Automatic channel selection using multi-objective prioritized jellyfish search (MPJS) algorithm for motor imagery classification using modified DB-EEGNET

Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 23, 2025

Language: Английский

---

EEG-based motor imagery recognition via novel explainable ensemble learning architecture

Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: May 17, 2025

Language: Английский

---

A novel feature extraction method PSS-CSP for binary motor imagery – based brain-computer interfaces

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 177, P. 108619 - 108619

Published: May 20, 2024

Language: Английский

---

Large-scale cortical network analysis and classification of MI-BCI tasks based on Bayesian nonnegative matrix factorization

IEEE Transactions on Neural Systems and Rehabilitation Engineering, Journal Year: 2024, Volume and Issue: 32, P. 2187 - 2197

Published: Jan. 1, 2024

Motor imagery (MI) is a high-level cognitive process that has been widely applied to clinical rehabilitation and brain-computer interfaces (BCIs). However, the decoding of MI tasks still faces challenges, neural mechanisms underlying its application are unclear, which seriously hinders development MI-based applications BCIs. Here, we combined EEG source reconstruction Bayesian nonnegative matrix factorization (NMF) methods construct large-scale cortical networks left-hand right-hand tasks. Compared MI, results showed significantly increased functional network connectivities (FNCs) mainly located among visual (VN), sensorimotor (SMN), right temporal network, central executive parietal in at β (13-30Hz) all (8-30Hz) frequency bands. For properties analysis, found clustering coefficient, global efficiency, local efficiency were characteristic path length was decreased compared These pattern differences indicated may need more modulation multiple (i.e., VN SMN) hemisphere. Finally, based on spatial FNC properties, propose classification model. The proposed model achieves top accuracy 78.2% cross-subject two-class MI-BCI Overall, our findings provide new insights into potential biomarker identify

Language: Английский

---

Enhancing motor imagery decoding in brain–computer interfaces using Riemann tangent space mapping and cross frequency coupling

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 99, P. 106797 - 106797

Published: Sept. 11, 2024

Language: Английский

---

Assessing the influence of latency variability on EEG classifiers - a case study of face repetition priming

Cognitive Neurodynamics, Journal Year: 2024, Volume and Issue: 18(6), P. 4055 - 4069

Published: Oct. 21, 2024

Abstract Data-driven strategies have been widely used to distinguish experimental effects on single-trial EEG signals. However, how latency variability, such as within-condition jitter or shifts between conditions, affects the performance of classifiers has not well investigated. Without explicitly considering and disentangling attributes single trials, neural network-based limitations in measuring their contributions. Inspired by domain knowledge subcomponent amplitude from traditional cognitive neuroscience, this study applies a stepwise correction method trials control for contributions classifier behavior. As case demonstrating value method, we measure repetition priming faces, which induce large reaction time differences, shifts, averaged event-related potentials. The results show that negatively impacts performance, but between-condition improve accuracy, whereas genuine differences no significant influence. While demonstrated effects, methodology can be generalized experiments involving many kinds time-varying signals account variability performance.

Language: Английский

---

Boosted Harris Hawks Shuffled Shepherd Optimization Augmented Deep Learning based motor imagery classification for brain computer interface

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(11), P. e0313261 - e0313261

Published: Nov. 21, 2024

Motor imagery (MI) classification has been commonly employed in making brain-computer interfaces (BCI) to manage the outside tools as a substitute neural muscular path. Effectual MI BCI improves communication and mobility for people with breakdown or motor damage, delivering bridge between brain’s intentions exterior actions. Employing electroencephalography (EEG) aggressive recordings, machine learning (ML) methods are used interpret patterns of brain action linked image tasks. These models frequently depend upon like support vector (SVM) deep (DL) distinguish among dissimilar classes, such visualizing left right limb This procedure allows individuals, particularly those disabilities, utilize their opinions command devices robotic limbs computer borders. article presents Boosted Harris Hawks Shuffled Shepherd Optimization Augmented Deep Learning (BHHSHO-DL) technique based on Imagery Classification BCI. The BHHSHO-DL mainly exploits hyperparameter-tuned DL approach identification Initially, performs data preprocessing utilizing wavelet packet decomposition (WPD) model. Besides, enhanced densely connected networks (DenseNet) model extracts preprocessed data’s complex hierarchical feature patterns. Meanwhile, BHHSHO technique-based hyperparameter tuning process is accomplished elect optimal parameter values DenseNet Finally, implemented by convolutional autoencoder (CAE) simulation value methodology performed benchmark dataset. performance validation portrayed superior accuracy 98.15% 92.23% over other techniques under BCIC-III BCIC-IV datasets.

Language: Английский

---

MBCNN-EATCFNet: A multi-branch neural network with efficient attention mechanism for decoding EEG-based motor imagery

Robotics and Autonomous Systems, Journal Year: 2024, Volume and Issue: unknown, P. 104899 - 104899

Published: Dec. 1, 2024

Language: Английский

---

Convolutional Neural Network in Brain-computer Interfaces-exoskeleton System

Highlights in Science Engineering and Technology, Journal Year: 2024, Volume and Issue: 120, P. 251 - 257

Published: Dec. 25, 2024

Brain-computer interfaces (BCIs) have emerged as a groundbreaking technology that has the potential to revolutionize field of stroke rehabilitation. These innovative systems allow individuals who suffered from strokes regain lost motor function by directly connecting their brains with external devices, such exoskeletons. One most commonly used paradigms in BCIs is imagery (MI), which involves generating electroencephalograms (EEGs) through imagined movements. This means patients can perform tasks simply help exoskeletons only thinking about them, without any physical movement required. The ability decode these EEG signals crucial for enabling effective communication between brain and devices. Deep learning (DL), particularly convolutional neural networks (CNNs) are able extract meaningful features raw data accurately classify different types movements, proven be highly decoding generated during already made numerous contributions this area. article provides an initial overview CNNs, followed explanation how CNNs derived imagery, well utilization controlling exoskeleton Finally, current limitations future directions discussed.

Language: Английский

---

Attention Induced Dual Convolutional-Capsule Network (AIDC-CN): A deep learning framework for motor imagery classification

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 183, P. 109260 - 109260

Published: Oct. 18, 2024

Language: Английский

---