A5001885257- Complex Network Analysis Techniques
- Opinion Dynamics and Social Influence
- Spam and Phishing Detection
- Misinformation and Its Impacts
- Sentiment Analysis and Opinion Mining
- Advanced Graph Neural Networks
- Peer-to-Peer Network Technologies
- 3D Shape Modeling and Analysis
- Petri Nets in System Modeling
- Formal Methods in Verification
- Image and Signal Denoising Methods
- Remote-Sensing Image Classification
- Text and Document Classification Technologies
- Generative Adversarial Networks and Image Synthesis
- Digital and Cyber Forensics
- CCD and CMOS Imaging Sensors
- Kruppel-like factors research
- Macrophage Migration Inhibitory Factor
- Advanced Surface Polishing Techniques
- Elevator Systems and Control
- Simulation and Modeling Applications
- Mineral Processing and Grinding
- Human Mobility and Location-Based Analysis
- Privacy-Preserving Technologies in Data
- Advanced Image Fusion Techniques
Macquarie University
2022-2025
Hong Kong Polytechnic University
2024
Wuhan University
2023
Lanzhou University
2019-2021
Nanjing University
2013-2021
Australian National University
2013-2014
Data61
2014
Nanjing General Hospital of Nanjing Military Command
2013
A community reveals the features and connections of its members that are different from those in other communities a network. Detecting is great significance network analysis. Despite classical spectral clustering statistical inference methods, we notice significant development deep learning techniques for detection recent years with their advantages handling high dimensional data. Hence, comprehensive overview detection's latest progress through timely to academics practitioners. This...
Users' involvement in creating and propagating news is a vital aspect of fake detection online social networks. Intuitively, credible users are more likely to share trustworthy news, while untrusted have higher probability spreading untrustworthy news. In this paper, we construct dual-layer graph (i.e., layer user layer) extract multi-relations networks derive rich information for detecting Based on the graph, propose model Us-DeFake. It learns propagation features interaction layer. Through...
Community structures can reveal organizations and functional properties of complex networks; hence, detecting communities from networks is great importance. With the surge large in recent years, efficiency community detection demanded critically. Therefore, many local methods have emerged. In this paper, we propose a node similarity based method, which also one consisted two phases. first phase, take out with largest degree network to it as an exemplar insert its most similar neighbor into...
Many real-world systems can be abstracted as networks. As those always change dynamically in nature, the corresponding networks also evolve over time general, and detecting communities from such time-evolving has become a critical task. In this paper, we propose an incremental detection method, which stably detect high-quality community structures When network evolves previous snapshot to current one, proposed method only considers affiliations of partial nodes efficiently, are either...
In the context of Fashion Apparel Industry 4.0, a transformative evolution is directed towards Online Mass Customization (OAMC) strategy, which provides efficient and personalized apparel product solutions to consumers. A critical challenge within this customization process determination sizes. While existing research addresses comfort evaluation in relation wearer garment fit, little attention has been given how fit influences wearer’s body image, also an important purchase consideration....
Abstract In the field of ultra-precision manufacturing, such as lithography lenses, achieving nanometer-level errors across entire frequency range is crucial. Magnetorheological finishing (MRF) technology, a high-precision processing method with high efficiency and low subsurface damage, often introduces mid-spatial (MSF) error due to removal attenuation effect regular polishing trajectory in long continuous process. It causes various imaging light transmission defects that limit performance...
To tackle the challenges of edge image processing scenarios, we have developed a novel heterogeneous signal processor (HISP) pipeline combining advantages traditional processors and deep learning ISP (DLISP). Through multi-dimensional quality assessment (IQA) system integrating methods like RankIQA, BRISQUE, SSIM, various partitioning schemes were compared to explore highest-quality imaging scheme. The UNet-specific deep-learning unit (DPU) based on field programmable gate array (FPGA)...
The centrality plays an important role in many community-detection algorithms, which depend on various kinds of centralities to identify seed vertices communities first and then expand each based the seeds get resulting community structure. traditional algorithms always use a single measure recognize from network, but has both pros cons when being used this circumstance; hence identified using might not be best ones. In paper, we propose framework integrates advantages measures network...
The data abuse issue has risen along with the widespread development of deep learning inference service (DLIS). Specifically, mobile users worry about their input being labeled to secretly train new models that are unrelated DLIS they subscribe to. This unique issue, unlike privacy problem, is rights owners in context learning. However, preventing demanding when considering usability and generality scenario. In this work, we propose, our best knowledge, first prevention mechanism called...
Social events reflect the dynamics of society and, here, natural disasters and emergencies receive significant attention.The timely detection these can provide organisations individuals with valuable information to reduce or avoid losses.However, due complex heterogeneities content structure social media, existing models only learn limited information; large amounts semantic structural are ignored.In addition, high labour costs, it is rare for media datasets include high-quality labels,...
Community structure is one of the important features complex networks. Researchers have derived a number algorithms for detecting communities, some them suffer from high complexity or need prior knowledge, such as size community communities. For them, quality detected cannot be guaranteed, even results are nondeterministic. In this paper, we propose Self-Organizing Map (SOM)-based method We first preprocess network by removing nodes and their associated edges which little contribution to...