A5100388627- Recommender Systems and Techniques
- Glycosylation and Glycoproteins Research
- Galectins and Cancer Biology
- Cloud Computing and Resource Management
- Blockchain Technology Applications and Security
- Cancer Mechanisms and Therapy
- Human Mobility and Location-Based Analysis
- Software System Performance and Reliability
- Software Engineering Research
- Service-Oriented Architecture and Web Services
- Advanced Software Engineering Methodologies
- Big Data and Digital Economy
- Advanced Bandit Algorithms Research
- Advanced Computational Techniques and Applications
- Graph Theory and Algorithms
- Caching and Content Delivery
- Enzyme Production and Characterization
- Topic Modeling
- Chronic Lymphocytic Leukemia Research
- IoT and Edge/Fog Computing
- Educational Technology and Assessment
- Software Testing and Debugging Techniques
- Advanced Decision-Making Techniques
- Advanced Database Systems and Queries
- Cognitive Computing and Networks
Chengdu University of Information Technology
2023-2025
Fudan University
2021-2024
Jilian Technology Group (China)
2023
Shandong Xiehe University
2023
Wuhan Business University
2023
University of Tsukuba
2023
Shanghai Polytechnic University
2022
Université de Rennes
2022
Centre National de la Recherche Scientifique
2022
Institut d'Électronique et des Technologies du numéRique
2022
To facilitate software maintenance and evolution, a helpful step is to locate features concerned in particular task. In the literature, both dynamic interactive approaches have been proposed for feature location. this paper, we present static non-interactive method achieving objective. The main idea of our approach use information retrieval (IR) technology reveal basic connections between computational units source code. Due characteristics retrieved connections, representation code named...
Studies on next point-of-interest (POI) recommendation mainly seek to learn users' transition patterns with certain historical check-ins. However, in reality, movements are typically uncertain (i.e., fuzzy and incomplete) where most existing methods suffer from the pattern vanishing issue. To ease this issue, we propose a novel interactive multi-task learning (iMTL) framework better exploit interplay between activity location preference. Specifically, iMTL introduces: (1) temporal-aware...
Existing studies on next point-of-interest (POI) recommendation mainly attempt to learn user preference from the past and current sequential behaviors. They, however, completely ignore impact of future behaviors decision-making, thus hindering quality learning. Intuitively, users' POI visits may also be affected by their multi-step behaviors, as users often have activity planning in mind. To fill this gap, we propose a novel Context-aware Future Preference inference Recommender (CFPRec) help...
Mycobacterial arabinogalactan (AG) is an essential cell wall component of mycobacteria and a frequent structural bio-synthetical target for anti-tuberculosis (TB) drug development. Here, we report that mycobacterial AG recognized by galectin-9 exacerbates infection. Administration AG-specific aptamers inhibits cellular infiltration caused Mycobacterium tuberculosis (Mtb) or bovis BCG, moderately increases survival Mtb-infected mice marinum-infected zebrafish. interacts with carbohydrate...
The uncertain check-ins bring challenges for current static next point-of-interest (POI) recommendation methods. Fortunately, the conversation-based has been shown merit of integrating immediate user preference more accurate recommendations. We, therefore, propose a adaptive relational translation (CART) approach POI over check-ins. It is equipped with recommender and conversation modules to interactively acquire users' preferences make dynamic Specifically, built upon method performs...
With the popularity of Web Services and Service-Oriented Architecture (SOA), quality assurance SOA applications, such as testing, has become a research focus. Programs implemented by Business Process Execution Language for (WS-BPEL), which can be used to compose partner into composite Services, are one popular kind applications. The unique features WS-BPEL programs bring new challenges testing. A test case testing program is sequence messages that received under test. Previous not studied...
Distributed interactive applications (DIAs) are networked systems that allow multiple participants at different locations to interact with each other. Wide spreads of client in large-scale DIAs often require geographical distribution servers meet the latency requirements applications. In distributed server architecture, network latencies involved interactions between clients directly affected by how assigned servers. this paper, we focus on problem assigning appropriate enhance their...
Most existing studies on next point-of-interest (POI) recommendation assume that users deliver certain check-ins over individual POIs. In reality, we typically obtain uncertain due to the presence of collective POIs, which are gathering places multiple POIs (e.g., shopping malls). On one hand, such hinder more accurate POI for transition vanishing issue; other poses challenge businesses select locate in complicated competition and cooperation relations between businesses. As such, these...
Current study on next point-of-interest (POI) recommendation mainly explores user sequential transitions with the fine-grained individual-user POI check-in trajectories only, which suffers from severe data sparsity issue. In fact, coarse-grained signals (i.e., region- and global-level check-ins) in such sparse check-ins would also benefit to augment preference learning. Specifically, our analysis unveils that movement exhibits noticeable patterns w.r.t. regions of visited POIs. Meanwhile,...
