A5054691502- Machine Learning and Data Classification
- Machine Learning and ELM
- Domain Adaptation and Few-Shot Learning
- Neural Networks and Applications
- Face and Expression Recognition
- Orthopedic Infections and Treatments
- Computational Drug Discovery Methods
- Complex Systems and Time Series Analysis
- Microfinance and Financial Inclusion
- Digital Imaging for Blood Diseases
- Fuzzy Logic and Control Systems
- Imbalanced Data Classification Techniques
- Hydrological Forecasting Using AI
- Machine Learning and Algorithms
- Text and Document Classification Technologies
- Brain Tumor Detection and Classification
- Stock Market Forecasting Methods
- Blockchain Technology Applications and Security
- Medical Image Segmentation Techniques
- Economic Growth and Development
- Financial Markets and Investment Strategies
- Medical Imaging and Analysis
- Energy, Environment, and Transportation Policies
- FinTech, Crowdfunding, Digital Finance
- Image Retrieval and Classification Techniques
Yanbian University
2025
Shenzhen University
2019-2024
Naval University of Engineering
2024
Fiberhome Technology Group (China)
2024
Despite the remarkable success of deep neural networks (DNNs), security threat adversarial attacks poses a significant challenge to reliability DNNs. By introducing randomness into different parts DNNs, stochastic methods can enable model learn some uncertainty, thereby improving robustness efficiently. In this paper, we theoretically discover universal phenomenon that will shift distributions feature statistics. Motivated by theoretical finding, propose enhancement module called Feature...
The advancement of the digital economy is vital for decreasing agricultural carbon emissions and fostering high-quality development. Using panel data from 31 Chinese provinces between 2000 2021, this paper employs a dual machine learning model causal inference to analyze impact financial inclusion on intensity, its underlying mechanisms, characteristics heterogeneity. study finds that inclusive finance significantly reduces intensity through two main channels: enhancing scientific...
In response to the escalating threat of cyberattacks on smart connected vehicles, numerous Intrusion Detection Systems (IDSs) have emerged. However, existing IDSs often prioritize enhancing detection accuracy while overlooking time needed for training and detection. Moreover, they may not fully leverage combined utilization CAN bus IDs data field with external network data. Consequently, these systems frequently struggle meet real-time demands broader attack scenarios inherent in in-vehicle...
The coronavirus disease (COVID-19) pandemic has flooded public health organizations around the world, highlighting significance and responsibility of medical crowdfunding in filling a series gaps shortcomings publicly funded system providing new fundraising solution for people that addresses health-related needs. However, fact remains from sources is relatively low only few studies have been conducted regarding this issue. Therefore, performance predictions multi-model comparisons important...
The continuous combination of digital network technology and traditional financial services has given birth to networks, which explore massive economic data under the AI-driven models achieve intelligent connections among institutions, markets, transactions, instruments. Empirical asset pricing is a challenging task in analysis, attracted research attention. However, existing studies only focus on tackling challenges equity risk premium single stock market. Considering multiple linkages...
The representation, measure, and handling of uncertainty in an application deep learning have a significant impact on the performance systems.Uncertainty is embedded entire process from data, which can roughly be categorized as three types, i.e., data uncertainty, model prediction uncertainty.Appropriately modeling processing uncertainties different phases significantly improve accuracy robustness.Focusing 3rd type lies phase output (i.e., probability distribution label space) to final...