A5106695869- Cloud Computing and Resource Management
- Distributed and Parallel Computing Systems
- Stock Market Forecasting Methods
- Parallel Computing and Optimization Techniques
- Age of Information Optimization
- Medical Image Segmentation Techniques
- Neural Networks and Applications
- Radiomics and Machine Learning in Medical Imaging
- Advanced Database Systems and Queries
- IoT Networks and Protocols
- Software Testing and Debugging Techniques
- Algorithms and Data Compression
- Software Reliability and Analysis Research
- Software System Performance and Reliability
- Traffic Prediction and Management Techniques
- Peer-to-Peer Network Technologies
- IoT and Edge/Fog Computing
- Microstructure and mechanical properties
- Caching and Content Delivery
- AI in cancer detection
- Time Series Analysis and Forecasting
- Aluminum Alloy Microstructure Properties
- Advanced Materials Characterization Techniques
Hunan University
2016-2022
Hong Kong University of Science and Technology
2021
University of Hong Kong
2021
South China University of Technology
2012
Recently, artificial intelligence plays a more and important role in our study daily lives. People use it to forecast or make the best decisions. Artificial neural network (ANN) is most model forecast. However, not satisfying enough that accuracy just 80%-92%. So we need strengthen do better job. In this paper, come up with way improve network, through which users can forecasting, classifying other work exactly. To implement model, add new parameter activation function so whole may...
Task scheduling in cloud environments is the problem of assigning and executing computational tasks on available resources. Effective task can improve processor utilization, reduce energy consumption, user experience. Large-scale under multiple constraints an NP-complete problem. The traditional algorithm cannot be applied to large-scale scheduling, either because high time complexity or its heuristic complexly scenarios. gradually becoming a challenge computing. article proposes...
The prediction of the glass-forming ability (GFA) alloys is crucial for developing new materials with excellent properties. However, GFA-prediction very difficult due to absence both fundamental theory and limitation experimental approaches. With help Regression Random Forest predict absent but necessary feature, 4 datasets (training, test, validation, predicting datasets) binary are first established; same training test six machine-leaning (ML) models then trained tested. best performance...
Status code mappings reveal state shifts of a program, mapping one status to another. Due careless programming or the lack system-wide knowledge whole developers can make incorrect mappings. Such errors are widely spread across modern software, some which have even become critical vulnerabilities. Unfortunately, existing solutions merely focus on single values, while never considering relationships, that is, mappings, among them. Therefore, it is imperative propose an effective method detect...