Outlier detection in high-density surface electromyographic signals
- PDF / 589,055 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 85 Downloads / 246 Views
ORIGINAL ARTICLE
Outlier detection in high-density surface electromyographic signals Hamid R. Marateb • Monica Rojas-Martı´nez Marjan Mansourian • Roberto Merletti • Miguel A. Man˜anas Villanueva
•
Received: 9 October 2010 / Accepted: 13 June 2011 / Published online: 23 June 2011 International Federation for Medical and Biological Engineering 2011
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 nearzero 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 H. R. Marateb (&) R. Merletti Laboratory for Engineering of the Neuromuscular Systems, Department of Electronics, Politecnico di Torino, Turin, Italy e-mail: [email protected] M. Rojas-Martı´nez Biomedical Research Networking Center in Bioengineering, Biomaterials and Nanomedicine, CIBER-BBN, CREB, Department ESAII, Technical University of Catalonia, UPC, Barcelona, Spain M. Mansourian Department of Biostatistics and Epidemiology, Health School, Isfahan University of Medical Science, Isfahan, Iran M. A. Man˜anas Villanueva Biomedical Engineering Research Centre, CREB, CIBER-BBN, Department ESAII, Technical University of Catalonia, UPC, Barcelona, Spain
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. Keywords Detection theory Feature extraction Logistic regression Multichannel surface electromyography Multivariate outlier detection Robust statistics 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 Prin
Data Loading...
