B 12:171–181

    Google Scholar 

  14. Davies L, Gather U (1993) The identification of multiple outliers. J Am Stat Assoc 88:782–792

    Article  Google Scholar 

  15. Duan L, Xu L, Liu Y, Lee J (2009) Cluster-based outlier detection. Ann Oper Res 168(1):151–168

    Article  Google Scholar 

  16. Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. Wiley, New York

    Google Scholar 

  17. Faul F, Erdfelder E, Lang AG, Buchner A (2007) G*Power 3: a flexible statistical power analysis program for the social, behavioral, and biomedical sciences. Behav Res Method 39(2):175–191

    Article  Google Scholar 

  18. Faul F, Erdfelder E, Buchner A, Lang AG (2009) Statistical power analyses using G*Power 3.1: Tests for correlation and regression analyses. Behav Res Methods 41(4):1149–1160

    Article  PubMed  Google Scholar 

  19. Fleiss JL (1971) Measuring nominal scale agreement among many raters. Psychol Bull 76(5):378–382

    Article  Google Scholar 

  20. Geddes LA, Valentinuzzi ME (1973) Temporal changes in electrode impedance while recording the electrocardiogram with dry electrodes. Ann Biomed Eng 1:356–367

    Article  PubMed  CAS  Google Scholar 

  21. Goldberg KM, Iglewicz B (1992) Bivariate extensions of boxplot. Technometrics 34(3):307–320

    Article  Google Scholar 

  22. Gonzalez RC, Woods RE (2002) Digital image processing, 2nd edn. Prentice-Hall, New Jersey

    Google Scholar 

  23. Grönlund C, Roeleveld K, Holtermann A, Karlsson JS (2005) On-line signal quality estimation of multichannel surface electromyograms. Med Biol Eng Comput 43(3):357–364

    Article  PubMed  Google Scholar 

  24. Grubbs F (1969) Procedures for detecting outlying observations in samples. Technometrics 11(1):1–21

    Article  Google Scholar 

  25. Hadi AS (1992) Identifying outliers in multivariate data. J R Stat Soc B 54(3):761–771

    Google Scholar 

  26. Hadi AS, Rahmatullah Imon AHM, Werner M (2009) Detection of outliers. WIREs Comp Stat 1. Wiley, New York, pp 57–70

    Google Scholar 

  27. Hampel FR (1971) A general qualitative measure of robustness. Ann Stat 42:1887–1896

    Article  Google Scholar 

  28. Hawkins DM (1980) Identification of outliers. Chapman and Hall, London, New York

    Google Scholar 

  29. Hosmer DW, Hollander M, Wolfe DA (1973) Nonparametric statistical methods, 3rd edn. Wiley, New York

    Google Scholar 

  30. Inbar GF, Noujaim AE (1984) On surface EMG spectral characterization and its application to diagnostic classification. IEEE Trans Biomed Eng 31(9):597–604

    Article  PubMed  CAS  Google Scholar 

  31. Jones MC, Marron JS, Sheather ST (1996) A brief survey of bandwidth selection for density estimation. J Am Stat Assoc 91(433):401–407

    Article  Google Scholar 

  32. Kendall FP, McCreary EK, Provance PG (1993) Muscles and testing function, 3rd edn. Williams & Wilkins, Baltimore

    Google Scholar 

  33. Kriegel H, Kröger P, Schubert E, Zimek A (2009) LoOP: local outlier probabilities. ACM, CIKM’09, Hong Kong

  34. Last M, Kandel A (1999) Automated perceptions in data mining. In: Proceedings of the 8th IEEE international conference on fuzzy systems, August 22–25, Seoul, Korea. Part I: pp 190–197. doi:10.1109/FUZZY.1999.793233

  35. Lemeshow S (2000) Applied logistic regression, 2nd edn. Wiley, New York

    Google Scholar 

  36. López AM, Lumbreras F, Serrat J, Villanueva JJ (1999) Evaluation of methods for ridge and valley detection. IEEE Trans Pattern Anal 21(4):327–335

    Article  Google Scholar 

  37. Mahalanobis PC (1936) On the generalized distance in statistics. Proc Nat Inst Sci India 2:49–55

    Google Scholar 

  38. Malinowski ER (1991) Factor analysis in chemistry, 2nd edn. Wiley-Interscience, New York

    Google Scholar 

  39. Marateb HR, Soares AF, Rojas M, Merletti R (2009) An expert-based fuzzy system for automatically identifying the location of muscle innervation zones in surface electromyography. In: Proceedings of the International Xth Quantitative EMG conference, May 6–10, Venice, Italy

  40. Marateb HR, Rojas-Martínez M, Mañanas Villanueva MA, Merletti R (2010) Robust outlier detection in high-density surface electromyographic signals. Conf Proc IEEE Eng Med Biol Soc 1:4850–4853

    Google Scholar 

  41. Maronna RA, Zamar RH (2002) Robust estimates of location and dispersion of high-dimensional datasets. Technometrics 44(4):307–317

