A5024214644- Recommender Systems and Techniques
- Complex Network Analysis Techniques
- Advanced Graph Neural Networks
- Caching and Content Delivery
- Image and Video Quality Assessment
- Advanced Bandit Algorithms Research
- Topic Modeling
- Human Mobility and Location-Based Analysis
- Cancer-related molecular mechanisms research
- Advanced Battery Technologies Research
- Opinion Dynamics and Social Influence
- Gallbladder and Bile Duct Disorders
- Pediatric Hepatobiliary Diseases and Treatments
- Image Retrieval and Classification Techniques
- Bioinformatics and Genomic Networks
- Data Management and Algorithms
- Circular RNAs in diseases
- Microgrid Control and Optimization
- Customer churn and segmentation
- Advanced Computing and Algorithms
- Electric Vehicles and Infrastructure
- Pancreatic and Hepatic Oncology Research
- MicroRNA in disease regulation
- Silkworms and Sericulture Research
- Expert finding and Q&A systems
South China University of Technology
2025
Southern University of Science and Technology
2024
Jinan University
2024
University of Electronic Science and Technology of China
2012-2023
Xinjiang University
2021-2023
Huzhou University
2021-2022
Southwest University
2013-2021
Chinese People's Liberation Army
2021
Shenzhen Institutes of Advanced Technology
2020
174th hospital of the People's Liberation Army
2018
The Taming of the Silkworm Silkworms, Bombyx mori , represent one few domesticated insects, having been over 10,000 years ago. Xia et al. (p. 433 published online 27 August) sequenced 29 domestic and 11 wild silkworm lines identified genes that were most likely to be selected during domestication. These those enhance silk production, reproduction, growth. Furthermore, silkworms probably only once from a large progenitor population, rather than on multiple occasions, as has observed for other animals.
Power batteries play a vital role in electric vehicle (EV) industry. To evaluate their charging and discharging performance achieve energy recovery, power accumulator battery testing system (PABTS) based DC-microgrid (DC-MG) is proposed. However, during testing, frequent current test may endanger the stability of PABTS DC-MG. Although, traditional virtual inertia control (VIC) approach can stabilize DC-bus voltage, its anti-interference ability still limited. solve this problem, an active...
Several technical indicators have been proposed to assess the impact of authors and institutions. Here, we combine h-index PageRank algorithm do away with some individual limitations these two indices. Most importantly, aim take into account value differences between citations-evaluating citation sources by defining using score rather than citations. The resulting PR-index is then constructed evaluating source popularity as well publication authority. Extensive tests on available collections...
With the rapid growth of Internet and overwhelming amount information that people are confronted with, recommender systems have been developed to effectively support users' decision-making process in online systems. So far, much attention has paid designing new recommendation algorithms improving existent ones. However, few works considered different contributions from users performance a system. Such studies can help us improve efficiency by excluding irrelevant users. In this paper, we...
In some recommender systems where users can vote objects by ratings, the similarity between be quantified a benchmark index, namely Pearson correlation coefficient, which reflects rating correlations. Another alternative way is to calculate based solely on relevance information, whether user has voted an object. The former one uses more information than latter, and intuitively expected give accurate predictions under standard collaborative filtering framework. However, according extensive...
Recommender systems are becoming a popular and important set of personalization techniques that assist individual users with navigating through the rapidly growing amount information. A good recommender system should be able to not only find out objects preferred by users, but also help in discovering their personalized tastes. The former corresponds high accuracy recommendation, while latter diversity. big challenge is design an algorithm provides both highly accurate diverse...
The gene therapy attracted more and attention for the tumor therapy. To obtain a safe system, new vectors beyond virus were developed high efficiency. ultrasound mediated was safer plasmid DNA could be delivered by microbubbles combined with to increase transfection In this work, cationic decorated Cyclo(Cys-Arg-Gly-Asp-Lys-Gly-Pro-AspCys) (iRGD peptides) magnetic Fe3O4 nanoparticles (MBiM) designed targeted contrast imaging guided of tumors. image intensity dramatically enhanced at site...
