Publications by authors named "Chaoyi Dong"
Article Synopsis
- Traditional methods struggle with classifying short-time window steady-state visual evoked potential (SSVEP) signals in brain-computer interface (BCI) systems.
- The proposed CBAM-CNN method utilizes multi-subfrequency bands and a convolutional block attention module for better feature extraction and fusion.
- Experimental results demonstrate that CBAM-CNN achieves a peak accuracy of 0.9813 percentage points and outperforms other methods, especially in the short-time window, significantly enhancing information transmission rates.
Article Synopsis
- The paper discusses advancements in Brain-Computer Interface (BCI) technology, specifically focusing on improving accuracy in motor imagery (MI) classification using EEG signals by extracting meaningful brain network features.
- It introduces a new method combining directed transfer function (DTF) and graph theory with traditional common spatial pattern (CSP) techniques, filtering out redundant features using the Lasso method for better classification outcomes.
- The results show that the proposed method, termed CDGL, significantly outperformed traditional CSP methods with higher accuracy, sensitivity, and specificity, especially using 8 EEG electrodes in the Beta frequency band.
A Fused Multidimensional EEG Classification Method Based on an Extreme Tree Feature Selection.
Comput Intell Neurosci
August 2022
When a brain-computer interface (BCI) is designed, high classification accuracy is difficult to obtain for motor imagery (MI) electroencephalogram (EEG) signals in view of their relatively low signal-to-noise ratio. In this paper, a fused multidimensional classification method based on extreme tree feature selection (FMCM-ETFS) is proposed for discerning motor imagery EEG tasks. First, the EEG signal was filtered by a Butterworth filter for preprocessing.
View Article and Find Full Text PDFAiming at the feature extraction of left- and right-hand movement imagination EEG signals, this paper proposes a multichannel correlation analysis method and employs the Directed Transfer Function (DTF) to identify the connectivity between different channels of EEG signals, construct a brain network, and extract the characteristics of the network information flow. Since the network information flow identified by DTF can also reflect indirect connectivity of the EEG signal networks, the newly extracted DTF features are incorporated into the traditional AR model parameter features and extend the scope of feature sets. Classifications are carried out through the Support Vector Machine (SVM).
View Article and Find Full Text PDFBackground: In the study of brain-computer interfaces (BCIs) based on steady-state visual evoked potentials (SSVEPs), how to improve the classification accuracies of BCIs has always been the focus of researchers. Canonical correlation analysis (CCA) is widely used in BCI systems of SSVEPs because of its rapidity and scalability. However, the classical CCA algorithm always encounters the difficulty of low accuracy in a short time.
View Article and Find Full Text PDFArticle Synopsis
- The study focuses on mapping the functional connections in Biological Neural Networks (BNNs) to understand how their structures influence network functions.
- The researchers extended linear Granger causality approaches to nonlinear models, utilizing Radial Basis Functions to analyze neuron firing signals and identify how information flows between presynaptic and postsynaptic neurons.
- The proposed Nonlinear Granger Causality Identification Method (NGCIM) demonstrated high accuracy in identifying synaptic connections in various sized networks, outperforming traditional methods, indicating its potential for advancing brain science research.
Article Synopsis
- Feedback circuits play a key role in biological networks and are essential for understanding synchronized bursting behaviors in neural dynamics, making their identification through time-series measurements crucial.
- The Multi-Step Granger Causality Method (MSGCM) was created to effectively identify feedback loops in biological networks, overcoming limitations of previous methods by demonstrating bi-directional multi-step causality between network nodes.
- MSGCM was validated using synthetic neural models and lab-cultured rat neural networks, revealing numerous feedback loops associated with synchronized oscillations, highlighting their significance in neural network dynamics.
Background: Synchronized bursting activity (SBA) is a remarkable dynamical behavior in both ex vivo and in vivo neural networks. Investigations of the underlying structural characteristics associated with SBA are crucial to understanding the system-level regulatory mechanism of neural network behaviors.
Results: In this study, artificial pulsed neural networks were established using spike response models to capture fundamental dynamics of large scale ex vivo cortical networks.
Motivation: Synchronized bursting behavior is a remarkable phenomenon in neural dynamics. So, identification of the underlying functional structure is crucial to understand its regulatory mechanism at a system level. On the other hand, we noted that feedback loops (FBLs) are commonly used basic building blocks in engineering circuit design, especially for synchronization, and they have also been considered as important regulatory network motifs in systems biology.
View Article and Find Full Text PDFFeedback circuits are crucial dynamic motifs which occur in many biomolecular regulatory networks. They play a pivotal role in the regulation and control of many important cellular processes such as gene transcription, signal transduction, and metabolism. In this study, we develop a novel computationally efficient method to identify feedback loops embedded in intracellular networks, which uses only time-series experimental data and requires no knowledge of the network structure.
View Article and Find Full Text PDF