A brain-computer interface (BCI) is a communication pathway for a user to interact with his/her surroundings by using brain signals, which contain information about the user’s cognitive state or intentions. The brain signals could be non-invasive, e.g., the scalp electroencephalogram (EEG), magnetoencephalography (MEG), functional magnetic resonance imaging (fMRI), and functional near-infrared spectroscopy (fNIRS), and invasive, e.g., electrocorticography (ECoG). Early BCI systems were mainly used to help people with disabilities. For example, motor imagery based BCIs have been used to help severely paralyzed patients to control powered exoskeletons or wheelchairs without the involvement of muscles, and event related potential spellers enable patients who cannot move nor speak to type. Recently, the application scope of BCIs has been extended to able-bodied people. However, there are still many challenges in the transition of BCIs from laboratory settings to real-life applications, including the reliability and convenience of the sensing hardware, and the availability of high-performance and robust algorithms for signal analysis and interpretation. This symposium focuses on the latter. It will discuss how advances in computational intelligence can facilitate BCI signal processing, feature extraction, and pattern recognition, in order to make them more robustness and reliability in everyday applications.
Topics of interest include, but are not limited to：
- Computational intelligence for BCI signal processing, e.g., ICA, CSP, CCA, etc.
- Computational intelligence for BCI feature extraction, e.g., time-domain, frequency domain, time-frequency domain, spatiotemporal features, Riemannian Geometry, etc.
- Computational intelligence for BCI pattern recognition, e.g., deep learning, transfer learning, ensemble learning, reinforcement learning, active learning, multi-view learning, etc.
- Computational intelligence for emerging BCI applications, e.g., Multimodal and multiparadigm BCI, Hybrid BCI systems, Collaborative BCI, Neuro-robotics, Neurorehabilitation, Passive BCI, Affective BCI, Virtual Reality BCI.
- Online and offline BCI applications, e.g., cognitive-state assessment, human performance enhancement, human-agent teaming, brain robot interface.
- Different modalities of BCIs, e.g., EEG, MEG, fMRI, fNIRS, ECoG, Spikes, LFPs, etc.
- Invasive and non-invasive BCIs
Boon Giin, Lee, University of Nottingham Ningbo China
Trung-Hau Nguyen, Chi Minh City University of Technology, Vietnam
Dalin Yang, Pusan National University, South Korea
Ogechi Onuoha, University of Glasgow, UK
Fu-Yin Cherng, National Taiwan University, Taiwan
Poyuan Jeng, National Yang Ming Chiao Tung University, Taiwan
Kuan-Jung Chiang, University of California San Diego, USA
Tien-Thong Nguyen Do, University of Technology Sydney, AU
Fred Chang, University of Technology Sydney, AU