Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Sep 17;21(18):6234.
doi: 10.3390/s21186234.

A Study on the Classification Effect of sEMG Signals in Different Vibration Environments Based on the LDA Algorithm

Yanchao Wang  1 , Ye Tian  1   2 , Jinying Zhu  2 , Haotian She  1 , Hiroshi Yokoi  2   3 , Yinlai Jiang  2   3 , Qiang Huang  1   2
Affiliations

A Study on the Classification Effect of sEMG Signals in Different Vibration Environments Based on the LDA Algorithm

Yanchao Wang et al. Sensors (Basel). .

Abstract

Myoelectric prosthesis has become an important aid to disabled people. Although it can help people to recover to a nearly normal life, whether they can adapt to severe working conditions is a subject that is yet to be studied. Generally speaking, the working environment is dominated by vibration. This paper takes the gripping action as its research object, and focuses on the identification of grasping intentions under different vibration frequencies in different working conditions. In this way, the possibility of the disabled people who wear myoelectric prosthesis to work in various vibration environment is studied. In this paper, an experimental test platform capable of simulating 0-50 Hz vibration was established, and the Surface Electromyography (sEMG) signals of the human arm in the open and grasping states were obtained through the MP160 physiological record analysis system. Considering the reliability of human intention recognition and the rapidity of algorithm processing, six different time-domain features and the Linear Discriminant Analysis (LDA) classifier were selected as the sEMG signal feature extraction and recognition algorithms in this paper. When two kinds of features, Zero Crossing (ZC) and Root Mean Square (RMS), were used as input, the accuracy of LDA algorithm can reach 96.9%. When three features, RMS, Minimum Value (MIN), and Variance (VAR), were used as inputs, the accuracy of the LDA algorithm can reach 98.0%. When the six features were used as inputs, the accuracy of the LDA algorithm reached 98.4%. In the analysis of different vibration frequencies, it was found that when the vibration frequency reached 20 Hz, the average accuracy of the LDA algorithm in recognizing actions was low, while at 0 Hz, 40 Hz and 50 Hz, the average accuracy was relatively high. This is of great significance in guiding disabled people to work in a vibration environment in the future.

Keywords: LDA algorithm; feature extraction; hand-motion recognition; surface EMG signal; vibration frequency.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Sampling sEMG signals.
Figure 2
Figure 2
sEMG signal acquisition platform.
Figure 3
Figure 3
Vibration simulator (1, external shell; 2, hook; 3, frequency adjustment knob; 41, industrial handle; 42, commonly used handle; 5, switch button; 6, emergency stop button).
Figure 4
Figure 4
The sEMG signals for the open and grip modes of the prosthetic hand under various vibration frequencies.
Figure 5
Figure 5
EMG signal feature extraction process.
Figure 6
Figure 6
An overview of several sEMG signal processing algorithms.
Figure 7
Figure 7
Optimized selection of sliding window size.
Figure 8
Figure 8
LDA classification based on the ZC and RMS feature extraction algorithm.
Figure 9
Figure 9
LDA classification based on the VAR and RMS feature extraction algorithm.
Figure 10
Figure 10
LDA classification based on the MIN and RMS feature extraction algorithm.
Figure 11
Figure 11
The recognition accuracy of each feature combination for the LDA algorithm.
Figure 12
Figure 12
LDA classification based on the RMS, MAV and ZC feature extraction algorithm.
Figure 13
Figure 13
The recognition accuracy of all three-feature combinations for the LDA algorithm.
Figure 14
Figure 14
Accuracy comparison under different numbers of features for the LDA algorithm.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Xing K., Yang P., Huang J., Wang Y., Zhu Q. A real-time EMG pattern recognition method for virtual myoelectric hand control. Neurocomputing. 2014;136:345–355. doi: 10.1016/j.neucom.2013.12.010. - DOI
    1. Veer K., Sharma T. A novel feature extraction for robust EMG pattern recognition. J. Med. Eng. Technol. 2016;40:149–154. doi: 10.3109/03091902.2016.1153739. - DOI - PubMed
    1. Carlucci F., Orlando G., Haxhi J., Laudani L., Giombini A., Macaluso A., Pigozzi F., Sacchetti M. Older Age Is Associated with Lower Optimal Vibration Frequency in Lower-Limb Muscles During Whole-Body Vibration. Am. J. Phys. Med. Rehabil. 2015;94:522–529. doi: 10.1097/PHM.0000000000000193. - DOI - PubMed
    1. Lienhard K., Vienneau J., Nigg S., Friesenbichler B., Nigg B.M. Older adults show higher increases in lower-limb muscle activity during whole-body vibration exercise. J. Biomech. 2017;52:55–60. doi: 10.1016/j.jbiomech.2016.12.009. - DOI - PubMed
    1. Zaidell L.N., Mileva K.N., Sumners D.P., Bowtell J.L. Experimental Evidence of the Tonic Vibration Reflex during Whole-Body Vibration of the Loaded and Unloaded Leg. PLoS ONE. 2013;8:e85247. - PMC - PubMed