A transform-based feature extraction approach for motor imagery tasks classification

Simple item page
dc.contributor.authorBaali, Hamza
dc.contributor.authorKhorshidtalab, Aida
dc.contributor.authorMesbah, Mostefa
dc.contributor.authorSalami, Momoh-Jimoh E.
dc.date.accessioned2019-08-14T10:51:25Z
dc.date.available2019-08-14T10:51:25Z
dc.date.issued2015-10-16
dc.description.abstractIn this paper, we present a new motor imagery classification method in the context of electroencephalography (EEG)-based brain–computer interface (BCI). This method uses a signal-dependent orthogonal transform, referred to as linear prediction singular value decomposition (LP-SVD), for feature extraction. The transform defines the mapping as the left singular vectors of the LP coefficient filter impulse response matrix. Using a logistic tree-based model classifier; the extracted features are classified into one of four motor imagery movements. The proposed approach was first benchmarked against two related state-of-the-art feature extraction approaches, namely, discrete cosine transform (DCT) and adaptive autoregressive (AAR)-based methods. By achieving an accuracy of 67.35%, the LP-SVD approach outperformed the other approaches by large margins (25% compared with DCT and 6 % compared with AAR-based methods). To further improve the discriminatory capability of the extracted features and reduce the computational complexity, we enlarged the extracted feature subset by incorporating two extra features, namely, Q- and the Hotelling’s T 2 statistics of the transformed EEG and introduced a new EEG channel selection method. The performance of the EEG classification based on the expanded feature set and channel selection method was compared with that of a number of the state-of-the-art classification methods previously reported with the BCI IIIa competition data set. Our method came second with an average accuracy of 81.38%.en_US
dc.identifier.citationBaali, H., Khorshidtalab, A., Mesbah, M., & Salami, M. J. (2015). A transform-based feature extraction approach for motor imagery tasks classification. IEEE journal of translational engineering in health and medicine, 3, 1-8.en_US
dc.identifier.uri10.1109/JTEHM.2015.2485261
dc.identifier.urihttp://repository.elizadeuniversity.edu.ng/handle/20.500.12398/460
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.subjectBrain-computer interfaceen_US
dc.subjectChannel selectionen_US
dc.subjectFeature extractionen_US
dc.subjectLinear predictionen_US
dc.subjectOrthogonal transformen_US
dc.titleA transform-based feature extraction approach for motor imagery tasks classificationen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
A transform-based feature extraction approach for motor imagery tasks classification.pdf
Size:
2.66 MB
Format:
Adobe Portable Document Format
Description:
Article full-text
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.61 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Articles in Electrical and Electronics Engineering