sensors-logo

Journal Browser

Journal Browser

Special Issue "Brain-Computer and Brain-Machine Interfaces: Advances in EEG Acquisition, Processing and Machine Learning Technologies towards Better Usability"

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Biomedical Sensors".

Deadline for manuscript submissions: closed (30 April 2021).

Special Issue Editors

Prof. Natsue Yoshimura
E-Mail Website
Guest Editor
Institute of Innovative Research, Tokyo Institute of Technology, Tokyo 152-8550, Japan
Interests: neural decoding; machine learning, non-invasive brain imaging; brain-machine interfaces; source localization
Dr. Ludovico Minati
E-Mail Website
Guest Editor
Institute of Innovative Research, Tokyo Institute of Technology, Tokyo, Japan
Interests: EEG hardware; signal processing; robotics; brain-machine interfaces; adaptive and non-linear techniques; health technology innovation and assessment
Dr. Masaki Nakanishi
E-Mail Website
Guest Editor
Swartz Center for Computational Neuroscience, University of California San Diego, USA
Interests: brain-computer interfaces; biological signal processing; machine learning
Special Issues and Collections in MDPI journals
Dr. Fernando E. Rosas
E-Mail Website
Guest Editor
Faculty of Medicine, Department of Brain Sciences, Imperial College London, UK
Interests: non-linear methods; neural biomarkers; multivariate statistics; resting-state neuroimaging; neural decoding; computational psychiatry; active inference

Special Issue Information

Dear Colleagues,

Recent developments in data acquisition and processing technology for electroencephalography (EEG), alongside new filtering and machine learning methods, are helping to improve the decoding performance of simplified, low electrode-count EEG systems. These developments have the potential for expanding the scope and potential clinical applicability of EEG-based Brain-Computer and Brian-Machine Interfaces (BCI, BMI). To further accelerate this trend and enhance practical viability and thus social impact, it is necessary to conjointly explore multiple innovation avenues. One example is creating, bolstering, and exploring pathways for incorporating knowledge harvested from laboratory-based experiments using high-density EEG or other neuroimaging methods, alongside machine learning algorithms including deep-learning, into portable and self-contained EEG systems truly suitable for everyday patient use.
Under this overarching aim, the special issue addresses all types of EEG-based neural decoding infrastructure aimed at BCI and BMI, including but not limited to the following:

  • Adaptive and non-linear decoding techniques
  • Advances in real-time processing technology, including artefact reduction and electrode fault mitigation
  • Advances in sensor, front-end and other hardware technologies, including practical circuits
  • Advances in all engineering aspects of low-cost, wearable devices, including human-centric design
  • Analyses of normative, certification and impact, including health technology assessment-based analyses and innovation models
  • Brain activity imaging using EEG or other neuroimaging techniques, focusing on extracting priors for boosting decoding based on low channel numbers
  • Forward techniques for optimizing location and number of electrodes
  • General applications for portable or wearable EEG data acquisition systems
  • Hybrid approaches, for example combining EEG with machine vision to drive a robot
  • Multi-modal approaches, for example fusing EEG with electro-oculography or systemic physiological responses
  • New patient-friendly paradigms, focusing on their realistic performance in low channel-count scenarios
  • Open data-sets and community resources
  • Open-source hardware and software, with focus on low-cost, wearable devices
  • Patient-based studies of realistic application scenarios including usability evaluations
  • Performance comparisons between low- and high- density EEG, including laboratory- vs. field-based context comparisons
  • Signal processing techniques and machine learning algorithms, with a focus on deep-learning techniques

Prof. Natsue Yoshimura
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Brain-Computer interface
  • Brain-Machine interface
  • Electroencephalography
  • Machine learning and deep learning
  • Neural decoding
  • Signal processing
  • Adaptive decoding
  • Transfer learning
  • Portable or wearable EEG
  • Hybrid and multi-modal approach

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Open AccessArticle
Single-Option P300-BCI Performance Is Affected by Visual Stimulation Conditions
Sensors 2020, 20(24), 7198; https://doi.org/10.3390/s20247198 - 16 Dec 2020
Cited by 1 | Viewed by 497
Abstract
The P300 paradigm is one of the most promising techniques for its robustness and reliability in Brain-Computer Interface (BCI) applications, but it is not exempt from shortcomings. The present work studied single-trial classification effectiveness in distinguishing between target and non-target responses considering two [...] Read more.
The P300 paradigm is one of the most promising techniques for its robustness and reliability in Brain-Computer Interface (BCI) applications, but it is not exempt from shortcomings. The present work studied single-trial classification effectiveness in distinguishing between target and non-target responses considering two conditions of visual stimulation and the variation of the number of symbols presented to the user in a single-option visual frame. In addition, we also investigated the relationship between the classification results of target and non-target events when training and testing the machine-learning model with datasets containing different stimulation conditions and different number of symbols. To this end, we designed a P300 experimental protocol considering, as conditions of stimulation: the color highlighting or the superimposing of a cartoon face and from four to nine options. These experiments were carried out with 19 healthy subjects in 3 sessions. The results showed that the Event-Related Potentials (ERP) responses and the classification accuracy are stronger with cartoon faces as stimulus type and similar irrespective of the amount of options. In addition, the classification performance is reduced when using datasets with different type of stimulus, but it is similar when using datasets with different the number of symbols. These results have a special connotation for the design of systems, in which it is intended to elicit higher levels of evoked potentials and, at the same time, optimize training time. Full article
Show Figures

Figure 1

Open AccessArticle
Cross-Frequency Power-Power Coupling Analysis: A Useful Cross-Frequency Measure to Classify ICA-Decomposed EEG
Sensors 2020, 20(24), 7040; https://doi.org/10.3390/s20247040 - 09 Dec 2020
Cited by 1 | Viewed by 1215
Abstract
Magneto-/Electro-encephalography (M/EEG) commonly uses (fast) Fourier transformation to compute power spectral density (PSD). However, the resulting PSD plot lacks temporal information, making interpretation sometimes equivocal. For example, consider two different PSDs: a central parietal EEG PSD with twin peaks at 10 Hz and [...] Read more.
Magneto-/Electro-encephalography (M/EEG) commonly uses (fast) Fourier transformation to compute power spectral density (PSD). However, the resulting PSD plot lacks temporal information, making interpretation sometimes equivocal. For example, consider two different PSDs: a central parietal EEG PSD with twin peaks at 10 Hz and 20 Hz and a central parietal PSD with twin peaks at 10 Hz and 50 Hz. We can assume the first PSD shows a mu rhythm and the second harmonic; however, the latter PSD likely shows an alpha peak and an independent line noise. Without prior knowledge, however, the PSD alone cannot distinguish between the two cases. To address this limitation of PSD, we propose using cross-frequency power–power coupling (PPC) as a post-processing of independent component (IC) analysis (ICA) to distinguish brain components from muscle and environmental artifact sources. We conclude that post-ICA PPC analysis could serve as a new data-driven EEG classifier in M/EEG studies. For the reader’s convenience, we offer a brief literature overview on the disparate use of PPC. The proposed cross-frequency power–power coupling analysis toolbox (PowPowCAT) is a free, open-source toolbox, which works as an EEGLAB extension. Full article
Show Figures

Figure 1

Back to TopTop