As the invited editor of this special issue on braincomputer interface (BCI), I am pleased to give a comment on the state-of-the-art with the introduction of recent advances made at the Chengdu BCI Group, University of Electronic Science and Technology of China (UESTC). The ability to “talk” with others, no matter using speech, face expression, writing, gesture, or soul induction if possible, is a crucial factor that makes our life more enjoyable. Also, communication is the groundwork of human existence, makes us available to understand each other, share happiness or sadness, and run the daily life. However, there is also a group around us who lost all or part of these evolutional outputs, no matter due to accident or pathology. How to repair or replace such an output is the main dream of the brain-computer interface. The study on BCI was initiated about 40 years ago, and is now becoming a hot topic in neuroscience. BCI or brain-machine interface (BMI) is usually considered as an effective pathway connecting the human brain (or some primate animals) to a computer which directly translates human intentions into sequences of control commands for an output device. Meanwhile, BCIs can also be taken as a novel and interesting tool of communication for normal persons. For example, in the field of multimedia, BCIs could possibly be utilized as an additional modality, such as imagine games in which BCIs are used for control. BCIs can be invasive or non-invasive. The invasive way may provide more detailed and comprehensive information about the brain mental events, thus augment the communication between the computer and the brain. But the involved technical and scientific problems are not solved completely; much more efforts are still on the way. The non-invasive mode is assumed being based on the scalp electroencephalogram (EEG), and the main remaining problems are clear, i.e. how to get efficient features of the underlying mental activities and classify these features accurately. The current efforts are focused on maturing the
[1]
Dan Wu,et al.
Combining Spatial Filters for the Classification of Single-Trial EEG in a Finger Movement Task
,
2007,
IEEE Transactions on Biomedical Engineering.
[2]
Dezhong Yao,et al.
Stimulator selection in SSVEP-based BCI.
,
2008,
Medical engineering & physics.
[3]
Dezhong Yao,et al.
Transductive SVM for reducing the training effort in BCI
,
2007,
Journal of neural engineering.
[4]
Dezhong Yao,et al.
Frequency detection with stability coefficient for steady-state visual evoked potential (SSVEP)-based BCIs.
,
2008,
Journal of neural engineering.
[5]
Dezhong Yao,et al.
Application of SVM Framework for Classification of Single Trial EEG
,
2006,
ISNN.