A5101907160- EEG and Brain-Computer Interfaces
- Functional Brain Connectivity Studies
- Neural dynamics and brain function
- Blind Source Separation Techniques
- Neuroscience and Neural Engineering
- Neural and Behavioral Psychology Studies
- Emotion and Mood Recognition
- Advanced Memory and Neural Computing
- Gaze Tracking and Assistive Technology
- Anomaly Detection Techniques and Applications
- Human Pose and Action Recognition
- Fault Detection and Control Systems
- Heart Rate Variability and Autonomic Control
- Video Surveillance and Tracking Methods
- Sparse and Compressive Sensing Techniques
- Advanced Malware Detection Techniques
- Advanced Neural Network Applications
- Data Management and Algorithms
- Robotics and Sensor-Based Localization
- Multimodal Machine Learning Applications
- Gait Recognition and Analysis
- Software Engineering Research
- Network Security and Intrusion Detection
- Software Testing and Debugging Techniques
- Decision-Making and Behavioral Economics
Chongqing University of Posts and Telecommunications
2018-2025
North China University of Technology
2024
Beijing University of Posts and Telecommunications
2024
Jinan University
2023
Anhui Polytechnic University
2020-2023
Beihang University
2023
University of Electronic Science and Technology of China
2013-2022
Tianjin Normal University
2022
Tsinghua University
2018-2022
Taiyuan University of Technology
2020
In this paper, we propose a deep progressive reinforcement learning (DPRL) method for action recognition in skeleton-based videos, which aims to distil the most informative frames and discard ambiguous sequences recognizing actions. Since choices of selecting representative are multitudinous each video, model frame selection as process through learning, during progressively adjust chosen by taking two important factors into account: (1) quality selected (2) relationship between whole video....
Objective: Spectral power analysis plays a predominant role in electroencephalogram-based emotional recognition. It can reflect activity differences among multiple brain regions. In addition to activation difference, different emotions also involve large-scale network during related information processing. this paper, both propagation patterns and difference the were fused improve performance of Methods: We constructed emotion-related networks with phase locking value adopted feature fusion...
Motor imagery-based brain-computer interface (MI-BCI) systems hold promise in motor function rehabilitation and assistance for impaired people. But the ability to operate an MI-BCI varies across subjects, which becomes a substantial problem practical BCI applications beyond laboratory.Several previous studies have demonstrated that individual performance is related resting state of brain. In this study, we further investigate offline variations through perspective resting-state...
Objective. Movement control is an important application for EEG-BCI (EEG-based brain–computer interface) systems. A single-modality BCI cannot provide efficient and natural strategy, but a hybrid system that combines two or more different tasks can effectively overcome the drawbacks encountered in control. Approach. In current paper, we developed new by combining MI (motor imagery) mVEP (motion-onset visual evoked potential), aiming to realize 2D movement of cursor. Main result. The offline...
P300 is an important event-related potential that can be elicited by external visual, auditory, and somatosensory stimuli. Various cognition-related brain functions (i.e., attention, intelligence, working memory) multiple regions prefrontal, frontal, parietal) are reported to involved in the elicitation of P300. However, these studies do not investigate instant interactions across neural cortices from hierarchy milliseconds. Importantly, time-varying network analysis among uncover detailed...
Discriminating psychogenic nonepileptic seizures (PNES) from epilepsy is challenging, and a reliable automatic classification remains elusive. In this study, we develop an approach for discriminating between PNES using the common spatial pattern extracted brain network topology (SPN). The study reveals that 92% accuracy, 100% sensitivity, 80% specificity were reached focal epilepsy. newly developed SPN of resting EEG may be promising tool to mine implicit information can used differentiate
A new method for steady-state visual evoked potentials (SSVEPs) frequency recognition is proposed to enhance the performance of SSVEP-based brain-computer interface (BCI). Correlated component analysis (CORCA) introduced, which originally was designed find linear combinations electrodes that are consistent across subjects and maximally correlated between them. We propose a CORCA algorithm learn spatial filters with multiple blocks individual training data BCI scenario. The used remove...