    Article  Google Scholar 

  42. Mcgill R, Tukey JW, Larsen WA (1978) Variations of box plots. Am Stat 32(1):12–16

    Article  Google Scholar 

  43. Mewett DT, Reynolds KJ, Nazeran H (2004) Reducing power line interference in digitized electromyograms recordings by spectrum interpolation. Med Biol Eng Comput 42:524–531

    Article  PubMed  CAS  Google Scholar 

  44. Minium EW, Clarke RB, Coladarci T (1999) Elements of statistical reasoning. Wiley, New York

    Google Scholar 

  45. Mosteller F, Tukey JW (1977) Data analysis and regression: a second course in statistics, 1st edn. Addison, Wesley

    Google Scholar 

  46. Pearson RK (2002) Outliers in process modeling and identification. IEEE Trans Control Syst Technol 10:55–63

    Article  Google Scholar 

  47. Penny KI, Jolliffe IT (2001) A comparison of multivariate outlier detection methods for clinical laboratory safety data. Statistician 50(3):295–308

    Article  Google Scholar 

  48. Randles RH (1988) Wilcoxon signed rank test. In: Kotz S, Johnson NL (eds) Encyclopedia of statistical sciences, vol 9. Wiley, New York, pp 613–616

    Google Scholar 

  49. Rodriguez RN (1982) Correlation. In: Kotz S, Johnson NL (eds) Encyclopedia of statistical sciences, vol 2. Wiley, New York, pp 193–204

    Google Scholar 

  50. Rousseeuw PJ, Leory AM (1987) Robust regression and outlier detection. Wiley, New York ISBN: 9780471852339

    Book  Google Scholar 

  51. Rousseeuw PJ, Van Driessen K (1999) A fast algorithm for the minimum covariance determinant estimator. Technometrics 41:212–223

    Article  Google Scholar 

  52. Rousseeuw PJ, Ruts I, Tukey JW (1999) The bagplot: a bivariate boxplot. Am Stat 53(4):382–387

    Article  Google Scholar 

  53. Shapiro LG, Stockman GC (2001) Computer vision. Prentice-Hall, New Jersey ISBN 0-13-030796-3

    Google Scholar 

  54. Silverman BW (1986) Density estimation for statistics and data analysis. Chapman and Hall, London

    Google Scholar 

  55. Small CG (1990) A survey of multidimensional medians. Int Stat Rev 58(3):263–277

    Article  Google Scholar 

  56. Tukey JW (1977) Exploratory data analysis. Addison-Wesley, Reading, MA

    Google Scholar 

  57. Van Kerm P (2003) Adaptive kernel density estimation. Stat J 3(2):148–156

    Google Scholar 

  58. Varid Y, Zhang CH (2000) The multivariate L1-median and associated data depth. Proc Natl Acad Sci USA 97(4):1423–1426

    Article  Google Scholar 

  59. Wand MP, Jones MC (1994) Kernel smoothing (Monographs on statistics applied probability). 1st ed., Chapman Hall/CRC, London, p 71

  60. Westerweel J (1994) Efficient detection of spurious vectors in particle image velocimetry data. Exp Fluids 16:236–247

    Article  Google Scholar 

  61. Zhang K, Hutter M, Jin H (2009) A new local distance-based outlier detection approach for scattered real-world data. Lecturer Notes in Computer Science, Advances in knowledge discovery and data mining, 13th Pacific-Asia Conference, PAKDD 2009, April 27–30, Bangkok, Thailand, vol 5476, pp 813–822. doi:10.1007/978-3-642-01307-2_84

Download references

Acknowledgments

We are grateful to Kevin McGill for reviewing a draft of this paper. This work was supported by Compagnia di San Paolo, Fondazione CRT, the Spanish government (TEC2008-02754) and the Doctoral School of Politecnico di Torino, Italy.

Author information

Authors and Affiliations

  1. Laboratory for Engineering of the Neuromuscular Systems, Department of Electronics, Politecnico di Torino, Turin, Italy

    Hamid R. Marateb & Roberto Merletti

  2. Biomedical Research Networking Center in Bioengineering, Biomaterials and Nanomedicine, CIBER-BBN, CREB, Department ESAII, Technical University of Catalonia, UPC, Barcelona, Spain

    Monica Rojas-Martínez

  3. Department of Biostatistics and Epidemiology, Health School, Isfahan University of Medical Science, Isfahan, Iran

    Marjan Mansourian

  4. Biomedical Engineering Research Centre, CREB, CIBER-BBN, Department ESAII, Technical University of Catalonia, UPC, Barcelona, Spain

    Miguel A. Mañanas Villanueva

Authors
  1. Hamid R. Marateb
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Monica Rojas-Martínez
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Marjan Mansourian
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Roberto Merletti
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Miguel A. Mañanas Villanueva
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hamid R. Marateb.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Marateb, H.R., Rojas-Martínez, M., Mansourian, M. et al. Outlier detection in high-density surface electromyographic signals. Med Biol Eng Comput 50, 79–89 (2012). https://doi.org/10.1007/s11517-011-0790-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-011-0790-7

Keywords

Search

Navigation