A5101992019- Spam and Phishing Detection
- Imbalanced Data Classification Techniques
- Target Tracking and Data Fusion in Sensor Networks
- Cybercrime and Law Enforcement Studies
- Environmental Changes in China
- Neuroscience and Music Perception
- Complex Network Analysis Techniques
- Wireless Signal Modulation Classification
- Digital Marketing and Social Media
- Multisensory perception and integration
- Sentiment Analysis and Opinion Mining
- Radar Systems and Signal Processing
- Advanced Algorithms and Applications
- Stock Market Forecasting Methods
- Data Management and Algorithms
- Recommender Systems and Techniques
- Advanced Graph Neural Networks
- Customer churn and segmentation
- Consumer Retail Behavior Studies
- Financial Markets and Investment Strategies
- Energy Load and Power Forecasting
- Machine Learning and Data Classification
- Thin-Film Transistor Technologies
- Quantum Computing Algorithms and Architecture
- Advancements in Semiconductor Devices and Circuit Design
Shanghai University of Engineering Science
2021-2024
Huazhong University of Science and Technology
2023
Harbin Engineering University
2020
Beijing International Studies University
2020
Shanghai Jiao Tong University
2020
Central University of Finance and Economics
2020
Shanghai University
2018
National Cheng Kung University
2018
Peking University
2009
National University of Defense Technology
2006
Graphs have been widely adopted to accomplish fraud detection tasks because of their inherently favorable structure capture the intricate features in many complicated scenarios, especially some modern e-commerce situations that various relation attributes like transactions. These works tend utilize direct aggregate information about neighbor nodes target node or aggregation after conditional filter and mostly use local but ignore global information. However, cases, abnormal points are...
Graph-based fraud detection is crucial in identifying illegal activities social networks, finance, and other sectors. Despite recent progress this area, most of current researches typically require a large amount annotated data to demonstrate its benefits. In practice, obtaining sufficient high-quality challenging, limiting the effectiveness model training. Therefore, leveraging extremely limited label information enhance performance. We propose context-aware graph neural network (CGNN)...
Temperature-sensitive electrical parameter (TSEP) approaches are widely employed in the junction temperature (T <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">j</sub> ) extraction and prediction of power semiconductor devices. In this paper, turn-off loss (E xmlns:xlink="http://www.w3.org/1999/xlink">off</sub> time (t presented as temperature-sensitive parameters. The abrupt change Insulated Gate Bipolar Transistor (IGBT) occurs during...
The rapid development of quantitative portfolio optimization in financial engineering has produced promising results AI-based algorithmic trading strategies. However, the complexity markets poses challenges for comprehensive simulation due to various factors, such as abrupt transitions, unpredictable hidden causal and heavy tail properties. This paper aims address these by employing heavy-tailed preserving normalizing flows simulate high-dimensional joint probability complex environment...
This paper studies and establishes a system for the problem of lack personalized commodity recommendation low pertinence in shopping offline. Compared with online recommendation, offline has inherent disadvantages on data. overcomes its difficulties does further analysis research information image stores, algorithm model intelligent was established, then constructed to demonstrate practicability feasibility. Finally, we described future be solved, also provide promising outlook.
We propose a scheme for controllably entangling the ground states of five-state W-type atoms confined in cavity and realizing swap gate phase operations. In this is only virtually excited atomic are almost not occupied, so produced entangled quantum logic operations very robust against decay spontaneous emission.
In the field of modern wireless communication, electromagnetic spectrum resources are increasingly tight, and it is becoming more common for one single antenna to receive multiple communication signals. High-order cumulant can suppress noise well, has been widely used modulation recognition signal in single-channel but seldom time-frequency aliasing signals single-channel. This because we need use estimated carrier frequency down-conversion obtain baseband before calculating high-order...
摘要:
The study of the relationship between urban land and its population can further uncover simple nature behind complex elements, which is critical theory practical significance for solving contradictions environment, economy current city. This paper, based on geographic information system (GIS), has created a integrating model, taken cellular automaton (CA) as dominant center. It would become an important point relations in China. Moreover, artificial neural network, intelligent genetic...
PPI 的特异性调节, 并且神经机制方面的研究集中于听皮层区域, 仍缺乏对皮 层下机制的探讨。在以往研究的成果基础之上, 借助听觉信息加工的双通路模型, 采用行为测量、脑电和脑成 像技术, 揭示特征和空间两种注意调节 的神经活动在听觉系统中的层次性神经表达。包括 1)建立特征注 意和空间注意调节 的统一行为模型, 考察两种注意调节 的时间动态性异同; 2)两种注意调节 的脑 干分离机制, 即前脉冲刺激包络和精细结构成分加工在注意调节 中的作用差异; 3)两种注意调节 的关