A5079457723- Functional Brain Connectivity Studies
- EEG and Brain-Computer Interfaces
- Advanced Neuroimaging Techniques and Applications
- Face and Expression Recognition
- Neural dynamics and brain function
- Stock Market Forecasting Methods
- Advanced MRI Techniques and Applications
- Video Surveillance and Tracking Methods
- Mental Health Research Topics
- Advanced Algorithms and Applications
- Remote Sensing and Land Use
- Sparse and Compressive Sensing Techniques
- Remote-Sensing Image Classification
- Image Processing Techniques and Applications
- Autism Spectrum Disorder Research
- Data Management and Algorithms
- Advanced Text Analysis Techniques
- Anomaly Detection Techniques and Applications
- Advanced Computational Techniques and Applications
- Transportation Planning and Optimization
- Energy Load and Power Forecasting
- Maternal Mental Health During Pregnancy and Postpartum
- Advanced Memory and Neural Computing
- Advanced Measurement and Detection Methods
- Radiomics and Machine Learning in Medical Imaging
Shandong Institute of Business and Technology
2016-2025
Newcastle University
2025
Xinjiang Institute of Engineering
2024
University of Science and Technology of China
2022-2024
Nanjing Tech University
2024
Yantai University
2024
Changchun University of Science and Technology
2024
Southwestern Institute of Physics
2022
Beihang University
2022
Xihua University
2022
Vehicle trajectory prediction is a keystone for the application of internet vehicles (IoV). With help deep learning and big data, it possible to understand between-vehicle interaction pattern hidden in complex traffic environment. In this paper, we propose novel spatial-temporal dynamic attention network vehicle prediction, which can comprehensively capture temporal social patterns hierarchical manner. The relation between captured at each timestamp thus retains variation interaction....
Graphs are widely used in large scale social network analysis nowadays. Not only analysts need to focus on cohesive subgraphs study patterns among actors, but also normal users interested discovering what happening their neighborhood. However, effectively storing and efficiently identifying is challenging. In this work we introduce a novel subgraph concept capture the cohesion interactions, propose an I/O efficient approach discover subgraphs. Besides, analytic system which allows perform...
Functional brain networks derived from resting-state functional magnetic resonance imaging (rs-fMRI) have been widely used for Autism Spectrum Disorder (ASD) diagnosis. Typically, these are constructed by calculating connectivity (FC) between any pair of regions interest (ROIs), i.e., using Pearson's correlation rs-fMRI time series. However, this can only be called as a low-order representation the interaction, because relationship is investigated just two ROIs. Brain disorders might not...
As a core function of autonomous driving and the internet vehicles, accurately predicting trajectory vehicles can significantly improve traffic safety reduce crash injuries. In this paper, we propose an intention-aware non-autoregressive Transformer model with multi-attention learning for multi-modal vehicle prediction. We first present social attention where graph is properly integrated encoder so as to interaction between vehicles. Then, temporal dependency across consecutive frames...
Abstract Autism spectrum disorder (ASD) is a neurodevelopment disease characterized by impairment of social interaction, language, behavior, and cognitive functions. Up to now, many imaging‐based methods for ASD diagnosis have been developed. For example, one may extract abundant features from multi‐modality images then derive discriminant function map the selected toward label. A lot recent works, however, are limited single imaging centers. To this end, we propose novel multi‐center...
An optimised XGBoost model based on genetic algorithm to search for optimal parameter combinations is proposed in this paper. It was proved that the improved has better classification effect than existing approaches through liver disease data set Liver Disorders Data Set UCI Machine Learning Repository. In recent years, there have been many excellent intelligent algorithms field of machine learning and one them. However, when using algorithm, it usually involves adjustment various parameters...
The sliding-window-based dynamic functional connectivity networks (D-FCNs) derived from resting-state magnetic resonance imaging (rs-fMRI) are effective methods for diagnosing various neurological diseases, including autism spectrum disorder (ASD). However, traditional D-FCNs low-order based on pairwise correlation between brain regions, thus overlooking high-level interactions across multiple ROIs. Moreover, suffer the temporal mismatching issue, i.e., sub-networks in same window do not...
