This Research Topic is concerned with new technologies for Electroencephalography (EEG) and magnetoencephalography (MEG)-based Brain-Computer Interfaces (BCI) with special emphasis to neural underpinnings of Perception, Learning, and Motor control.
The method of EEG/MEG-data analysis may include emerging technologies of brain signal/image processing, including new algorithms on spatial filtering, feature extraction/selection, classifier design, and new control algorithms for BCI-based external robotic manipulators and Functional Electrical Stimulation based rehabilitative systems. Areas of interest include development of new algorithms for non-stationarity handling in single-trial classification of BCI data, implementing transfer learning/domain adaptation approaches in BCI.
Hybrid and multi-modal BCI also are gaining interest among researchers. Hybrid BCI attempts to utilize multiple brain signals to design and develop the BCI experiments. In contrast, multi-modal BCI employs multiple modalities of acquiring brain signals/images simultaneously or independently then attempts to fuse the brain signals/imaging information/attributes. These methods might help diagnose brain diseases and/or study cognitive functions.
We welcome both Original and Review articles using the above-mentioned technologies to develop practical stand-alone systems for future automated systems used in rehabilitative aids and to diagnose psychological diseases, memory malfunctioning (especially short-term and working memory), learning disability, neuro-motor disorders. We also welcome papers identifying brain activation regions and/or brain-connectivity involved in olfactory and tactile perception, learning, or mind-controlled artificial robotic limbs and motor control developed in BCI settings.
This Research Topic is concerned with new technologies for Electroencephalography (EEG) and magnetoencephalography (MEG)-based Brain-Computer Interfaces (BCI) with special emphasis to neural underpinnings of Perception, Learning, and Motor control.
The method of EEG/MEG-data analysis may include emerging technologies of brain signal/image processing, including new algorithms on spatial filtering, feature extraction/selection, classifier design, and new control algorithms for BCI-based external robotic manipulators and Functional Electrical Stimulation based rehabilitative systems. Areas of interest include development of new algorithms for non-stationarity handling in single-trial classification of BCI data, implementing transfer learning/domain adaptation approaches in BCI.
Hybrid and multi-modal BCI also are gaining interest among researchers. Hybrid BCI attempts to utilize multiple brain signals to design and develop the BCI experiments. In contrast, multi-modal BCI employs multiple modalities of acquiring brain signals/images simultaneously or independently then attempts to fuse the brain signals/imaging information/attributes. These methods might help diagnose brain diseases and/or study cognitive functions.
We welcome both Original and Review articles using the above-mentioned technologies to develop practical stand-alone systems for future automated systems used in rehabilitative aids and to diagnose psychological diseases, memory malfunctioning (especially short-term and working memory), learning disability, neuro-motor disorders. We also welcome papers identifying brain activation regions and/or brain-connectivity involved in olfactory and tactile perception, learning, or mind-controlled artificial robotic limbs and motor control developed in BCI settings.