Skip to main content
SpringerLink
Log in

Classification of nine directions using the maximum likelihood estimation based on electromyogram of both forearms

  • Original Article
  • Published:
Biomedical Engineering Letters Aims and scope Submit manuscript

Abstract

Introduction

In this paper, the nine directions are classified using the maximum likelihood estimation (MLE) based on electromyogram (EMG) obtained from both forearm. The authors compared the EMG features to confirm classification accuracy of nine directions.

Methods

Fifteen subjects participated in the experiment, were asked to act three types of motions for each forearm. The motions of left wrist were forward, backward, and rest, while the motions of right wrist were left, right, and rest. Three motions of left wrist and three motion of right wrist were combined to classify the nine directions. The EMG features with 166ms time-window for five seconds of each motion were extracted from the obtained EMG signals. The difference absolute mean value (DAMV), difference absolute standard deviation value (DASDV), mean absolute value (MAV), and root mean square (RMS) were chosen as the EMG feature to compare classification accuracy of nine directions.

Results

In the results, the average classification accuracy of 97.71% was confirmed for each of the nine directions. The DAMV had the highest classification accuracy in the EMG features with 99.26% accuracy. And DASDV had classification accuracy with 99.19%.

Conclusions

These results demonstrate that in this study the classification performance using DAMV or DASDV is stronger than that using MAV or RMS. Furthermore, the classified direction using DAMV or DASDV can be used as precise input data for controlling of robots and devices in rehabilitation applications.

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

Similar content being viewed by others

References

  1. Kim JS, Kim HK, Jeong H, Kim KH, Lim SH, Son WH. Human-computer interface based on bio-signal. Elect Telecommun Trends. 2005; 20(4):67–81.

    Google Scholar 

  2. Lee YH, Choi CH, Kim SS, Kim DH. Detection of hand motions using cross-correlation of surface EMG. J Biomed Eng Res. 2004; 29(3):205–211.

    MathSciNet  Google Scholar 

  3. Lee J, Kwon HM. Comparison of algorithms estimating linear regression line from surface EMG signals. JKIEE. 2008; 57(3):527–535.

    Google Scholar 

  4. Chu JU, Moon IH. A wavelet-based EMG pattern recognition with nonlinear feature projection. J Inst Elect Eng Kor. 2005; 42(2):39–48.

    Google Scholar 

  5. Alkan A, Gunay M. Identification of EMG signals using discriminant analysis and SVM classifier. Expert Syst Appl. 2012; 39:44–47.

    Google Scholar 

  6. Song YR, Kim SJ, Jeong EC, Lee SM. A gaussian mixture model pattern classification algorithm of forearm electromyogram. J Rehab Welfare Eng Assistive Tech. 2011; 5(1):95–101.

    Google Scholar 

  7. Wheeler KR. Device control using gestures sensed from EMG. IEEE Int Workshop Soft Comput Ind Appl. 2003; 21–26.

  8. Kim MH, Park SB. The effect of bilateral activities of the upper Limb on motor performance of the affected Limb in children with hemiplegia. Kor J Sport Psychol. 2000; 11(2):57–76.

    Google Scholar 

  9. Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification. Expert Syst Appl. 2012; 39:7420–7431.

    Article  Google Scholar 

  10. Jenkins DB. Functional anatomy of the limbs and back. Hyunmoom Press; 2002.

  11. Kim KS, Choi HH, Moon CS, Mun CW. Comparison of knearest neighbor, quadratic discriminant and linear discriminant analysis in classification of electromyogram signals based on the wrist-motion directions. Curr Appl Phys. 2011; 11(3):740–745.

    Article  Google Scholar 

  12. Cho YJ, Kim JY. The limitation of interpretation of MPF parameter in muscle fatigue assessment. Fall Conf Ergon Soc Kor. 2008; 67–72.

  13. Ahsan MR, Ibrahimy MI, Khalifa OO. EMG signal classification for human computer interaction: A review. Eur J Sci Res. 2009; 33(3):480–501.

    Google Scholar 

  14. Myung IJ. Tutorial on maximum likelihood estimation. J Math Psychol. 2003; 47:90–100.

    Article  MathSciNet  MATH  Google Scholar 

  15. Han HY. The introduction of pattern recognition. Han-bit media; 2005.

  16. You KJ, Shin HC. Classifying finger flexing motions with surface EMG using entropy and the maximum likelihood method. J Inst Elect Eng Kor. 2009; 46(6):38–43.

    Google Scholar 

  17. Lee DH, Yoon KA, Bae DH. A missing data imputation by combining K nearest neighbor with maximum likelihood estimation for numerical software project data. Kor Inst Inform Sci Eng. 2009; 36(4):273–282.

    Google Scholar 

  18. You KJ, Shin HC. Hand motion inference using surface EMG signals. Summer Conf Inst Elect Eng Kor. 2009; 1131–1132.

  19. Kim SM, Kang HG. Introduction to statistics using EXCEL. Donam Press; 2000.

  20. Kim JS, Lee SS, Kim SJ, Yoon MS, Kwok SH. Introduction to statistics using EXCEL. Chung-ram Press; 2006.

Download references

Author information

Authors and Affiliations

  1. Department of Electronic Engineering, Inha University, Incheon, Korea

    Songhyun Yu, Euichul Jeong & Sangmin Lee

  2. Institute for Information and Electronics Research, Incheon, Korea

    Kihwan Hong & Sangmin Lee

Authors
  1. Songhyun Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Euichul Jeong
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kihwan Hong
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sangmin Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sangmin Lee.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Yu, S., Jeong, E., Hong, K. et al. Classification of nine directions using the maximum likelihood estimation based on electromyogram of both forearms. Biomed. Eng. Lett. 2, 129–137 (2012). https://doi.org/10.1007/s13534-012-0063-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13534-012-0063-x

Keywords

Search

Navigation