Improved pattern recognition classification accuracy for surface myoelectric signals using spectral enhancement

Paul McCool, Lykourgos Petropoulakis, John Soraghan, Navin Chatlani

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In this paper, we demonstrate that Spectral Enhancement techniques can be configured to improve the classification accuracy of a pattern recognition-based myoelectric control system. This is based on the observation that, when the subject is at rest, the power in EMG recordings drops to levels characteristic of the noise. Two Minimum Statistics techniques, which were developed for speech processing, are compared against electromyographic (EMG) de-noising methods such as wavelets and Empirical Mode Decomposition. In the cases of simulated EMG signals contaminated with white noise and for real EMG signals with added and intrinsic noise the gesture classification accuracy was shown to increase. The mean improvement in the classification accuracy is greatest when Improved Minima-Controlled Recursive Averaging (IMCRA)-based Spectral Enhancement is applied, thus demonstrating the potential of Spectral Enhancement techniques for improving the performance of pattern recognition-based myoelectric control.
LanguageEnglish
Pages61-68
Number of pages8
JournalBiomedical Signal Processing and Control
Volume18
Early online date29 Dec 2014
DOIs
Publication statusPublished - 4 Apr 2015

Fingerprint

Pattern recognition
Noise
Speech processing
Gestures
White noise
Statistics
Decomposition
Control systems
Power (Psychology)

Keywords

  • pattern recognition
  • surface myoelectric signals
  • spectral enhancement

Cite this

@article{37699ebe8fe844fabfdeff08d587caaf,
title = "Improved pattern recognition classification accuracy for surface myoelectric signals using spectral enhancement",
abstract = "In this paper, we demonstrate that Spectral Enhancement techniques can be configured to improve the classification accuracy of a pattern recognition-based myoelectric control system. This is based on the observation that, when the subject is at rest, the power in EMG recordings drops to levels characteristic of the noise. Two Minimum Statistics techniques, which were developed for speech processing, are compared against electromyographic (EMG) de-noising methods such as wavelets and Empirical Mode Decomposition. In the cases of simulated EMG signals contaminated with white noise and for real EMG signals with added and intrinsic noise the gesture classification accuracy was shown to increase. The mean improvement in the classification accuracy is greatest when Improved Minima-Controlled Recursive Averaging (IMCRA)-based Spectral Enhancement is applied, thus demonstrating the potential of Spectral Enhancement techniques for improving the performance of pattern recognition-based myoelectric control.",
keywords = "pattern recognition, surface myoelectric signals, spectral enhancement",
author = "Paul McCool and Lykourgos Petropoulakis and John Soraghan and Navin Chatlani",
year = "2015",
month = "4",
day = "4",
doi = "10.1016/j.bspc.2014.12.001",
language = "English",
volume = "18",
pages = "61--68",
journal = "Biomedical Signal Processing and Control",
issn = "1746-8094",

}

TY - JOUR

T1 - Improved pattern recognition classification accuracy for surface myoelectric signals using spectral enhancement

AU - McCool, Paul

AU - Petropoulakis, Lykourgos

AU - Soraghan, John

AU - Chatlani, Navin

PY - 2015/4/4

Y1 - 2015/4/4

N2 - In this paper, we demonstrate that Spectral Enhancement techniques can be configured to improve the classification accuracy of a pattern recognition-based myoelectric control system. This is based on the observation that, when the subject is at rest, the power in EMG recordings drops to levels characteristic of the noise. Two Minimum Statistics techniques, which were developed for speech processing, are compared against electromyographic (EMG) de-noising methods such as wavelets and Empirical Mode Decomposition. In the cases of simulated EMG signals contaminated with white noise and for real EMG signals with added and intrinsic noise the gesture classification accuracy was shown to increase. The mean improvement in the classification accuracy is greatest when Improved Minima-Controlled Recursive Averaging (IMCRA)-based Spectral Enhancement is applied, thus demonstrating the potential of Spectral Enhancement techniques for improving the performance of pattern recognition-based myoelectric control.

AB - In this paper, we demonstrate that Spectral Enhancement techniques can be configured to improve the classification accuracy of a pattern recognition-based myoelectric control system. This is based on the observation that, when the subject is at rest, the power in EMG recordings drops to levels characteristic of the noise. Two Minimum Statistics techniques, which were developed for speech processing, are compared against electromyographic (EMG) de-noising methods such as wavelets and Empirical Mode Decomposition. In the cases of simulated EMG signals contaminated with white noise and for real EMG signals with added and intrinsic noise the gesture classification accuracy was shown to increase. The mean improvement in the classification accuracy is greatest when Improved Minima-Controlled Recursive Averaging (IMCRA)-based Spectral Enhancement is applied, thus demonstrating the potential of Spectral Enhancement techniques for improving the performance of pattern recognition-based myoelectric control.

KW - pattern recognition

KW - surface myoelectric signals

KW - spectral enhancement

UR - http://www.sciencedirect.com/science/journal/17468094

U2 - 10.1016/j.bspc.2014.12.001

DO - 10.1016/j.bspc.2014.12.001

M3 - Article

VL - 18

SP - 61

EP - 68

JO - Biomedical Signal Processing and Control

T2 - Biomedical Signal Processing and Control

JF - Biomedical Signal Processing and Control

SN - 1746-8094

ER -