CLTNet: A Hybrid Deep Learning Model for Motor Imagery Classification

Brain Sciences, Год журнала: 2025, Номер 15(2), С. 124 - 124

Опубликована: Янв. 27, 2025

Background: Brain–computer interface (BCI) technology opens up new avenues for human–machine interaction and rehabilitation by connecting the brain to machines. Electroencephalography (EEG)-based motor imagery (MI) classification is a key component of BCI technology, which capable translating neural activity in into commands controlling external devices. Despite great potential challenges extracting decoding signals limit its wide application. Methods: To address this challenge, study proposes novel hybrid deep learning model, CLTNet, focuses on solving feature extraction problem improve MI-EEG signals. In preliminary stage, CLTNet uses convolutional network (CNN) extract time series, channel, spatial features EEG obtain important local information. model combines long short-term memory (LSTM) Transformer module capture time-series data global dependencies EEG. The LSTM explains dynamics activity, while Transformer’s self-attention mechanism reveals series. Ultimately, classifies through fully connected layer. Results: achieved an average accuracy 83.02% Kappa value 0.77 IV 2a dataset, 87.11% 0.74 2b both outperformed traditional methods. Conclusions: innovation that it integrates multiple architectures, offers more comprehensive understanding characteristics during imagery, providing perspective establishing benchmark future research area.

Язык: Английский

---

Efficient motor imagery electroencephalogram classification via cross tensor coupling decomposition based on augmented covariance networks.

Neurocomputing, Год журнала: 2025, Номер unknown, С. 129911 - 129911

Опубликована: Март 1, 2025

Язык: Английский

---

Exoskeleton Robot Based on Brain-Computer Interface

Applied and Computational Engineering, Год журнала: 2024, Номер 111(1), С. 66 - 71

Опубликована: Ноя. 29, 2024

Brain-computer interface (BCI) technology represents a means of facilitating human-computer interaction. One the most widely accepted paradigms brain-computer is motor imagery, which enables recognition electroencephalogram (EEG) signals generated in specific brain region by imagining movement limb. Following acquisition, preprocessing, feature processing, and signal classification EEG signals, complex are accurately recognized. Therefore, creating control system that translates recognized into commands for robot transmits them to robot, it possible robot's movements imagery. The convolutional neural network popular processing algorithm due its high accuracy, excellent performance extraction, superior end-to-end learning. an optimal method control. This makes CNN choice control, enhancing both effectiveness user experience BCI systems enabling more intuitive responsive interactions with robotic devices.

Язык: Английский

---

MCMTNet: Advanced network architectures for EEG-based motor imagery classification

Neurocomputing, Год журнала: 2024, Номер unknown, С. 129255 - 129255

Опубликована: Дек. 1, 2024

Язык: Английский

---