A5102016644- Recommender Systems and Techniques
- Topic Modeling
- Rough Sets and Fuzzy Logic
- Advanced Decision-Making Techniques
- Fire Detection and Safety Systems
- Combustion and Detonation Processes
- Natural Language Processing Techniques
- Fire dynamics and safety research
- Artificial Intelligence in Games
- Advanced Computational Techniques and Applications
- Sports Analytics and Performance
- Air Quality and Health Impacts
- Data Mining Algorithms and Applications
- Complex Network Analysis Techniques
- Remote-Sensing Image Classification
- Optimal Experimental Design Methods
- Context-Aware Activity Recognition Systems
- Evaluation and Optimization Models
- Advanced Sensor and Control Systems
- Privacy-Preserving Technologies in Data
- Machine Learning and ELM
- Sentiment Analysis and Opinion Mining
- Financial Risk and Volatility Modeling
- Gambling Behavior and Treatments
- Multimodal Machine Learning Applications
Liaoning Technical University
2024-2025
NetEase (China)
2023-2025
Tianjin University
2024
Community Link
2017
Southeast University
2009-2014
Beijing Aerospace Flight Control Center
2012
Tongji University
2007
To investigate the effect of space tightness on inerting liquid CO2. Pottery jar liquor warehouse was selected as research subject, numerical simulation utilized to study spatial and CO2 migration distribution under different degrees injection flow rates. The results revealed that after into space, distributed like an "umbrella", protective layer undergoes a dynamic process concentration increase thickness enhancement, achieving upward accumulation inert medium layer. divided direct zone,...
Abstract Clean fire extinguishing systems applicable to the pottery jar liquor warehouse are in demand. In this study, taking 53vol% as research subject, models of various clean comprising water mist, liquid carbon dioxide (LCO 2 ) and nitrogen (LN were established using a dynamic simulator determine their effect. A feasibility assessment was performed under different source types, sizes, ventilation conditions. The efficiency analyzed terms time, oxygen concentration, space temperature....
The Social Media Prediction (SMP) challenge aims to predict the future popularity of online posts by leveraging social media data. data contains multimodal information, such as text, images, time series, etc. Previous methods have proposed many feature extraction and construction represent these thereby predicting posts. Despite success previous in extracting features from data, tend be predominantly lower-order, posing a accurately capturing rich information contained text images. In this...
Task offloading is a potential solution to satisfy the strict requirements of computation-intensive and latency-sensitive vehicular applications due limited onboard computing resources. However, overwhelming upload traffic may lead unacceptable uploading time. To tackle this issue, for tasks taking environmental data as input, perceived by roadside units (RSU) equipped with several sensors can be directly exploited computation, resulting in novel task paradigm integrated communications,...
Graph Neural Networks (GNNs) are powerful deep learning models designed for graph-structured data, demonstrating effectiveness across a wide range of applications.The softmax function is the most commonly used classifier semi-supervised node classification. However, lacks spatial information graph structure. In this paper, we propose similarity regularized GNNs in By incorporating non-local total variation (TV) regularization into activation function, can more effectively capture inherent...
The burgeoning online video game industry has sparked intense competition among providers to both expand their user base and retain existing players, particularly within social interaction genres. To anticipate player churn, there is an increasing reliance on machine learning (ML) models that focus dynamics. However, the prevalent opacity of most ML algorithms poses a significant hurdle acceptance domain experts, who often view them as "black boxes". Despite availability eXplainable...
Classic methodologies of DOE are widely applied in design, manufacture, quality management and related fields. The resulting data can be analysed with linear modeling methods such as multiple regression which generates a set equations, Y = F(X), that enable us to understand how varying the mean one or more inputs changes responses. To develop, scale-up transfer robust processes manufacturing we also need control tolerances each critical X extent variation X’s propagate through Y’s this may...