In this paper, we provide a robust framework to detect anomalous electromyographic (EMG) signals and identify contamination types. As a first step for feature selection, optimally selected Lawton wavelets transform is applied. Robust principal component analysis (rPCA) is then performed on these wavelet coefficients to obtain features in a lower dimension. The rPCA based features are used for constructing a self-organizing map (SOM). Finally, hierarchical clustering is applied on the SOM that separates anomalous signals residing in the smaller clusters and breaks them into logical units for contamination identification. The proposed methodology is tested using synthetic and real world EMG signals. The synthetic EMG signals are generated using a heteroscedastic process mimicking desired experimental setups. A sub-part of these synthetic signals is introduced with anomalies. These results are followed with real EMG signals introduced with synthetic anomalies. Finally, a heterogeneous real world data set is used with known quality issues under an unsupervised setting. The framework provides recall of 90% (± 3.3) and precision of 99%(±0.4).
|Number of pages||10|
|Journal||IEEE Transactions on Neural Systems and Rehabilitation Engineering|
|Publication status||Published - 2018 Apr|
Bibliographical noteFunding Information:
Manuscript received October 25, 2016; revised July 18, 2017, December 21, 2017, and February 14, 2018; accepted February 22, 2018. Date of publication March 8, 2018; date of current version April 6, 2018. This work was supported in part by the Yonsei University for New Faculty Research Seed Funding Grant and in part by the New Faculty Research Equipment Support Grant. (Corresponding author: Jongeun Choi.) A. Ijaz is with ADDO AI, Singapore 058357 (e-mail: firstname.lastname@example.org).
© 2001-2011 IEEE.
All Science Journal Classification (ASJC) codes
- Internal Medicine
- Biomedical Engineering