A5110191664- Software Engineering Research
- Software Reliability and Analysis Research
- Complex Network Analysis Techniques
- Stock Market Forecasting Methods
- Biomedical Text Mining and Ontologies
- Impact of Technology on Adolescents
- Natural Language Processing Techniques
- Epigenetics and DNA Methylation
- Advanced Wireless Network Optimization
- Advanced Photocatalysis Techniques
- Anomaly Detection Techniques and Applications
- Software System Performance and Reliability
- Water Quality Monitoring Technologies
- Video Surveillance and Tracking Methods
- Forecasting Techniques and Applications
- Network Traffic and Congestion Control
- Advanced Neural Network Applications
- Gene expression and cancer classification
- Advanced Nanomaterials in Catalysis
- Single-cell and spatial transcriptomics
- Digital Marketing and Social Media
- TiO2 Photocatalysis and Solar Cells
- Peer-to-Peer Network Technologies
- Technology Adoption and User Behaviour
- Traffic Prediction and Management Techniques
Advanced Energy Materials (United States)
2025
Nankai University
2025
Xi’an University of Posts and Telecommunications
2021
Beihang University
2017-2019
National Taiwan University of Science and Technology
2011-2013
San Jose State University
2002
Software defect prediction can help us identify software modules and improve quality. The existing mainly analyzes the code or development process uses statistical feature data on files categories related to defects as metrics. method disregards macroscopic integrity of programs relevance local surrounding program elements. For this reason, study introduces a complex network technology into prediction, establishes model, metric design set metrics that reflect global features defects,...
Identifying the most important classes in a software system is crucial for engineers to understand or maintain an unfamiliar system. Complex network theory provides new way study characteristics of large-scale software. Unfortunately, current studies consider only one limited number factors affecting structure, rendering inaccurate results mining key Thus, we propose approach using various complex metrics automatically identify from global and local aspects. From aspect, location class its...
Swimmer tracking in swimming pools is a challenging vision task due to its varying complex background. Most moving object detection methods are developed for static or partial backgrounds, and thus can not be applied swimmer problems. This work presents an approach combining mean-shift clustering cascaded boosting learning algorithm detection. There three main steps the proposed framework: background modeling, detection, tracking. A recorded image sequences from practical indoor pool was...
Since the development of computer science, our lives have become increasingly dependent on software. While we enjoy benefits and convenience that software programs provide, cannot ignore issues with reliability, complexity, security. introduction complex networks, people been using network to analyze problems; however, traditional models are not currently capable analyzing large scale structures. In this paper, a new model is proposed, which each node in can be assigned set coordinates...
Abstract Spatially Resolved Transcriptomics (SRT) serves as a cornerstone in biomedical research, revealing the heterogeneity of tissue microenvironments. Integrating multimodal data including gene expression, spatial coordinates, and morphological information poses significant challenges for accurate domain identification. Herein, we present Multi-view Contrastive Graph Autoencoder (MCGAE), cutting-edge deep computational framework specifically designed intricate analysis transcriptomics...
In this study, a classification model for predicting human judgment accuracy in Taiwan Stock Exchange Capitalization Weighted Index (TAIEX) was developed using the decision tree model. The training data learning obtained from questionnaire responses of 22 participants various fields. Experimental results showed proposed is able to explore important factors that affect forecasters' accuracy. These including accumulated gain/loss investment, education level, occupation type, and working...
Facing the massive auroral observation data, it is necessary to automatically detect vortex event study its occurrence regularity and statistical characteristics. For this purpose, a large number of accurate pixel-level annotations are required by using supervised object detection methods. However, it's very difficult acquire structure. Only image-level (existence structures in image) bounding box can be acquired from experts. In study, we propose weakly method for detecting all-sky image....
Multimedia application integrates a variety of media, namely, audio, video, images, graphics, text and data. The ATM (Asynchronous Transfer Mode) technique has been recommended by the CCITT as transport vehicle for BISDN (Broadband Integrated Service Digital networks) which is designed to provide multimedia traffic services. In this work we study some ATM-compatible multiple access MAN (Metropolitan Area Network) protocols, including DQDB (Distributed Queue Dual Bus, also known IEEE 802.6),...