A5058853900- Complex Network Analysis Techniques
- Opinion Dynamics and Social Influence
- Misinformation and Its Impacts
- Stock Market Forecasting Methods
- Advanced Neural Network Applications
- Customer churn and segmentation
- Big Data and Business Intelligence
- Consumer Retail Behavior Studies
- Customer Service Quality and Loyalty
- Forecasting Techniques and Applications
- Time Series Analysis and Forecasting
- Evaluation and Optimization Models
- EEG and Brain-Computer Interfaces
- Infrared Target Detection Methodologies
- Advanced Text Analysis Techniques
- Functional Brain Connectivity Studies
- Video Surveillance and Tracking Methods
- Attention Deficit Hyperactivity Disorder
Hong Kong Polytechnic University
2024
Nanjing University of Information Science and Technology
2023
Communication University of China
2019-2021
Beijing Wuzi University
2016
Backgroud Effective communication of accurate information through social media constitutes an important component public health interventions in modern time, when traditional approaches such as contact tracing, quarantine and isolation are among the few options for containing disease spread population. The success control COVID-19 outbreak started from Wuhan, capital city Hubei Province China relies heavily on resilience residents to follow which induce substantial interruption...
Dynamic functional connectivity (dFC), which can capture the abnormality of brain activity over time in resting-state magnetic resonance imaging (rs-fMRI) data, has a natural advantage revealing abnormal mechanism patients with Attention Deficit/Hyperactivity Disorder (ADHD). Several deep learning methods have been proposed to learn dynamic changes from rs-fMRI for FC analysis, and achieved superior performance than those using static FC. However, most existing only consider dependencies two...
Target detection algorithms based on deep learning and convolutional neural networks (CNN), such as Faster Regionbased Convolutional Neural Network method (R-CNN) Single Shot Multi-Box Detector (SSD), are superior to traditional in accuracy speed. However, there is still a lack of detailed research the different performance between algorithms. This paper introduces R-CNN algorithm SSD respectively, implements function open source code. In order evaluate these two algorithms, large number...
<abstract> <p>In order to avoid forming an information cocoon, the propagation of COVID-19 is usually created through action "proactive search", important behavior other than "reactive follow". This has been largely ignored in modeling dynamics. Here, we propose fill this gap by proposing a proactive-reactive susceptible-discussing-immune (PR-SFI) model describe patterns co-propagation on social networks. based forwarding quantity and takes into account both proactive search...
Big data has played an increasingly important role in global manufacturing, circulation, distribution, and consumption activities. The management mode based on is remolding the of enterprises. In control enterprises, science become supporting tool for decision-making. It could help managers enterprises to better understand hold changes within outside environment enterprise so as establish effective strategies through excavate discover correlations among mass predict forms future. Firstly,...
With economic development, Express delivery companies is growing faster.In the fierce competition, quality of service become more and important in business, it gradual becomes core competitiveness express companies.This paper evaluates through perspective customer perception established assessment indices.Construct services evaluation system according to characteristics courier industry, we set up indicators six dimensions: character, function, safety, economy, aging, speed, which make a...
Microblog is the most prevalent social platform recently in China, where participants' classification plays a significant role. The existing methods usually categorize users into limited levels and ignore hierarchical characteristic of information spread. In this paper, we propose participant model based on core group mining opinion leader identification, develop an allocation algorithm to calculate allocated value for comprehensive indices each user. According directions dissemination,...