Your browser doesn't support javascript.
loading
The LightGBM-based classification algorithm for Chinese characters speech imagery BCI system.
Pan, Hongguang; Li, Zhuoyi; Tian, Chen; Wang, Li; Fu, Yunpeng; Qin, Xuebin; Liu, Fei.
Afiliación
  • Pan H; College of Electrical and Control Engineering, Xi'an University of Science and Technology, Xi'an, 710054 Shaanxi China.
  • Li Z; College of Electrical and Control Engineering, Xi'an University of Science and Technology, Xi'an, 710054 Shaanxi China.
  • Tian C; Shaanxi Broadcasting Corporation, Xi'an, 710061 Shaanxi China.
  • Wang L; School of Electronics and Communication Engineering, Guangzhou University, Guangzhou, 510006 Guangdong China.
  • Fu Y; College of Electrical and Control Engineering, Xi'an University of Science and Technology, Xi'an, 710054 Shaanxi China.
  • Qin X; College of Electrical and Control Engineering, Xi'an University of Science and Technology, Xi'an, 710054 Shaanxi China.
  • Liu F; College of Electrical and Control Engineering, Xi'an University of Science and Technology, Xi'an, 710054 Shaanxi China.
Cogn Neurodyn ; 17(2): 373-384, 2023 Apr.
Article en En | MEDLINE | ID: mdl-37007202
Brain-computer interface (BCI) can obtain text information by decoding language induced electroencephalogram (EEG) signals, so as to restore communication ability for patients with language impairment. At present, the BCI system based on speech imagery of Chinese characters has the problem of low accuracy of features classification. In this paper, the light gradient boosting machine (LightGBM) is adopted to recognize Chinese characters and solve the above problems. Firstly, the Db4 wavelet basis function is selected to decompose the EEG signals in six-layer of full frequency band, and the correlation features of Chinese characters speech imagery with high time resolution and high frequency resolution are extracted. Secondly, the two core algorithms of LightGBM, gradient-based one-side sampling and exclusive feature bundling, are used to classify the extracted features. Finally, we verify that classification performance of LightGBM is more accurate and applicable than the traditional classifiers according to the statistical analysis methods. We evaluate the proposed method through contrast experiment. The experimental results show that the average classification accuracy of the subjects' silent reading of Chinese characters "(left)", "(one)" and simultaneous silent reading is improved by 5.24%, 4.90% and 12.44% respectively.
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Prognostic_studies Idioma: En Revista: Cogn Neurodyn Año: 2023 Tipo del documento: Article

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Prognostic_studies Idioma: En Revista: Cogn Neurodyn Año: 2023 Tipo del documento: Article
...