A5035038002- Domain Adaptation and Few-Shot Learning
- Dementia and Cognitive Impairment Research
- Innovative Teaching and Learning Methods
- Brain Tumor Detection and Classification
- Online and Blended Learning
- Artificial Intelligence in Healthcare
- Online Learning and Analytics
- Knowledge Management and Sharing
- Simulation and Modeling Applications
- Neonatal and fetal brain pathology
- Team Dynamics and Performance
- Emotion and Mood Recognition
- Machine Learning in Bioinformatics
- Text and Document Classification Technologies
- Oral microbiology and periodontitis research
- Gaze Tracking and Assistive Technology
- Technology Adoption and User Behaviour
- Color perception and design
- EEG and Brain-Computer Interfaces
- Machine Learning in Healthcare
- Industrial Technology and Control Systems
- Image Retrieval and Classification Techniques
- Face and Expression Recognition
- Speech Recognition and Synthesis
- Advanced Computational Techniques and Applications
Chongqing Three Gorges University
2008-2021
Beijing University of Posts and Telecommunications
2020
University of Hong Kong
2011-2017
Nanjing University of Aeronautics and Astronautics
2011-2015
University of North Carolina at Chapel Hill
2013-2015
Beijing University of Technology
2012-2013
Imaging Center
2013
Beijing University of Civil Engineering and Architecture
2011
University of Michigan
2011
Shanghai Liangyou (China)
2011
Machine learning methods have successfully been used to predict the conversion of mild cognitive impairment (MCI) Alzheimer's disease (AD), by classifying MCI converters (MCI-C) from nonconverters (MCI-NC). However, most existing construct classifiers using data one particular target domain (e.g., MCI), and ignore in other related domains AD normal control (NC)) that may provide valuable information improve prediction performance. To address is limitation, we develop a novel transfer method...
Abstract Multimodality based methods have shown great advantages in classification of Alzheimer's disease (AD) and its prodromal stage, that is, mild cognitive impairment (MCI). Recently, multitask feature selection are typically used for joint common features across multiple modalities. However, one disadvantage existing multimodality is they ignore the useful data distribution information each modality, which essential subsequent classification. Accordingly, this paper we propose a...
Software development managers could improve the quality of software products through controlling time and budget in process by using effort estimation. But until now, there have not effective methods estimating for agile development. In this paper, author extracts data from thousands projects provided ISBSG DATA Release 11, analyze method principal component analysis. Finally, paper gets out set factor affecting
E-learning is increasingly playing an important role in human resource development, attracting increasing attention from both researchers and practitioners. Various topics on e-learning for workforce development have emerged, showing the dynamics of knowledge this field. This study aims to determine core concepts research themes domain enabled development. Academic industrial journals, magazines, conference proceedings field were selected as dataset. A set methods including co-occurrence...
Graph convolutional networks (GCN) have been applied in knowledge base question answering (KBQA) task. However, the pairwise connection between nodes of GCN limits representation capability high-order data correlation. Furthermore, most previous work does not fully utilize semantic relation information, which is vital to reasoning. In this paper, we propose a novel multi-hop KBQA model based on hypergraph network. By constructing hypergraph, form and converted high-level edges, effectively...