In a DC-microgrid (DC-MG) composed of power accumulator battery test system (PABTS), owing to the low inertia DC capacitance, charging and discharging PABTS can easily cause DC-link voltage fluctuations, which may jeopardize stability. Hence, virtual control (VIC) strategy is proposed suppress these fluctuations enhance stability DC-MG. The VIC method realized in bidirectional grid-connected converter (BGCC), combines model predictive (MPC). provide support during transient state dynamic...
Electric vehicle (EV) has been widely used in our life, one of the key technologies is batteries, power accumulator battery test system (PABTS), which initiated for evaluating performance EV many battery-manufacture companies. The parallel operation PABTS forms a dc-microgrid, owing to low inertia dc-link capacitance, charging and discharging tests batteries can easily cause dc-bus voltage fluctuations, may jeopardize stability. To increase achieve good stability, fractional-order...
In the era of big data, available information on Internet has overwhelmed human processing capabilities in some commercial applications. Recommendation techniques are indispensable to predict user ratings items terms historical data and deal with overload. many applications, problem sparsity usually results overfitting fails give desirable performance. Therefore, works have started investigate cross-domain recommendation overcome challenge. However, it is not trivial. this paper, we propose...
Papilla with hooknose or long protruding shape may increase the difficulty of cannulation during endoscopic retrograde cholangiopancreatography (ERCP). However, relationship between papilla anatomy and complications ERCP has not been fully understood. We aimed to investigate effect major duodenal morphology on post-ERCP pancreatitis (PEP) procedure cannulation.Patients native who underwent were recruited this multicenter study. Papilla-related variables collected, including length axis (L),...
With the rapid growth of Internet and overwhelming amount information choices that people are confronted with, recommender systems have been developed to effectively support users' decision-making process in online systems. However, many recommendation algorithms suffer from data sparsity problem, i.e. user-object bipartite networks so sparse cannot accurately recommend objects for users. This problem makes well-known perform poorly. To solve we propose a algorithm based on semi-local...
Fire detection and monitoring systems based on machine vision have been gradually developed in recent years. Traditional centralized deep learning model training methods transfer large amounts of video image data to the cloud, making privacy confidentiality difficult. In order protect fire system with heterogeneous enhance its efficiency, this paper proposes an improved federated algorithm incorporating computer vision: FedVIS, which uses a dropout gradient selection reduce communication...
Collaborative filtering is one of the most successful recommendation techniques, which can effectively predict possible future likes users based on their past preferences. The key problem this method how to define similarity between users. A standard approach using correlation ratings that two give a set objects, such as Cosine index and Pearson coefficient. However, costs computing kind indices are relatively high, thus it impossible be applied in huge-size systems. To solve problem, paper,...
In this paper, we propose a new synchronization-inspired co-clustering algorithm by dynamic simulation, called CoSync, which aims to discover biologically relevant subgroups embedding in given gene expression data matrix. The basic idea is view matrix as dynamical system, and the weighted two-sided interactions are imposed on each element of from both aspects genes conditions, resulting values all co-cluster synchronizing together. Experiments show that our allows uncovering high-quality...
Up to now, more and social media sites have started allow their users build the relationships. Take Last.fm for example (which is a popular music-sharing site), can not only add each other as friends, but also join interest groups that include people with common tastes. Therefore, in this environment, might be interested receiving item recommendations, friend recommendations whom they consider putting contact list, group may joining in. To support such needs, paper, we propose generalized...
Recommender systems are designed to effectively support individuals' decision-making process on various web sites. It can be naturally represented by a user-object bipartite network, where link indicates that user has collected an object. Recently, research the information backbone attracted researchers' interests, which is sub-network with fewer nodes and links but carrying most of relevant information. With backbone, system generate satisfactory recommenda- tions while saving much...
Recommender systems are designed to assist individual users navigate through the rapidly growing amount of information. One most successful recommendation techniques is collaborative filtering, which has been extensively investigated and already found wide applications in e-commerce. challenges this algorithm how accurately quantify similarities user pairs item pairs. In paper, we employ multidimensional scaling (MDS) method measure between nodes user-item bipartite networks. The MDS can...