Multichannel electroencephalogram (EEG) is an array signal that represents brain neural networks and can be applied to characterize information propagation patterns for different emotional states. To reveal these inherent spatial graph features increase the stability of emotion recognition, we propose effective recognition model performs multicategory with multiple emotion-related network topology (MESNPs) by learning discriminative topologies in EEG networks. evaluate performance our...
Linear discriminant analysis (LDA) is one of the most popular classification algorithms for brain-computer interfaces (BCI). LDA assumes Gaussian distribution data, with equal covariance matrices concerned classes, however, assumption not usually held in actual BCI applications, where heteroscedastic class distributions are observed. This paper proposes an enhanced version LDA, namely z-score linear (Z-LDA), which introduces a new decision boundary definition strategy to handle...
Abstract This study used large-scale time-varying network analysis to reveal the diverse patterns during different decision stages and found that responses of rejection acceptance involved structures. When participants accept unfair offers, brain recruits a more bottom-up mechanism with much stronger information flow from visual cortex (O2) frontal area, but when they reject it displayed top-down derived (Fz) parietal occipital cortices. Furthermore, we performed 2 additional studies...
Decision-making plays an essential role in the interpersonal interactions and cognitive processing of individuals. There has been increasing interest being able to predict individual's decision-making response (i.e., acceptance or rejection). We proposed electroencephalogram (EEG)-based computational intelligence framework individual responses. Specifically, discriminative spatial network pattern (DSNP), a supervised learning approach, was applied single-trial EEG data extract DSNP feature...
The accurate identification of an attention deficit hyperactivity disorder (ADHD) subject has remained a challenge for both neuroscience research and clinical diagnosis. Unfortunately, the traditional methods concerning classification model feature extraction usually depend on single-channel static measurements (i.e., functional connectivity, FC) in small, homogenous single-site dataset, which is limited may cause loss intrinsic information MRI (fMRI). In this study, we proposed new...
The "lifting from 2D pose" method has been the dominant approach to 3D Human Pose Estimation (3DHPE) due powerful visual analysis ability of pose estimators. Widely known, there exists a depth ambiguity problem when estimating solely pose, where one can be mapped multiple poses. Intuitively, rich semantic and texture information in images contribute more accurate "lifting" procedure. Yet, existing research encounters two primary challenges. Firstly, distribution image data motion capture...
Benefiting from the high-temporal resolution of electroencephalogram (EEG), EEG-based emotion recognition has become one hotspots affective computing. For systems, it is crucial to utilize state-of-the-art learning strategies automatically learn emotion-related brain cognitive patterns emotional EEG signals, and learned stable effectively ensure robustness system. In this work, realize efficient decoding EEG, we propose a graph system Graph Convolutional Network framework with Brain network...
Ensemble Empirical Mode Decomposition (EEMD) has been popularised for single-channel Electromyography (EMG) signal processing as it can effectively extract the temporal information of EMG time series. However, few papers examine and spatial characteristics across multiple muscle groups in relation to multichannel signals. The experimental data was obtained from Center Machine Learning Intelligent Systems, University California Irvine (UCI). donated by Nueva Granada Military Technopark node...
In this paper, we propose a Semantics-Preserving Teacher-Student (SPTS) model for group activity recognition in videos, which aims to mine the semantics-preserving attention automatically seek key people and discard misleading people. Conventional methods usually aggregate features extracted from individual persons by pooling operations, cannot fully explore contextual information recognition. To address this, our SPTS networks first learn Teacher Network semantic domain, classifies word of...
EEG inverse problem is underdetermined, which poses a long standing challenge in Neuroimaging. The combination of source-imaging and analysis cortical directional networks enables us to noninvasively explore the underlying neural processes. However, existing source imaging approaches mainly focus on performing direct operation for estimation, will be inevitably influenced by noise strategy used find solution. Here, we develop new technique, Deep Brain Neural Network (DeepBraiNNet), robust...
As a kind of biological network, the brain network conduces to understanding mystery high-efficiency information processing in brain, which will provide instructions develop efficient brain-like neural networks. Large-scale dynamical functional connectivity (dFNC) provides more context-sensitive, dynamical, and straightforward sight at higher level. Nevertheless, dFNC analysis needs good enough resolution both temporal spatial domains, construction capture time-varying correlations between...