- Sentiment Analysis and Opinion Mining
- Web Data Mining and Analysis
- Data Management and Algorithms
- Hate Speech and Cyberbullying Detection
- Advanced Database Systems and Queries
- Speech Recognition and Synthesis
- Collaboration in agile enterprises
- Neural dynamics and brain function
- Machine Learning and Data Classification
- Educational Technology and Pedagogy
- Advanced Sensor and Control Systems
- Recommender Systems and Techniques
- AI in cancer detection
- Medical Imaging and Analysis
- Bullying, Victimization, and Aggression
- Green IT and Sustainability
- Gas Sensing Nanomaterials and Sensors
- Multi-Agent Systems and Negotiation
- Explainable Artificial Intelligence (XAI)
- Digital Marketing and Social Media
- Advanced Text Analysis Techniques
- Speech and Audio Processing
- Distributed and Parallel Computing Systems
- Advanced Computational Techniques and Applications
- Service-Oriented Architecture and Web Services
Shandong Institute of Automation
2022-2023
Chinese Academy of Sciences
2021-2023
Beijing Academy of Artificial Intelligence
2022-2023
University of Chinese Academy of Sciences
2022-2023
Suzhou Institute of Nano-tech and Nano-bionics
2021
East China University of Science and Technology
2018
East China University of Technology
2018
Central China Normal University
2017
Wuhan University
2008-2012
Tianjin Agricultural University
2009
Under the background of leap-forward development for internet, e-commerce has played an important role in people's daily life, but huge data sizes have also brought problems, such as information overload which can be solved by using a recommendation system effectively. However, with e-commerce, amount product catalogs and users becomes larger, causes lower performance traditional system. This article comes up personalized algorithm based on mining reviews to optimize new Features were...
The rapid spread of the pandemic coronavirus disease 2019 (COVID-19) has created an unprecedented, global health disaster. During outburst period, paucity knowledge and research aggravated devastating panic fears that lead to social stigma serious obstacles contain disastrous epidemic. We propose a deep learning-based method detect stigmatized contents on online network (OSN) platforms in early stage COVID-19. Our performs semantic-based quantitative analysis unveil essential...
One of challenges in GIS Web service is mass data storage and processing. This paper proposes a distributed cached solution, as the mixture Mongo DB Memcached cache, for service. solution tends to solve three obstacles: mismatch between frequent requirement concurrent tasks accessing poor performance conventional mechanism such relational databases, insufficiency databases manage complex types service, horizontal scalability non-stop evolution. A concise case indicates feasibility solution.
In this paper, we would like to quantify factors that contribute the cacheability decision of web objects. Our study is based on a comprehensive object attributes are related HTTP protocol transfer, proxy preference, content availability, freshness revalidation as well inter-relationship and dependency among them. Furthermore, relative importance these towards final objects also investigated. This important because it provides hints how optimize caching performance.
Super-resolution (SR) aims to enhance the quality of low-resolution images and has been widely applied in medical imaging. We found that design principles most existing methods are influenced by SR tasks based on real-world do not take into account significance multi-level structure pathological images, even if they can achieve respectable objective metric evaluations. In this work, we delve two super-resolution working paradigms propose a novel network called CWT-Net, which leverages...
Latent confounders are a fundamental challenge for inferring causal effects from observational data. The instrumental variable (IV) approach is practical way to address this challenge. Existing IV based estimators need known or other strong assumptions, such as the existence of two more IVs in system, which limits application approach. In paper, we consider relaxed requirement, assumes there an proxy system without knowing proxy. We propose Variational AutoEncoder (VAE) disentangled...