A5100745269- Environmental Impact and Sustainability
- Data Stream Mining Techniques
- Water-Energy-Food Nexus Studies
- Machine Learning and Data Classification
- Energy, Environment, Economic Growth
- Recycling and Waste Management Techniques
- Social Capital and Networks
- Water resources management and optimization
- Sustainable Supply Chain Management
- Migration and Labor Dynamics
- Sustainability and Ecological Systems Analysis
- Wastewater Treatment and Reuse
- Economic Development and Regional Competitiveness
- Sentiment Analysis and Opinion Mining
- Sustainable Building Design and Assessment
- Machine Learning and Algorithms
- Elite Sociology and Global Capitalism
- Text and Document Classification Technologies
- Mercury impact and mitigation studies
- Cloud Computing and Resource Management
- China's Socioeconomic Reforms and Governance
- Peer-to-Peer Network Technologies
- Migration, Ethnicity, and Economy
- Advanced Text Analysis Techniques
- Advanced Database Systems and Queries
Peking University
2018-2023
Shanxi University
2019
Ningbo Polytechnic
2013
Recently using machine learning (ML) based techniques to optimize the performance of modern database management systems (DBMSs) has attracted intensive interest from both industry and academia. With an objective tune a specific component DBMS (e.g., index selection, knobs tuning), ML-based tuning agents have shown be able find better configurations than experienced administrators (DBAs). However, one critical yet challenging question remains unexplored -- how make those work collaboratively....
A large-scale and high-quality training dataset is an important guarantee to learn ideal classifier for text sentiment classification. However, manually constructing such a with labels labor-intensive time-consuming task. Therefore, based on the idea of effectively utilizing unlabeled samples, synthetical framework that covers whole process semi-supervised learning from seed selection, iterative modification set, co-training strategy proposed in this paper To provide basis selecting texts...
Distributed data analytic engines like Spark are common choices to process massive in industry. However, the performance of SQL highly depends on choice configurations, where optimal ones vary with executed workloads. Among various alternatives for tuning, Bayesian optimization (BO) is a popular framework that finds near-optimal configurations given sufficient budget, but it suffers from re-optimization issue and not practical real production. When applying transfer learning accelerate...
Due to the continuous deepening impact of COVID-19 pandemic on global economy and exacerbation "triple overlapping" situation in China, there has been a significant increase employment pressure dynamic changes considerable number migrant workers. This brought about new situations problems for economic social development urban rural areas. The urbanization workers is systematic project involving multiple sectors departments such as reform, finance, education, housing, human resources,...