Limits...
Influence of the training set on the accuracy of surface EMG classification in dynamic contractions for the control of multifunction prostheses.

Lorrain T, Jiang N, Farina D - J Neuroeng Rehabil (2011)

Bottom Line: A 9 class experiment was designed involving both static and dynamic situations.Moreover, the performance of the pattern recognition algorithms tested significantly improved by optimizing the choice of the training set.Finally, the results also showed that rather simple approaches for classification of time domain features provide results comparable to more complex classification methods of wavelet features.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Neurorehabilitation Engineering, Bernstein Center for Computational Neuroscience, University Medical Center Göttingen, Georg-August University, Göttingen, Germany.

ABSTRACT

Background: For high usability, myo-controlled devices require robust classification schemes during dynamic contractions. Therefore, this study investigates the impact of the training data set in the performance of several pattern recognition algorithms during dynamic contractions.

Methods: A 9 class experiment was designed involving both static and dynamic situations. The performance of various feature extraction methods and classifiers was evaluated in terms of classification accuracy.

Results: It is shown that, combined with a threshold to detect the onset of the contraction, current pattern recognition algorithms used on static conditions provide relatively high classification accuracy also on dynamic situations. Moreover, the performance of the pattern recognition algorithms tested significantly improved by optimizing the choice of the training set. Finally, the results also showed that rather simple approaches for classification of time domain features provide results comparable to more complex classification methods of wavelet features.

Conclusions: Non-stationary surface EMG signals recorded during dynamic contractions can be accurately classified for the control of multi-function prostheses.

Show MeSH

Related in: MedlinePlus

Error rates depending on the training section. Performance (mean and standard deviation) of the different combinations of feature sets and classifiers (a): LDA; (b): SVM-OVO; (c): SVM-OVR, depending on the training sections as defined in Figure 2.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3113948&req=5

Figure 5: Error rates depending on the training section. Performance (mean and standard deviation) of the different combinations of feature sets and classifiers (a): LDA; (b): SVM-OVO; (c): SVM-OVR, depending on the training sections as defined in Figure 2.

Mentions: Figure 5(a) confirms that LDA does not perform optimally with the WT feature set. In addition, it shows that the combination of LDA with TD+AR features determines high performance (error limited to ~8%) when trained using some part of the dynamic portion in addition to the static portion. Although the differences in performance when using different dynamic sections (sections including a portion of the dynamic contraction) for training were very low (<0.6%), the best results were obtained using the threshold based training section, which provides automatically an efficient way to determine which portion of the signals should be used as the training set.


Influence of the training set on the accuracy of surface EMG classification in dynamic contractions for the control of multifunction prostheses.

Lorrain T, Jiang N, Farina D - J Neuroeng Rehabil (2011)

Error rates depending on the training section. Performance (mean and standard deviation) of the different combinations of feature sets and classifiers (a): LDA; (b): SVM-OVO; (c): SVM-OVR, depending on the training sections as defined in Figure 2.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3113948&req=5

Figure 5: Error rates depending on the training section. Performance (mean and standard deviation) of the different combinations of feature sets and classifiers (a): LDA; (b): SVM-OVO; (c): SVM-OVR, depending on the training sections as defined in Figure 2.
Mentions: Figure 5(a) confirms that LDA does not perform optimally with the WT feature set. In addition, it shows that the combination of LDA with TD+AR features determines high performance (error limited to ~8%) when trained using some part of the dynamic portion in addition to the static portion. Although the differences in performance when using different dynamic sections (sections including a portion of the dynamic contraction) for training were very low (<0.6%), the best results were obtained using the threshold based training section, which provides automatically an efficient way to determine which portion of the signals should be used as the training set.

Bottom Line: A 9 class experiment was designed involving both static and dynamic situations.Moreover, the performance of the pattern recognition algorithms tested significantly improved by optimizing the choice of the training set.Finally, the results also showed that rather simple approaches for classification of time domain features provide results comparable to more complex classification methods of wavelet features.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Neurorehabilitation Engineering, Bernstein Center for Computational Neuroscience, University Medical Center Göttingen, Georg-August University, Göttingen, Germany.

ABSTRACT

Background: For high usability, myo-controlled devices require robust classification schemes during dynamic contractions. Therefore, this study investigates the impact of the training data set in the performance of several pattern recognition algorithms during dynamic contractions.

Methods: A 9 class experiment was designed involving both static and dynamic situations. The performance of various feature extraction methods and classifiers was evaluated in terms of classification accuracy.

Results: It is shown that, combined with a threshold to detect the onset of the contraction, current pattern recognition algorithms used on static conditions provide relatively high classification accuracy also on dynamic situations. Moreover, the performance of the pattern recognition algorithms tested significantly improved by optimizing the choice of the training set. Finally, the results also showed that rather simple approaches for classification of time domain features provide results comparable to more complex classification methods of wavelet features.

Conclusions: Non-stationary surface EMG signals recorded during dynamic contractions can be accurately classified for the control of multi-function prostheses.

Show MeSH
Related in: MedlinePlus