An improved feature extraction method using low-rank representation for motor imagery classification. (February 2023)

• Record Type: Journal Article
• Authors: Zhu, Jieping; Zhu, Lei; Ding, Wangpan; Ying, Nanjiao; Xu, Ping; Zhang, Jianhai
• Is Part Of: Biomedical signal processing and control. Volume 80:Part 2(2023)
• Publication Date: 2023-02
• Subjects: Brain-computer interface -- Motor imagery -- Manifold learning -- Low-rank representation -- Feature extraction; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104389
• Languages: English
• ISSNs: 1746-8094

Abstract

Graphical abstract: Highlights: It is assumed that an EEG sample can be partitioned into a clean task-related EEG matrix and a noise matrix. Manifold learning, low-rank representation and projection are combined to one algorithm. The global structure information is kept while preserving the local neighborhood relation. An alternatively iterative algorithm is designed. Abstract: Motor imagery (MI) classification using electroencephalography (EEG) signal analysis is gaining significant interest for movement intent recognition, where feature extraction is critical for recognition accuracy. Traditional feature extraction methods ignore the spatial and neighborhood structure information of feature signals. In this paper, we assume that an EEG sample can be partitioned into a clean task-related EEG matrix and a noise matrix at first, because of the low-rank structure on underlying data representation disclosed by Low-Rank Representation (LRR). Then, Bilinear Two-Dimensional Discriminant Locality Preserving Projection (B2DDLPP) and LRR are combined to form a new feature extraction method known as Bilinear Low-Rank 2D Discriminant Locality Preserving Projection (BLRDLPP). It keeps the global structure information while preserving the local neighborhood relation. During experimentation, the proposed algorithm achieved classification accuracies of 73.26 % and 82.27 % on the four-class MI of the BCI Competition IV-2a dataset and III-3a dataset, respectively. The results demonstrate that the proposed method can effectively improve the acquisition of discriminant features.