A Lightweight Network with Domain Adaptation for Motor Imagery Recognition DOI Creative Commons
Xinmin Ding, Zenghui Zhang, Kun Wang

et al.

Entropy, Journal Year: 2024, Volume and Issue: 27(1), P. 14 - 14

Published: Dec. 27, 2024

Brain-computer interfaces (BCI) are an effective tool for recognizing motor imagery and have been widely applied in the control assistive operation domains. However, traditional intention-recognition methods face several challenges, such as prolonged training times limited cross-subject adaptability, which restrict their practical application. This paper proposes innovative method that combines a lightweight convolutional neural network (CNN) with domain adaptation. A feature extraction module is designed to extract key features from both source target domains, effectively reducing model's parameters improving real-time performance computational efficiency. To address differences sample distributions, adaptation strategy introduced optimize alignment. Furthermore, adversarial employed promote learning of domain-invariant features, significantly enhancing generalization ability. The proposed was evaluated on fNIRS dataset, achieving average accuracy 87.76% three-class classification task. Additionally, experiments were conducted two perspectives: model structure optimization data selection. results demonstrated potential advantages this applications recognition systems.

Language: Английский

A Comparative Review of Detection Methods in SSVEP-based Brain-Computer Interfaces DOI Creative Commons

Amin Besharat,

Nasser Samadzadehaghdam, Reyhaneh Afghan

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 181232 - 181270

Published: Jan. 1, 2024

Language: Английский

Citations

2
Current implications of EEG and fNIRS as functional neuroimaging techniques for motor recovery after stroke DOI Creative Commons
Xiaolong Sun,

Chun‐Qiu Dai,

Xiangbo Wu

et al.

Medical Review, Journal Year: 2024, Volume and Issue: 4(6), P. 492 - 509

Published: May 23, 2024

Persistent motor deficits are highly prevalent among post-stroke survivors, contributing significantly to disability. Despite the prevalence of these deficits, precise mechanisms underlying recovery after stroke remain largely elusive. The exploration system reorganization using functional neuroimaging techniques represents a compelling yet challenging avenue research. Quantitative electroencephalography (qEEG) parameters, including power ratio index, brain symmetry and phase synchrony have emerged as potential prognostic markers for overall post-stroke. Current evidence suggests correlation between qEEG parameters outcomes in recovery. However, accurately identifying source activity poses challenge, prompting integration EEG with other modalities, such near-infrared spectroscopy (fNIRS). fNIRS is nowadays widely employed investigate function, revealing disruptions network induced by stroke. Combining two methods, referred integrated fNIRS-EEG, neural hemodynamics signals can be pooled out offer new types neurovascular coupling-related features, which may more accurate than individual modality alone. By harnessing fNIRS-EEG localization, connectivity analysis could applied characterize cortical associated stroke, providing valuable insights into assessment treatment

Language: Английский

Citations

1
Recent progress on smart lower prosthetic limbs: a comprehensive review on using EEG and fNIRS devices in rehabilitation DOI Creative Commons
Nouf Jubran AlQahtani, Ibraheem Al‐Naib, Murad Althobaiti

et al.

Frontiers in Bioengineering and Biotechnology, Journal Year: 2024, Volume and Issue: 12

Published: Aug. 26, 2024

The global rise in lower limb amputation cases necessitates advancements prosthetic technology to enhance the quality of life for affected patients. This review paper explores recent integration EEG and fNIRS modalities smart limbs rehabilitation applications. synthesizes current research progress, focusing on synergy between brain-computer interfaces neuroimaging technologies functionality user experience prosthetics. discusses potential decoding neural signals, enabling more intuitive responsive control devices. Additionally, highlights challenges, innovations, prospects associated with incorporation these neurotechnologies field rehabilitation. insights provided this contribute a deeper understanding evolving landscape pave way effective user-friendly solutions realm neurorehabilitation.

Language: Английский

Citations

1
Strategic Integration: A Cross-Disciplinary Review of the fNIRS-EEG Dual-Modality Imaging System for Delivering Multimodal Neuroimaging to Applications DOI Creative Commons
Jiafa Chen, Kaiwei Yu, Yifei Bi

et al.

Brain Sciences, Journal Year: 2024, Volume and Issue: 14(10), P. 1022 - 1022

Published: Oct. 16, 2024

Background: Recent years have seen a surge of interest in dual-modality imaging systems that integrate functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG) to probe brain function. This review aims explore the advancements clinical applications this technology, emphasizing synergistic integration fNIRS EEG. Methods: The begins with detailed examination fundamental principles distinctive features EEG techniques. It includes critical technical specifications, data-processing methodologies, analysis techniques, alongside an exhaustive evaluation 30 seminal studies highlight strengths weaknesses fNIRS-EEG bimodal system. Results: paper presents multiple case across various domains—such as attention-deficit hyperactivity disorder, infantile spasms, depth anesthesia, intelligence quotient estimation, epilepsy—demonstrating system’s potential uncovering disease mechanisms, evaluating treatment efficacy, providing precise diagnostic options. Noteworthy research findings pivotal breakthroughs further reinforce developmental trajectory interdisciplinary field. Conclusions: addresses challenges anticipates future directions for dual-modal system, including improvements hardware software, enhanced system performance, cost reduction, real-time monitoring capabilities, broader applications. offers researchers comprehensive understanding field, highlighting neuroscience medicine.