Differential phase-contrast computed tomography (DPC-CT) is a powerful analysis tool for soft-tissue and low-atomic-number samples. Limited by the implementation conditions, DPC-CT with incomplete projections happens quite often. Conventional reconstruction algorithms face difficulty when given data. They usually involve complicated parameter selection operations, which are also sensitive to noise time-consuming. In this paper, we report new deep learning framework data DPC-CT. It involves...
Previous studies have found qualitative structural and functional brain changes in major depressive disorder (MDD) patients. However, most ignored the complementarity of multisequence MRI neuroimaging features cannot determine accurate biomarkers.To evaluate machine-learning models combined with to diagnose patients MDD.Prospective.A training cohort including 111 90 healthy controls (HCs) a test 28 22 HCs.A 3.0 T/T1-weighted imaging, resting-state echo-planar sequence, single-shot diffusion...
Vehicle re-identification (Re-ID) that aims at matching vehicles across multiple non-overlapping cameras is prevalently recognized as an important application of computer vision in intelligent transportation. One the major challenges to extract discriminative features are resistant viewpoint variations. To address this problem, paper proposes a novel vehicle Re-ID model from perspectives effective feature fusion and adaptive part attention. Firstly, we put forward channel attention-based...
Graph convolutional networks (GCNs), with their powerful ability to model non-Euclidean graph data, have shown advantages in learning representations of brain networks. However, considering the complexity, multilayeredness, and spatio-temporal dynamics activities, we identified two limitations current GCN-based research on networks: 1) Most studies focused unidirectional information transmission across network levels, neglecting joint or bidirectional exchange among 2) existing models...
Abstract Major depressive disorder (MDD) is a clinically heterogeneous disorder. Its mechanism still unknown. Although the altered intersubject variability in functional connectivity (IVFC) within gray‐matter has been reported MDD, alterations to IVFC white‐matter (WM‐IVFC) remain Based on resting‐state MRI data of discovery (145 MDD patients and 119 healthy controls [HCs]) validation cohorts (54 patients, 78 HCs), we compared WM‐IVFC between two groups. We further assessed meta‐analytic...
Functional connectivity (FC) network based on resting-state functional magnetic resonance imaging (rs-fMRI) has become an important tool to explore and understand the brain, which can provide objective basis for diagnosis of neurodegenerative diseases, such as autism spectrum disorder (ASD). However, most networks only consider unilateral features nodes or edges, interaction between them is ignored. In fact, their integration more comprehensive crucial information in diagnosis. To address...
Accurate detection and classification of breast lesions in early stage is crucial to timely formulate effective treatments for patients. We aim develop a fully automatic system detect classify using multiple contrast-enhanced mammography (CEM) images.In this study, total 1,903 females who underwent CEM examination from three hospitals were enrolled as the training set, internal testing pooled external set prospective set. Here we developed CEM-based multiprocess (MDCS) perform task lesions....
Background Traditional neuroimaging studies have primarily emphasized analysis at the group level, often neglecting specificity individual level. Recently, there has been a growing interest in differences brain connectivity. Investigating individual‐specific connectivity is important for understanding mechanisms of major depressive disorder (MDD) and variations among individuals. Purpose To integrate individualized functional structural with machine learning techniques to distinguish people...
Brain functional connectivity network (FCN) based on resting-state magnetic resonance imaging (rs-fMRI) has been widely used to identify neuropsychiatric disorders such as autism spectrum disorder (ASD). Most existing FCN-based methods only estimate the correlation between brain regions of interest (ROIs), without exploring more informative higher-level interactions among multiple ROIs which could be beneficial disease diagnosis. To fully explore discriminative information provided by...
Accurate diagnosis of breast lesions and discrimination axillary lymph node (ALN) metastases largely depend on radiologist experience. To develop a deep learning-based whole-process system (DLWPS) for segmentation ALN metastasis. Retrospective. 1760 patients, who were divided into training validation sets (1110 patients), internal (476 external (174 patients) test sets. 3.0T/dynamic contrast-enhanced (DCE)-MRI sequence. DLWPS was developed using classification models. The DLWPS-based model...