A5100658869- Stochastic processes and statistical mechanics
- Differential Equations and Numerical Methods
- Stochastic processes and financial applications
- Statistical Distribution Estimation and Applications
- Bayesian Methods and Mixture Models
- Theoretical and Computational Physics
- Nonlinear Differential Equations Analysis
- Differential Equations and Boundary Problems
- Recommender Systems and Techniques
- Advanced Statistical Methods and Models
- Numerical methods for differential equations
- Financial Risk and Volatility Modeling
- Epigenetics and DNA Methylation
- Sparse and Compressive Sensing Techniques
- Complex Systems and Time Series Analysis
- Insurance and Financial Risk Management
- Human Mobility and Location-Based Analysis
- Electronic Health Records Systems
- Optimism, Hope, and Well-being
- Mathematical Biology Tumor Growth
- Artificial Intelligence in Healthcare
- Random Matrices and Applications
- Probability and Risk Models
- Control Systems and Identification
- Adversarial Robustness in Machine Learning
Zhejiang Gongshang University
2010-2024
Anqing Normal University
2014
Shanghai Public Security Bureau
2011
The development of breast cancer is closely linked to the estrogen receptor ERα, which also considered be an important target for treatment cancer. Therefore, compounds that can antagonize ERα activity may drug candidates In development, save manpower and resources, potential active are often screened by establishing compound prediction model. For 1974 collected, top 20 molecular descriptors significantly affected biological were using LASSO regression models combined with 10-fold...
Assess the level of meaning in life patients with COVID-19, explore relationship among COVID-19 perceived social support, medical coping modes, psychological resilience and meaning, clarify mediating effect.Through convenience sampling method, 144 were selected year 2021, surveyed by using general information questionnaire, support scale (PSSS), modes questionnaire (MCMQ), (MLQ) Connor-Davidson (CD-RISC). After collected data preprocessed SPSS, t-tests, multiple comparison Pearson...
Denoising diffusion models have shown great potential in multiple research areas. Existing diffusion-based generative methods on de novo 3D molecule generation face two major challenges. Since majority heavy atoms molecules allow connections to through single bonds, solely using pair-wise distance model geometries is insufficient. Therefore, the first one involves proposing an effective neural network as denoising kernel that capable capture complex multi-body interatomic relationships and...
Since the emergence of deep neural network (DNN), it has achieved excellent performance in various research areas. As combination DNN and reinforcement learning, learning (DRL) becomes a new paradigm for solving differential game problems. In this study, we build up environment apply relevant DRL methods to specific bio-inspired problem: dog sheep game. The is set on circle where chases down attempting escape. According some presuppositions, are able acquire kinematic pursuit evasion...
Abstract Hepatitis C, a particularly dangerous form of viral hepatitis caused by C virus (HCV) infection, is major socio-economic and public health problem. Due to the rapid development deep learning, it has become common practice apply learning healthcare industry improve effectiveness accuracy disease identification. In order detection, this study proposes an improved denoising autoencoder (IDAE) applies detection. Conventional introduces random noise at input layer encoder. However, due...
Summary The development of the internet has brought great convenience to people's travel and shopping. More more people choose shop online. As e‐commerce continues grow in scale, number variety products are also growing rapidly, which results customers taking a lot time find they want buy. This problem prevents from using Internet quickly efficiently. In order solve these problems, personalized recommendation system comes into being. It can directly predict content that users may be...
To address the issues of target omission and inclusion a large number background points in keypoint sampling for point cloud-based object detection, an improved algorithm based on PV-RCNN network is introduced. This approach employs both regional proposal fusion weighted Non-Maximum Suppression (NMS) to merge proposals generated at various scales while eliminating redundancy. A segmentation utilized segment foreground from original cloud, center are identified these proposals. Gaussian...
The development of “wise medical” is crucial to global carbon reduction. medical sector not only has the moral obligation reduce emissions, but also responsibility provide high-quality services patients. Existing research mostly focuses on relationship between low-carbon and wise medical, while ignoring transformation patients’ opinions in context transition. paper crawls text data comments Zhihu platform (a Chinese similar Quora), explores focus patients through co-occurrence analysis...
Abstract The SCN networks is incrementally generated by stochastic configuration (SC) algorithms. It randomly assigns the input weights and deviations of hidden nodes through a supervisory mechanism, which can be trained solving linear modeling problems. version that uses least squares to estimate output weight performs well. This article introduces an alternative strategy for performing complete Bayesian inference (BI) networks. Different from traditional way, training algorithm we proposed...