Under the cloud manufacturing environment, with increasing number of services, one issues needs to be resolved is find a service that meets users' demand. However, until now, there not an outstanding discovery mechanism help users appropriate solution among numerous existing services. In order realize services rapidly, efficiently and accurately match, multi-level intelligent matching method was proposed in this paper. This includes 3 parts: (1) describing model based on OWL (Ontology Web...
As one of the most concerned digital technologies in recent years, blockchain and distributed ledger technology are an important driving force for a new round technological development.It is currently process accelerating its evolution maturity, has gradually integrated with other technologies.It been applied many industries, providing decentralized solutions various realizing innovative storage models, building trust system.As officially incorporated into China's information infrastructure...
Deeper understanding of the crosstalk between host cells and Mycobacterium tuberculosis (Mtb) provides crucial guidelines for rational design novel intervention strategies against (TB). Mycobacteria possess a unique complex cell wall with arabinogalactan (AG) as critical component. AG has been identified virulence factor Mtb which is recognized by galectin-9. Here, we demonstrate that galectin-9 directly inhibited mycobacterial growth through AG-binding property carbohydrate-recognition...
Automated Program Repair (APR) helps improve the efficiency of software development and maintenance. Recent APR techniques use deep learning, particularly encoder-decoder architecture, to generate patches. Though existing DL-based approaches have proposed different encoder architectures, decoder remains be standard one, which generates a sequence tokens one by replace faulty statement. This has multiple limitations: 1) allowing syntactically incorrect programs, 2) inefficiently representing...
Blockchain technology has developed rapidly in recent years. Especially, China, it is included country's new information infrastructure. As one of the important digital technologies for China's economy, blockchain many applications financial industry, and development standards also been widely carried out. The four major international standardization organizations have achieved preliminary results, but there are still some problems at present. next step can be out from aspects: building a...
Sui Lutris is the first smart-contract platform to sustainably achieve sub-second finality. It achieves this significant decrease in latency by employing consensusless agreement not only for simple payments but a large variety of transactions. Unlike prior work, neither compromises expressiveness nor throughput and can run perpetually without restarts. safely integrating consensuless with high-throughput consensus protocol that invoked out critical finality path makes sure when transaction...
With the continually-increasing capability of computer hardware and scale software, complexity software is also continually increasing, has manifest itself as one key factors that limit significant improvement quality productivity.The structural complexity, especially high-level considered most important a system.How to control in efficient effective ways become critical issue for large-scale development Internet computing environment, which open, dynamic constantly changing.To resolve this...
Blockchain and Distributed Ledger Technology (DLT) are becoming important driving forces for a new round of scientific technological development. The construction blockchain information infrastructure has risen to national strategic height. industrial applications DLT developing landing rapidly. At present, it included many fields such as finance, government affairs justice. the same time, will have far-reaching impact on international scientific, economic For healthy orderly development...
Collaborative filtering is a popular tool for recommendation systems. However, collaborative technologies often suffer from high time complexity, the cold-start problem, and low coverage. Recent research shows that social networks trust-aware methods can effectively solve these proble ms. Therefore, we propose Trust Domain Expert Filtering system. First, divide user item rating matrix into multiple sub-matrices based on domain attributes of each item. For sub-matrix, then use experts to...
In order to improve the effect of software defect prediction, many algorithms including feature selection, have been proposed. Based on Wrapper and Filter hybrid framework, a feature-grouping-based selection algorithm is proposed in this paper. The composed two steps. first step, remove redundant features, we group features according redundancy between features. symmetry uncertainty used as constant indicator correlation FCBF-based grouping second subset are selected from each form final...
Standards are an important key to the success of developing technologies, and formulating right standards at time for technology development helps ensure ease use interoperability technology, blockchain is no exception. As has been officially incorporated into China's new information infrastructure category, application field expanded rapidly, gradually extending from financial government affairs other fields in real economy. The implementation inseparable open a complete standard system....
A code generation system generates programming language based on an input natural description. State-of-the-art approaches rely neural networks for generation. However, these generators suffer from two problems. One is the long dependency problem, where a element often depends another far-away element. variable reference, example, its definition, which may appear quite few lines before. The other problem structure modeling, as programs contain rich structural information. In this paper, we...
In view of the complex fault mechanism secondary device on intelligent substation, and traditional single index was difficult to mine potential risk equipment, according data that equipment can collect, this paper proposes a status assessment method based combination weighting cloud model. Firstly, comprehensive state indicator set is constructed, then weight each will be obtained by using AHP with anti-entropy theory. Finally, membership function replaced model for achieving evaluation...
Deeper understanding of the crosstalk between host cells and Mycobacterium tuberculosis (Mtb) provides crucial guidelines for rational design novel intervention strategies against (TB). Mycobacteria possess a unique complex cell wall with arabinogalactan (AG) as critical component. AG has been identified virulence factor Mtb which is recognized by galectin-9. Here we demonstrate that galectin-9 directly inhibited mycobacterial growth through AG-binding property carbohydrate-recognition...