A5101530677- Quantum Information and Cryptography
- Complex Network Analysis Techniques
- Aquaculture Nutrition and Growth
- Algebraic structures and combinatorial models
- Advanced Graph Neural Networks
- Aquaculture disease management and microbiota
- Machine Learning in Bioinformatics
- Advanced Topics in Algebra
- Gene expression and cancer classification
- Quantum Computing Algorithms and Architecture
- Bioinformatics and Genomic Networks
- Computational Drug Discovery Methods
- Quantum and electron transport phenomena
- Machine Learning in Materials Science
- Physiological and biochemical adaptations
- Artificial Intelligence in Healthcare
- Advanced Software Engineering Methodologies
- Multi-Criteria Decision Making
- Metabolomics and Mass Spectrometry Studies
- AI in cancer detection
- Anomaly Detection Techniques and Applications
- Imbalanced Data Classification Techniques
- Invertebrate Immune Response Mechanisms
- Machine Learning in Healthcare
- Electricity Theft Detection Techniques
Anhui Agricultural University
2023-2025
Nanjing Agricultural University
2023-2024
Inspire Institute
2024
National University of Defense Technology
2019-2023
University of Chinese Academy of Sciences
2021-2022
Dalian Maritime University
2022
Qingdao University
2022
Hohai University
2019-2021
Northeast Normal University
2009-2021
Macau University of Science and Technology
2017-2018
Lipids are critical nutrients for aquatic animals, and excessive or insufficient lipid intake can lead to physiological disorders, which further affect fish growth health. In the gut microbiota has an important regulatory role in metabolism. However, effects of a high-fat diet on physical health diversity freshwater drum (Aplodinotus grunniens) unclear. Therefore, present study, control group (Con, 6%) (HFD, 12%) were established 16-week feeding experiment explore changes potential...
Abstract Identifying the vital nodes in networks is of great significance for understanding function and nature networks. Many centrality indices, such as betweenness (BC), eccentricity (EC), closeness centricity (CC), structural holes (SH), degree (DC), PageRank (PR) eigenvector (VC), have been proposed to identify influential However, some these indices limited application scopes. EC CC are generally only applicable undirected networks, while PR VC used directed To design a more measure,...
Air pollution has become one of the key environmental concerns in urban sustainable development. It is important to evaluate impact air on socioeconomic development since it prerequisite enforce an effective prevention policy pollution. In this paper, we model economic as a Multiple Criteria Decision Making (MCDM) problem. particular, propose novel Technique for Order Preference by Similarity Ideal Solution (TOPSIS) analysis framework multiple factors pollutants and Our method can overcome...
Training gene expression data with supervised learning approaches can provide an alarm sign for early treatment of lung cancer to decrease death rates. However, the samples features involve lots noises in a realistic environment. In this study, we present random forest self-paced bootstrap improvement classification and prognosis based on data. To be specific, propose ensemble approach improving model performance by selecting multi-classifiers. Then, investigate sampling strategy gradually...
Cysteine S-carboxyethylation, a novel post-translational modification (PTM), plays critical role in the pathogenesis of autoimmune diseases, particularly ankylosing spondylitis. Accurate identification S-carboxyethylation sites is essential for elucidating their functional mechanisms. Unfortunately, there are currently no computational tools that can accurately predict these sites, posing significant challenge to this area research. In study, we developed new deep learning model, DLBWE-Cys,...
A deep understanding of mechanical waves is crucial for students to succeed in studying many advanced physics topics. Studies existing literature have revealed that often widespread difficulties and misconceptions on wave propagation. This research develops applies a conceptual framework model examine students' propagation from the knowledge integration perspective. Based interview results, was developed used guide development multiple-choice test targets assessment The given first-year...
The growing expansion of data availability in medical fields could help improve the performance machine learning methods. However, with healthcare data, using multi-institutional datasets is challenging due to privacy and security concerns. Therefore, privacy-preserving methods are required. Thus, we use a federated model train shared global model, which central server that does not contain private all clients maintain sensitive their own institutions. scattered training connected...
One of recent proposals on standardizing quality user experience (QoE) video streaming over mobile network is Mean Opinion Score (vMOS), which can model QoE in 5 discrete grades. However, there are few studies quantifying vMOS and investigating the relationship between other service (QoS) parameters. In this paper, we address concern by proposing a novel data analytical framework based data. particular, our consists K-means clustering logistic regression. This integrates benefits both these...
High frequency of network security incidents has also brought a lot negative effects and even huge economic losses to countries, enterprises individuals in recent years. Therefore, more attention been paid the problem security. In order evaluate newly included vulnerability text information accurately, reduce workload experts false rate traditional method. Multiple deep learning methods for classification evaluation are proposed this paper. The standard Cross Site Scripting (XSS) data is...
Mortality risk prediction helps clinicians make better decisions in patient healthcare. However, existing severity scoring systems or algorithms used intensive care units (ICUs) often rely on laborious manual collection of complex variables and lack sufficient validation diverse clinical environments, thus limiting their practical applicability. This study aims to evaluate the performance machine learning models that utilize routinely collected data for short-term mortality prediction.Using...
Molecular descriptor selection is an essential procedure to improve a predictive quantitative structure-activity relationship (QSAR) model. However, within the QSAR model, there are number of redundant, noisy and irrelevant descriptors. In this study, we propose novel framework using self-paced learning (SPL) via sparse logistic regression (LR) with Logsum penalty (SPL-Logsum), which can simultaneously adaptively identify simple complex samples avoid over-fitting. SPL inspired by process...
Abstract In recent years, a surge of criminal activities with cross-cryptocurrency trades have emerged in Ethereum, the second-largest public blockchain platform. Most existing anomaly detection methods utilize traditional machine learning feature engineering or graph representation technique to capture information transaction network. However, these either ignore timestamp and flow direction network only consider single network, trading patterns Ethereum are usually ignored. this paper, we...
The appropriate level of dietary lipids is essential for the nutrient requirements, rapid growth, and health maintenance aquatic animals, while excessive lipid intake will lead to deposition affect fish health. However, symptoms in liver freshwater drums (Aplodinotus grunniens) remain unclear. In this study, a 4-month rearing experiment feeding with high-fat diets 6-week starvation stress were conducted evaluate physiological alteration underlying mechanism associated A. grunniens. From...
A method of constructing Temperley-Lieb algebra (TLA) representations has been introduced in [Xue et al. arXiv:0903.3711]. Using this method, we can obtain another series n 2 × matrices U which satisfy the TLA with single loop [Formula: see text]. Specifically, present a 9 matrix Via Yang-Baxterization approach, unitary text]-matrix, solution Yang-Baxter equation. This is universal for quantum computing.
Cancer diseases have serious influence on people's live, but the-state-of-art machine learning approaches the potential to decrease cancer death rates by formulating prevention strategies for treatment. Some supervised methods been used give early warning of successfully using gene expression data, most prominent challenge is insufficient labeled samples biological especially in datasets. It may cause training model with over-fitting. Therefore, semi-supervised method approaches, such as...