Language: Английский

Citations

1
Near-infrared Spectroscopy for Brain and Breast Imaging DOI Open Access
Daniel H. Buckley

Published: Dec. 26, 2023

Near-infrared spectroscopy (NIRS) has become a key modality in medical imaging, finding application both brain and breast imaging. This paper discusses the current trends NIRS for exploring advances multi-modal integration with modalities such as functional magnetic resonance imaging (fMRI) electroencephalography (EEG). Challenges related to spatial resolution, depth sensitivity, impact of extracerebral tissues on signal specificity are examined. In addition, ongoing efforts enhance hemodynamic measurements’ quantitative accuracy. Challenges, including limited resolution tissue heterogeneity, discussed. The discussion extends diffuse optical tomography instrumentation development, clinical trials studies validating diagnostic efficacy emphasizes need standardization, into routine practice, motivates future work.

Language: Английский

Citations

1
Enhancing classification accuracy of HRF signals in fNIRS using semi-supervised learning and filtering DOI
Cheng-Hsuan Chen, Kuo‐Kai Shyu, Yi-Chao Wu

et al.

Progress in brain research, Journal Year: 2024, Volume and Issue: unknown, P. 83 - 104

Published: Jan. 1, 2024

Language: Английский

Citations

0
Brain-Computer Interfaces in Robotic Arm for Motor Rehabilitation after Stroke DOI Creative Commons

Yiwei Le

MedScien, Journal Year: 2024, Volume and Issue: 1(7)

Published: June 6, 2024

Stroke is a common disease that can cause injury to humankind’s neuron systems all over the world. To help these patients with their motor rehabilitation, applying Brain-Computer interface (BCI) technology has recently become popular approach. One innovative method of using BCI regain ability develop BCIs-controlled external robotic arm system. This paper aims summarize some research focusing on this field, analyze outstanding points and drawbacks, provide several ways improve First, author gives brief introduction BCIs controlled arm. After that, analyzes advantages disadvantages system then potential solutions, fNIRS-EEG three implanting methods. Finally, discusses previous studies provides future directions in advancing In review, mainly focuses approaches based studies. By stressing drawbacks difficulties each technique, comes up other methods related latest combines together reaches new directions. The contained review covers past five years, from 2018 2023.

Language: Английский

Citations

0
Hybrid Functional Near-Infrared Spectroscopy System and Electromyography for Prosthetic Knee Control DOI Creative Commons
Nouf Jubran AlQahtani, Ibraheem Al‐Naib, Ijlal Shahrukh Ateeq

et al.

Biosensors, Journal Year: 2024, Volume and Issue: 14(11), P. 553 - 553

Published: Nov. 13, 2024

The increasing number of individuals with limb loss worldwide highlights the need for advancements in prosthetic knee technology. To improve control and quality life, integrating brain-computer communication motor imagery offers a promising solution. This study introduces hybrid system that combines electromyography (EMG) functional near-infrared spectroscopy (fNIRS) to address these limitations enhance movements above-knee amputations. involved an experiment nine healthy male participants, consisting two sessions: real execution imagined using imagery. OpenBCI Cyton board collected EMG signals corresponding desired movements, while fNIRS monitored brain activity prefrontal cortices. analysis simultaneous measurement muscular hemodynamic responses demonstrated combining data sources significantly improved classification accuracy compared each dataset alone. results showed both consistently achieved higher accuracy. More specifically, Support Vector Machine performed best during tasks, average 49.61%, Linear Discriminant Analysis excelled achieving 89.67%. research validates feasibility approach enable through imagery, representing significant advancement potential

Language: Английский

Citations

0
Noninvasive brain-computer interfaces for children with neurodevelopmental disorders: Attention deficit hyperactivity disorder and autism spectrum disorder DOI Creative Commons
Tongtong Zhang, Xiangyue Zhou, Xin Li

et al.

Displays, Journal Year: 2024, Volume and Issue: unknown, P. 102886 - 102886

Published: Nov. 1, 2024

Language: Английский

Citations

0
3D convolutional neural network based on spatial-spectral feature pictures learning for decoding motor imagery EEG signal DOI Creative Commons
Xiaoguang Li, Yaqi Chu, Xuejian Wu

et al.

Frontiers in Neurorobotics, Journal Year: 2024, Volume and Issue: 18

Published: Dec. 10, 2024

Non-invasive brain-computer interfaces (BCI) hold great promise in the field of neurorehabilitation. They are easy to use and do not require surgery, particularly area motor imagery electroencephalography (EEG). However, EEG signals often have a low signal-to-noise ratio limited spatial temporal resolution. Traditional deep neural networks typically only focus on features EEG, resulting relatively decoding accuracy rates for tasks. To address these challenges, this paper proposes 3D Convolutional Neural Network (P-3DCNN) method that jointly learns spatial-frequency feature maps from frequency domains signals. First, Welch is used calculate band power spectrum 2D matrix representing topology distribution electrodes constructed. These representations then generated through cubic interpolation data. Next, designs 3DCNN network with 1D convolutional layers series optimize kernel parameters effectively learn EEG. Batch normalization dropout also applied improve training speed classification performance network. Finally, experiments, proposed compared various classic machine learning techniques. The results show an average rate 86.69%, surpassing other advanced networks. This demonstrates effectiveness our approach offers valuable insights development BCI.

Language: Английский

Citations

0