Signal acquisition of brain–computer interfaces: A medical-engineering crossover perspective review

Fundamental Research, Journal Year: 2024, Volume and Issue: 5(1), P. 3 - 16

Published: April 16, 2024

Brain-computer interface (BCI) technology represents a burgeoning interdisciplinary domain that facilitates direct communication between individuals and external devices. The efficacy of BCI systems is largely contingent upon the progress in signal acquisition methodologies. This paper endeavors to provide an exhaustive synopsis technologies within realm by scrutinizing research publications from last ten years. Our review synthesizes insights both clinical engineering viewpoints, delineating comprehensive two-dimensional framework for understanding BCIs. We delineate nine discrete categories technologies, furnishing exemplars each salient challenges pertinent these modalities. furnishes researchers practitioners with broad-spectrum comprehension landscape BCI, deliberates on paramount issues presently confronting field. Prospective enhancements should focus harmonizing multitude disciplinary perspectives. Achieving equilibrium fidelity, invasiveness, biocompatibility, other pivotal considerations imperative. By doing so, we can propel forward, bolstering its effectiveness, safety, dependability, thereby contributing auspicious future human-technology integration.

Language: Английский

---

Heart-brain connection: How can heartbeats shape our minds?

Matter, Journal Year: 2024, Volume and Issue: 7(5), P. 1684 - 1687

Published: May 1, 2024

Language: Английский

---

Decoding Pain: A Comprehensive Review of Computational Intelligence Methods in Electroencephalography-Based Brain–Computer Interfaces

Diagnostics, Journal Year: 2025, Volume and Issue: 15(3), P. 300 - 300

Published: Jan. 27, 2025

Objective pain evaluation is crucial for determining appropriate treatment strategies in clinical settings. Studies have demonstrated the potential of using brain–computer interface (BCI) technology classification and detection. Collating knowledge insights from prior studies, this review explores extensive work on detection based electroencephalography (EEG) signals. It presents findings, methodologies, advancements reported 20 peer-reviewed articles that utilize machine learning deep (DL) approaches EEG-based We analyze various ML DL techniques, support vector machines, random forests, k-nearest neighbors, convolution neural network recurrent networks transformers, their effectiveness decoding The motivation combining AI with BCI lies significant real-time responsiveness adaptability these systems. reveal techniques effectively EEG signals recognize pain-related patterns. Moreover, we discuss challenges associated detection, focusing applications settings functional requirements effective By evaluating current research landscape, identify gaps opportunities future to provide valuable researchers practitioners.

Language: Английский

---

Objective Pain Assessment Using Deep Learning Through EEG-Based Brain–Computer Interfaces

Biology, Journal Year: 2025, Volume and Issue: 14(2), P. 210 - 210

Published: Feb. 17, 2025

Objective pain measurements are essential in clinical settings for determining effective treatment strategies. This study aims to utilize brain–computer interface technology reliable classification and detection. We developed an electroencephalography-based detection system comprising two main components: (1) pain/no-pain (2) severity across three levels: low, moderate, high. Deep learning models, including convolutional neural networks recurrent networks, were employed classify the wavelet features extracted through time–frequency domain analysis. Furthermore, we compared performance of our against conventional machine such as support vector machines random forest classifiers. Our deep approach outperformed baseline achieving accuracies 91.84% 87.94% classification, respectively.

Language: Английский

---

Align and Pool for EEG Headset Domain Adaptation (ALPHA) to Facilitate Dry Electrode Based SSVEP-BCI

IEEE Transactions on Biomedical Engineering, Journal Year: 2021, Volume and Issue: 69(2), P. 795 - 806

Published: Aug. 18, 2021

Objective: The steady-state visual evoked potential based brain-computer interface (SSVEP-BCI) implemented in dry electrodes is a promising paradigm for alternative and augmentative communication real-world applications. To improve its performance reduce the calibration effort dry-electrode systems, we utilize cross-device transfer learning by exploiting auxiliary individual wet-electrode electroencephalogram (EEG). Methods: We proposed novel framework named AL ign xmlns:xlink="http://www.w3.org/1999/xlink">P ool EEG xmlns:xlink="http://www.w3.org/1999/xlink">H eadset domain xmlns:xlink="http://www.w3.org/1999/xlink">A daptation (ALPHA), which aligns spatial pattern covariance adaptation. evaluate efficacy, 75 subjects performed an experiment of 2 sessions involving 12-target SSVEP-BCI task. Results: ALPHA significantly outperformed baseline approach (canonical correlation analysis, CCA) two competing approaches (transfer template CCA, ttCCA least square transformation, LST) directions. When transferring from wet to headsets, fully-calibrated task-related component analysis (TRCA). Conclusion: advances frontier recalibration-free SSVEP-BCIs boosts electrode systems. Significance: has methodological practical implications pushes boundary toward

Language: Английский

---

A Spectrally-Dense Encoding Method for Designing a High-Speed SSVEP-BCI With 120 Stimuli

IEEE Transactions on Neural Systems and Rehabilitation Engineering, Journal Year: 2022, Volume and Issue: 30, P. 2764 - 2772

