Brain-Computer-Int erface Inspire d Communications

Following the massive commercialization of 5G mobile communication systems, both academia and industry are initiating research activities to shape the next-generation communication systems, namely,6G.Although the detailed killer-applications and key technologies of 6G have not been clearly defined yet,it is commonly expected that 6G will provide hyper-coverage and hyper-connectivity.Enabled by these capabilities, the 6G communication systems are especially aiming at improving the user’s experience greatly, or more ambitiously, to change the way of human’s everyday life.So far, many new services with more stringent requirements, such as truly immersive extended reali¬ty (XR), high-fidelity mobile hologram, and digital replica, are expected to be satisfied by the 6G communication systems.

In recent years, brain-computer-interface (BCI)technologies have achieved extraordinary progress.A BCI, which is also called a brain-machine interface (BMI), is a direct communication pathway between the brain and an external device.The BCIs are often directed at assisting, augmenting, or repairing human cognitive or sensory-motor functions.The latest report shows that the transmission rate by the BCIs can achieve more than 5bits/s, which means in online typing applications, the people using BCIs are comparable with those using fingers.We can anticipate that empowered by advanced BCIs in the future,people will express their commands or desires more directly and conveniently.

The fast and reliable transmission is the key performance indicator of BCIs.Beside the neural and brain technologies, the main technical challenges of BCIs come from the brain communication theory and the advanced decoding algorithms for brain signal.In the past, the neuroscientists often use very basic communication technologies for BCIs.However, as the BCIs attracting more attentions, more advanced communication technologies for the brain channel are emerging.

The primary goal of this feature topic is to present the state-of-the-art high-quality research advances in the theoretical foundations and practical implementations of BCI communications, including brain signal modulation/demodulation methods, artificial intelligence aided detection and analysis of brain signals, prototypes and experimental results for BCI communications, and application scenarios design with requirement analysis for BCI communications,etc.All of the submitted papers are evaluated according to the standard reviewing process of China Communications.Following a rigorous peer-review process, 7 articles are finally accepted in this special issue.

The accepted papers cover the topics about the user-friendly brain signal modulation, stimuli design,transfer learning based brain signal detection and analysis, interference cancellation of brain signals,BCI rehabilitation prototype design, and practical application of BCI in cognitive state detection.We hope this special issue may inspire the existing and important future research works in various BCI inspired communications.

Steady-state visual evoked potential (SSVEP) is one of the most popular brain signal modulation methods.It has the advantages such as high signal-to-noise ratio, high information transfer rate(ITR), and minimal user training.However, the conventional stimuli normally relies on the low frequency, i.e., about 15Hz, which is quite far away from user-friendly.The first paper entitled “A User-friendly SSVEP-based BCI Using Imperceptible Phase-coded Flickers at 60Hz” by Wang et al.studies a SSVEP elicited by flickers at 60Hz, which is higher than the critical fusion frequency.Although the BCI performance of 60Hz was lower than that of 15Hz and 30Hz, the results of the behavioral test indicated that, with no perception of flicker, the BCI system with 60Hz was more comfortable to use than 15Hz and 30Hz.Moreover, the maximum ITR for a subject was 80bpm with 0.5s at 60Hz.This study is important because it demonstrates the feasibility and potential of a user-friendly SSVEP-based BCI using imperceptible flickers.

The next paper entitled “Steady-State Visual Evoked Potential (SSVEP) in A New Paradigm Containing Dynamic Fixation Points” by Li et al.is also on the SSVEP based brain signal modulation.In this paper, the authors further consider the spatial information beside the frequency domain modulation.So far, the edge information of each region cannot be identified in spatial coding based on SSVEP-BCI technology, and the user experience is poor.To solve this problem, a new paradigm is designed to explore the relationship between the fixation point position of continuous sliding and the correlation coefficient ratio in the dual frequency case.Also, the authors demonstrate that it is feasible to detect the amplitude change of frequency component in SSVEP by utilizing the spatial coding method in this paper to improve the extraction accuracy of spatial information.

Although the bandwidth of communication systems increased dramatically in recent years, the demanding requirement increased much faster.Neurophysiological assessment of image and video quality has highlight advantages for it does not interfere with natural viewing behavior, and it can be used for the network operator to evaluate the necessary clarity of the images or videos transmitted.In the paper“Toward A Neurophysiological Measure of Image Quality Perception based on Algebraic Topology Analysis, Liu et al.propose an EEG analysis approach based on algebraic topology analysis, and the result shows that the difference between Euler characteristics of EEG evoked by different distortion images is striking both in the alpha and beta band.Moreover, the authors further discuss the relationship between the images and the EEG signals, and the results implied that the algebraic topological properties of images are consistent with that of brain perception, which is possible to give birth to brain inspired image compression based on algebraic topological features.This study is beneficial to provide a reliable score for data compression in the network and improve the network transmission capacity.

Beside SSVEP, motor imagery (MI) is also a widely used BCI.As it is passive and does not need tages in many application.The non-stationary of the MI electroencephalography (EEG) signal combined with the changes of the experimental environment make the feature distribution of EEG signal transfer.In the paper “Transfer Learning Algorithm Design for Feature Transfer Problem in Motor Imagery Brain-computer Interface”, Li et al.propose a transfer learning algorithm to solve the problem of EEG signal feature transfer.The results show that the proposed algorithm can significantly improve the classification accuracy of the test set.Moreover, the algorithm based on transfer learning has the potential to improve the consistency of feature distribution that the traditional algorithm does not have.

In the signal processing of the brain signals, the interferences such as ocular artifacts in EEG recordings will highly influence the demodulation and decoding results.In “Removal of Ocular Artifacts from Electroencephalo-graph by Improving Variational Mode Decomposition”, Wang et al.propose an improved squirrel search algorithm based on global optimal guidance and opposition based learning.The algorithm can optimize the important parameters of variational mode decomposition (VMD), which is used for removing ocular artifacts in the EEG signal analysis.The experimental results show that the SNR of the dataset can be improved.

Applications of BCI are also important.In different applications, various customized prototypes should be designed.In “BCI+VR Rehabilitation Design of Closed-Loop Motor Imagery based on the Degree of Drug Addiction”, Gu et al.design a closed-loop virtual-reality (VR), motor imagery (MI)rehabilitation training system based on BCI, aiming to enhance the self-control, cognition, and emotional regulation of drug addicts via personalized rehabilitation schemes.In the prototype, EEG and near-infrared spectroscopy (NIRS) are operated in a dual-mode fashion, and the synchronous signals are jointly analyzed using a convolutional neural network (CNN) algorithm to detect and classify the addiction degree.

Using EEG for cognitive state detection with various tasks is another important application of BCIs.In our last paper “E3GCAPS: Efficient EEG-based Multi-Capsule Framework with Dynamic Attention for Cross-subject Cognitive State Detection”, Zhao et al.propose an efficient interpretation model based on multiple capsule networks for cross-subject EEG cognitive state detection.Specifically, a self-exprestions between samples, which is beneficial to alleviate the sensitivity of outliers that are caused by the individual differences of cross-subject EEG.Experimental results demonstrate that the proposed scheme can achieve remarkable results on the EEG-based cross-subject cognitive state detection under different tasks.

To sum up, the Guest Editors of this feature topic would like to thank all the authors for their valuable contributions and the anonymous reviewers for their helpful comments and suggestions.Also, we would like to acknowledge the guidance from the editorial team of China Communications.