Complex networks and deep learning for EEG signal analysis
- PDF / 3,185,460 Bytes
- 20 Pages / 595.276 x 790.866 pts Page_size
- 57 Downloads / 205 Views
(0123456789().,-volV)(0123456789(). ,- volV)
REVIEW PAPER
Complex networks and deep learning for EEG signal analysis Zhongke Gao1 • Weidong Dang1 • Xinmin Wang1 • Xiaolin Hong1 • Linhua Hou1 • Kai Ma2 Matjazˇ Perc3
•
Received: 4 February 2020 / Revised: 20 July 2020 / Accepted: 16 August 2020 Ó Springer Nature B.V. 2020
Abstract Electroencephalogram (EEG) signals acquired from brain can provide an effective representation of the human’s physiological and pathological states. Up to now, much work has been conducted to study and analyze the EEG signals, aiming at spying the current states or the evolution characteristics of the complex brain system. Considering the complex interactions between different structural and functional brain regions, brain network has received a lot of attention and has made great progress in brain mechanism research. In addition, characterized by autonomous, multi-layer and diversified feature extraction, deep learning has provided an effective and feasible solution for solving complex classification problems in many fields, including brain state research. Both of them show strong ability in EEG signal analysis, but the combination of these two theories to solve the difficult classification problems based on EEG signals is still in its infancy. We here review the application of these two theories in EEG signal research, mainly involving brain–computer interface, neurological disorders and cognitive analysis. Furthermore, we also develop a framework combining recurrence plots and convolutional neural network to achieve fatigue driving recognition. The results demonstrate that complex networks and deep learning can effectively implement functional complementarity for better feature extraction and classification, especially in EEG signal analysis. Keywords Electroencephalogram signals Complex network Deep learning
Introduction Real-world systems evolve over time and present complex system dynamics. Observing complex systems from different aspects can acquire diverse time-based measurements, namely, time series. Via learning the system dynamics from these acquired time series, one can better understand the external system behaviors and then predict the system accurately. After a long-term development,
& Matjazˇ Perc [email protected]; [email protected] Zhongke Gao [email protected] 1
School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
2
Tencent Youtu Lab, Malata Building, 9998 Shennan Avenue, Shenzhen 518057, Guangdong Province, China
3
Faculty of Natural Sciences and Mathematics, University of Maribor, Korosˇka cesta 160, 2000 Maribor, Slovenia
observing and characterizing complex systems from the observed time series has become a major filed of complex system sciences. Common methods applied into time series analysis mainly contain complexity theory (Aboy et al. 2006), symbolic theory (Keogh et al. 2003), chaos theory (Sugihara and May 1990), correlation theory (Podobnik and Stanley 2008), etc. Each of them specializes in a spe
Data Loading...