Algorithm Research & Explore
|
App. Res. of Comp. Printed Article
Vol. 41, 2024 No. 2
501-506

Multilayer discriminant dictionary pair learning algorithm for motor imagery electroencephalogram recognition

Shang Junyan1,2
Ding Hui1
Hu Xuelong2
1. Dept. of Information Engineering, Changzhou Vocational Institute of Industry Technology, Changzhou Jiangsu 213164, China
2. College of Information Engineering, Yangzhou University, Yangzhou Jiangsu 225127, China
DOI: 10.19734/j.issn.1001-3695.2023.06.0238

Abstract

BCI for motion imagination can directly control external electronic devices in real-time using electroencephalogram signals triggered by specific actions of autonomous imagination. MI-EEG signals have characteristics such as low signal-to-noise ratio, large intra-class differences, and small inter-class differences, resulting in low and unstable recognition performance in MI-EEG. This paper proposed a multi-layer discriminant dictionary pair learning(MDDPL) algorithm to address the issue. Different from current dictionary based MI-EEG recognition algorithm, MDDPL incorporated the dictionary pair learning into the multi-layer learning model and projects data into the discriminant subspaces through a series of nonlinear projections. With the joint learning of synthesis dictionary and analysis dictionary, MDDPL used the encoding vector of the previous layer as the input of the current layer. At the same time, MDDPL constructed the multi-classification item based on the analysis dictionary on each layer of the model, so as to ensure the minimum classification error of sparse encoding and enhance the model's class differentiation ability. In addition, MDDPL applied low rank constraints on the sparse encoding matrix of the last layer to ensure its compactness and similarity. In solving the objective function, MDDPL adopted an alternating update strategy to obtain analytical solutions for each parameter, ensuring that all parameters were simultaneously optimal. The experimental results on the international BCI competition datasets show that the MDDPL algorithm achieves the best classification performance among all comparison algorithms.

Foundation Support

国家自然科学基金资助项目(61802336)
江苏省“六大人才高峰”第七批高层次人才资助项目(2010-DZXX-149)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2023.06.0238
Publish at: Application Research of Computers Printed Article, Vol. 41, 2024 No. 2
Section: Algorithm Research & Explore
Pages: 501-506
Serial Number: 1001-3695(2024)02-027-0501-06

Publish History

[2023-08-03] Accepted Paper
[2024-02-05] Printed Article

Cite This Article

商俊燕, 丁辉, 胡学龙. 面向运动想象脑电信号识别的多层判别字典对学习方法 [J]. 计算机应用研究, 2024, 41 (2): 501-506. (Shang Junyan, Ding Hui, Hu Xuelong. Multilayer discriminant dictionary pair learning algorithm for motor imagery electroencephalogram recognition [J]. Application Research of Computers, 2024, 41 (2): 501-506. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)