Published: Jan. 1, 2022

The practical functionality of a brain-computer interface (BCI) is critically affected by the number stimuli, especially for steady-state visual evoked potential based BCI (SSVEP-BCI), which shows promise implementation multi-target system real-world applications. Joint frequency-phase modulation (JFPM) an effective and widely used method in modulating SSVEPs. However, ability JFPM to implement SSVEP-BCI with large e.g., over 100 remains unclear. To address this issue, spectrally-dense JPFM (sJFPM) proposed encode broad array modulates low- medium-frequency SSVEPs frequency interval 0.1 Hz triples stimuli conventional 120. validate effectiveness 120-target system, offline experiment subsequent online testing 18 healthy subjects total were conducted. verified feasibility using sJFPM designing 120 stimuli. Furthermore, demonstrated that achieved average performance 92.47±1.83% accuracy 213.23±6.60 bits/min information transfer rate (ITR), where more than 75% attained above 90% ITR 200 bits/min. This present study demonstrates elevating extends our understanding encoding means finer division.

Language: Английский

---

Optimizing Stimulus Frequency Ranges for Building a High-Rate High Frequency SSVEP-BCI

IEEE Transactions on Neural Systems and Rehabilitation Engineering, Journal Year: 2023, Volume and Issue: 31, P. 1277 - 1286

Published: Jan. 1, 2023

The brain-computer interfaces (BCIs) based on steady-state visual evoked potential (SSVEP) have been extensively explored due to their advantages in terms of high communication speed and smaller calibration time. stimuli the low- medium-frequency ranges are adopted most existing studies for eliciting SSVEPs. However, there is a need further improve comfort these systems. high-frequency used build BCI systems generally considered significantly comfort, but performance relatively low. distinguishability 16-class SSVEPs encoded by three frequency ranges, i.e., 31-34.75 Hz with an interval 0.25 Hz, 31-38.5 0.5 31-46 1 this study. We compare classification accuracy information transfer rate (ITR) corresponding system. According optimized range, study builds online 16-target SSVEP-BCI verifies feasibility proposed system 21 healthy subjects. narrowest 31-34.5 highest ITR. Therefore, range An averaged ITR obtained from experiment 153.79 ± 6.39 bits/min. These findings contribute development more efficient comfortable SSVEP-based BCIs.

Language: Английский

---

A hybrid steady-state visual evoked response-based brain-computer interface with MEG and EEG

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 223, P. 119736 - 119736

Published: Feb. 25, 2023

While recent developments in electroencephalogram (EEG)-based brain-computer interfaces (BCIs) have enabled a bridge between the brain and external devices with relatively high communication speed, there is still room for improvement. Notably, phenomenon of "BCI illiteracy," which refers to 15%–30% people who struggle type or control using BCI, remains unsolved, limiting practical application BCI systems. The EEG-based BCIs performance constrained by low-quality scalp EEG signals due attenuation distortion skull. To address these limitations, this study proposes hybrid system combining magnetoencephalogram (MEG), neuroimaging technology not influenced volume conduction effect, boost enhancing signal quality. Comparative experiments involving 22 subjects showed that steady-state visual evoked response (SSVER) from MEG has wider range effective bandwidth higher signal-to-noise ratio than EEG. Moreover, differences spectral spatiotemporal characteristics explain better performance. Simultaneous MEG-EEG recording suggested achieved significantly information transfer rate either modality alone (hybrid: 312 ± 17 bits/min, MEG: 272 EEG: 240 27 bits/min). 40-target classification accuracy illiterate" increased 50% 95% help MEG. These results highlight methodological advantages suggesting promising paradigm implementing high-speed BCIs.

Language: Английский

---

TRCA-Net: using TRCA filters to boost the SSVEP classification with convolutional neural network

Journal of Neural Engineering, Journal Year: 2023, Volume and Issue: 20(4), P. 046005 - 046005

Published: July 3, 2023

Abstract Objective. The steady-state visual evoked potential (SSVEP)-based brain–computer interface has received extensive attention in research due to its simple system, less training data, and high information transfer rate. There are currently two prominent methods dominating the classification of SSVEP signals. One is knowledge-based task-related component analysis (TRCA) method, whose core idea find spatial filters by maximizing inter-trial covariance. other deep learning-based approach, which directly learns a model from data. However, how integrate achieve better performance not been studied before. Approach. In this study, we develop novel algorithm named TRCA-Net (TRCA-Net) enhance signal classification, enjoys advantages both method model. Specifically, proposed first performs TRCA obtain filters, extract components Then TRCA-filtered features different rearranged as new multi-channel signals for convolutional neural network (CNN) classification. Introducing approach improves signal-to-noise ratio input hence benefiting learning Main results. We evaluate using publicly available large-scale benchmark datasets, results demonstrate effectiveness TRCA-Net. Additionally, offline online experiments separately testing ten five subjects further validate robustness Further, conduct ablation studies on CNN backbones that our can be transplanted into models boost their performance. Significance. believed have promising promote practical applications communication control. code at https://github.com/Sungden/TRCA-Net .

Language: Английский

---

Deep transfer learning-based SSVEP frequency domain decoding method

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 89, P. 105931 - 105931

Published: Jan. 2, 2024

Language: Английский

---