A5100404178- Functional Brain Connectivity Studies
- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Advanced Neuroimaging Techniques and Applications
- Face and Expression Recognition
- Advanced MRI Techniques and Applications
- Dementia and Cognitive Impairment Research
- Brain Tumor Detection and Classification
- Alzheimer's disease research and treatments
- Advanced Algorithms and Applications
- Gaze Tracking and Assistive Technology
- Aeolian processes and effects
- Advanced Memory and Neural Computing
- Neonatal and fetal brain pathology
- Soil erosion and sediment transport
- Neural Networks and Applications
- Image Processing Techniques and Applications
- Mental Health Research Topics
- Blind Source Separation Techniques
- Image Retrieval and Classification Techniques
- Mind wandering and attention
- Domain Adaptation and Few-Shot Learning
- Prenatal Substance Exposure Effects
- Geology and Paleoclimatology Research
- Calibration and Measurement Techniques
Beijing Institute of Technology
2024-2025
Shenyang University of Chemical Technology
2025
Beijing Normal University
2015-2024
China Rehabilitation Research Center
2024
Capital Medical University
2024
Chinese Institute for Brain Research
2024
State Key Laboratory of Cognitive Neuroscience and Learning
2023
Siemens (China)
2022-2023
Chengdu University of Information Technology
2022
Hebei Academy of Sciences
2022
Recently, electroencephalogram (EEG) based on motor imagery (MI) have gained significant traction in brain-computer interface (BCI) technology, particularly for the rehabilitation of paralyzed patients. But low signal-to-noise ratio MI EEG makes it difficult to decode effectively and hinders development BCI. In this paper, a method attention-based multiscale EEGNet (AMEEGNet) was proposed improve decoding performance MI-EEG. First, three parallel EEGNets with fusion transmission were...
The triple network model, consisting of the central executive (CEN), salience (SN) and default mode (DMN), has been recently employed to understand dysfunction in core networks across various disorders. Here we used model investigate large-scale brain cognitively normal apolipoprotein e4 (APOE4) carriers who are at risk Alzheimer's disease (AD). To explore functional connectivity for each three effective among them, evaluated 17 individuals with a family history AD least one copy APOE4...
A common drawback of EEG-based emotion recognition is that volume conduction effects the human head introduce interchannel dependence and result in highly correlated information among most EEG features. These features cannot provide extra useful information, they actually reduce performance recognition. However, existing feature selection methods, commonly used to remove redundant for recognition, ignore correlation between or utilize a greedy strategy evaluate interdependence, which leads...
Objective: Previous reports have demonstrated significant brain activity changes in bilateral blindness, whereas late monocular blindness (MB) at rest are not well studied. Our study aimed to investigate spontaneous patients with middle-aged MB using the amplitude of low-frequency fluctuation (ALFF) method and their relationship clinical features. Methods: A total 32 (25 males 7 females) healthy control (HC) subjects females), similar age, sex, education, were recruited for study. All...
Accurate classification of either patients with Alzheimer's disease (AD) or mild cognitive impairment (MCI), the prodromal stage AD, from cognitively unimpaired (CU) individuals is important for clinical diagnosis and adequate intervention. The current study focused on distinguishing AD MCI CU based multi-feature kernel supervised within-Class-similar discriminative dictionary learning algorithm (MKSCDDL), which we introduced in a previous study, demonstrating that MKSCDDL had superior...
Impulsiveness is a stable personal characteristic that contributes to obesity and may interact with it. Specifically, caused by unrestrained impulse eating not consciously controlled leads hormonal imbalance also can impair control. However, the mechanism of this relationship unclear. In our study, 35 obese individuals (body mass index, BMI > 28) were recruited matched 31 healthy controls (BMI < 24) in age education level. All participants underwent resting-state fMRI completed Barratt...
Autism spectrum disorder (ASD) is a pervasive neurodevelopmental characterized by restricted interests and repetitive behaviors. Non-invasive measurements of brain activity with functional magnetic resonance imaging (fMRI) have demonstrated that the abnormality in default mode network (DMN) crucial neural basis ASD, but time-frequency feature DMN has not yet been revealed. Hilbert-Huang transform (HHT) conducive to extraction biomedical signals recently suggested as an effective way explore...
Using deep neural networks (DNNs) to explore spatial patterns and temporal dynamics of human brain activities has been an important yet challenging problem because the artificial are hard be designed manually. There have several promising learning methods, e.g., belief network (DBN), convolutional (CNN), sparse recurrent auto-encoder (DSRAE), that can decompose neuroscientific meaningful spatiotemporal from 4D functional Magnetic Resonance Imaging (fMRI) data. However, those previous studies...
Psychiatric disorders are a pressing public health challenge, posing significant threat to the well-being of millions people worldwide. Their elusive etiology, rooted in complex interplay genetic, environmental, and neural factors, requires innovative research approaches. The advent advanced neuroimaging techniques connectomics marks transformative era, enabling researchers delve into structural functional networks human brain. This transformation is underscored by establishment large brain...
The Gobi deserts are important landscapes and major sandstorm source areas in arid northwestern China. Unsaturated sand flow decreasing supply capacity is well known as the basic characteristics of gobi surface, but relatively little attention has been paid to fetch effect transport which closely related indicative wind erosion process gobi. Using a field experiment, we investigated spatial temporal variations on manually disturbed surface downwind sand-blocking belt sand-fixing by measuring...
Recent studies showed that convolutional neural network (CNN) models possess remarkable capability of differentiating and characterizing fMRI signals from cortical gyri sulci. In addition, visualization analysis the filters in learned CNN suggest sulcal are more diverse have higher frequency than gyral signals. However, it is not clear whether can be further divided into sub-populations, e.g., 3-hinge areas vs 2-hinge areas. It also unclear two classes (gyral sulcal) classification optimized...