A5019383391- Graph Theory and Algorithms
- Advanced Graph Neural Networks
- Data Management and Algorithms
- Teleoperation and Haptic Systems
- Manufacturing Process and Optimization
- Advanced Database Systems and Queries
- Complex Network Analysis Techniques
- Dielectric materials and actuators
- Medical Image Segmentation Techniques
- Caching and Content Delivery
- Advanced Neural Network Applications
- Fault Detection and Control Systems
- Machine Fault Diagnosis Techniques
- Medical Imaging and Analysis
- 3D Surveying and Cultural Heritage
- Advanced Image and Video Retrieval Techniques
- Carbon dioxide utilization in catalysis
- Algorithms and Data Compression
- Robot Manipulation and Learning
- Functional Brain Connectivity Studies
- Electromagnetic wave absorption materials
- Autonomous Vehicle Technology and Safety
- Cell Image Analysis Techniques
- Neural dynamics and brain function
- Machine Learning and Data Classification
UNSW Sydney
2019-2025
Hanseo University
2025
Shandong University
2020-2024
First People's Hospital of Yunnan Province
2024
National Engineering Research Center of Electromagnetic Radiation Control Materials
2019-2024
University of Electronic Science and Technology of China
2019-2024
Suzhou University of Science and Technology
2024
University of Hong Kong
2000-2024
Chongqing University
2014-2024
Shanghai University
2023-2024
With the rapid development of artificial intelligence, machine learning is gradually becoming popular for predictions in all walks life. In meteorology, it competing with traditional climate dominated by physical models. This survey aims to consolidate current understanding Machine Learning (ML) applications weather and prediction—a field growing importance across multiple sectors, including agriculture disaster management. Building upon an exhaustive review more than 20 methods highlighted...
Deep learning has attracted wide attention recently because of its excellent feature representation ability and end-to-end automatic method. Especially in clinical medical imaging diagnosis, the semi-supervised deep model is favored widely used it can make maximum use a limited number labeled data combine with large unlabeled to extract more information knowledge from it. However, scarcity image data, vast size, instability quality directly affect model's robustness, generalization,...
Recently there emerge many distributed algorithms that aim at solving subgraph matching scale. Existing algorithm-level comparisons failed to provide a systematic view of mainly due the intertwining strategy and optimization. In this paper, we identify four strategies three general-purpose optimizations from representative state-of-the-art algorithms. We implement with based on common Timely dataflow system for strategy-level comparison. Our implementation covers all conduct extensive...
The recent advances in photo-promoted CO<sub>2</sub> hydrogenation over solid catalysts have been reviewed.
The formation of reversible hydrogen bonds is a promising strategy for cross-linking organosilicon elastomers, which can yield the fascinating properties. Herein, we reported new type self-healing silicone rubber (hydrogen bond cross-linked rubber, HBSR) by multiple with α,ω-aminopropyl poly(dimethylsiloxane) and ethylene carbonate based on nonisocyanate reaction. between carbonyl imino groups as well generated hydroxyl were proved variable temperature Fourier transform infrared analysis....
Subgraph enumeration is a fundamental problem in graph analytics, which aims to find all instances of given query on large data graph. In this paper, we propose system called HUGE efficiently process subgraph at scale the distributed context. features 1) an optimiser compute advanced execution plan without constraints existing works; 2) hybrid communication layer that supports both pushing and pulling communication; 3) novel two-stage mode with lock-free zero-copy cache design; 4)...
With the rapid development of artificial intelligence, machine learning is gradually becoming popular in predictions all walks life. In meteorology, It competing with traditional climate dominated by physical models. This survey aims to consolidate current understanding Machine Learning (ML) applications weather and prediction&mdash;a field growing importance across multiple sectors including agriculture disaster management. Building upon an exhaustive review more than 20 methods...
In few-shot semantic segmentation (FSS), the key challenges are efficiently tuning interaction between support set and query distinguishing context, background, interfering items. To address these challenges, we propose prototype comparison networks for one-shot (OPCN) to capture details required FSS. Specifically, offer Fusion Interaction Module (FIM) improve performance by capturing correlation information features. Subsequently, Feature Enhancement (FEM), which aims enhance in features...
A new green energetic metal–organic framework has potential application prospects in the fields of greener propellants and multi-dimensional magnetic materials.
Sequential recommendation aims to recommend the next item that matches a user's interest, based on sequence of items he/she interacted with before. Scrutinizing previous studies, we can summarize common learning-to-classify paradigm -- given positive item, recommender model performs negative sampling add and learns classify whether user prefers them or not, his/her historical interaction sequence. Although effective, reveal two inherent limitations:(1) it may differ from human behavior in...
Abstract Localized electrochemical deposition microadditive manufacturing (AM) (LECD-µAM) technology represents a nontraditional method applied for the layer-by-layer fabrication of metal microstructures via fully automatic feedback mechanism. In terms material utilization and complex structure formation, proposed exhibits great potential microstructure fabrication. The LECD-µAM introduced in this study involves reduction cations electrolyte to form microstructures. This showed flow...
Lateralization of temporal lobe epilepsy (TLE) is critical for successful outcome surgery to relieve seizures. TLE affects brain regions beyond the lobes and has been associated with aberrant networks, based on evidence from functional magnetic resonance imaging. We present here a machine learning-based method determining laterality TLE, using features extracted resting-state connectivity brain. A comprehensive feature space was constructed include network properties within local regions,...
Hypergraphs provide a versatile framework for modeling complex relationships beyond pairwise interactions, finding applications in various domains. k -core decomposition is fundamental task hypergraph analysis that decomposes hypergraphs into cohesive substructures. Existing studies capture the cohesion based on vertex neighborhood size. However, such poses unique challenges, including efficiency of core value updates, redundant computation, and high memory consumption. We observe...