Weak Feature Extraction and Strong Noise Suppression for SSVEP-EEG Based on Chaotic Detection Technology

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 29; pp. 862 - 871
• Main Authors: Zhang, Kai, Xu, Guanghua, Du, Chenghang, Wu, Yongchen, Zheng, Xiaowei, Zhang, Sicong, Han, Chengcheng, Liang, Renhao, Chen, Ruiquan
• Format: Journal Article
• Language: English
• Published: United States IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: BCI-Illiteracy; Brain computer interface (BCI); Brain modeling; Chaos; Chaotic detection (Chaos); EEG; electroencephalogram (EEG); Electroencephalography; Feature extraction; Force; Mathematical model; Noise reduction; steady-state visual evoked potentials (SSVEP); Visualization
• ISSN: 1534-4320; 1558-0210
• DOI: 10.1109/TNSRE.2021.3073918

Brain computer interface (BCI) is a novel communication method that does not rely on the normal neural pathway between the brain and muscle of human. It can transform mental activities into relevant commands to control external equipment and establish direct communication pathway. Among different paradigms, steady-state visual evoked potential (SSVEP) is widely used due to its certain periodicity and stability of control. However, electroencephalogram (EEG) of SSVEP is extremely weak and companied with multi-scale and strong noise. Existing algorithms for classification are based on the principle of template matching and spatial filtering, which cannot obtain satisfied performance of feature extraction under the multi-scale noise. Especially for the subjects produce weak response for external stimuli in EEG representation, i.e., BCI-Illiteracy subject, traditional algorithms are difficult to recognize the internal patterns of brain. To address this issue, a novel method based on Chaos theory is proposed to extract feature of SSVEP. The rule of this method is applying the peculiarity of nonlinear dynamics system to detect feature of SSVEP by judging the state changes of chaotic systems after adding weak EEG. To evaluate the validity of proposed method, this research recruit 32 subjects to participate the experiment. All subjects are divided into two groups according to the preliminary classification accuracy (mean acc >70% or < 70%) by canonical correlation analysis and we define the accuracy above 70% as group A (normal subjects), below 70% as group B (BCI-Illiteracy). Then, the classification accuracy and information transmission rate of two groups are verified using Chaotic theory. Experimental results show that all classification methods using in our study achieve good performance for normal subjects while chaos obtain excellent performance and significant improvements than traditional methods for BCI-Illiteracy.