- Service-Oriented Architecture and Web Services
- Recommender Systems and Techniques
- Caching and Content Delivery
- Advanced Software Engineering Methodologies
- Semantic Web and Ontologies
- Web Data Mining and Analysis
- Software System Performance and Reliability
- Image Retrieval and Classification Techniques
- Advanced Computational Techniques and Applications
- Business Process Modeling and Analysis
- Topic Modeling
- Advanced Graph Neural Networks
- Cloud Computing and Resource Management
- Digital Marketing and Social Media
- Peer-to-Peer Network Technologies
- Consumer Market Behavior and Pricing
- Text and Document Classification Technologies
- Software Engineering Techniques and Practices
- IoT and Edge/Fog Computing
- Transportation Planning and Optimization
- Web Applications and Data Management
- Advanced Bandit Algorithms Research
- Advanced Image and Video Retrieval Techniques
- Software Engineering Research
- Multimodal Machine Learning Applications
Wuhan University
2016-2025
Southeast University
2025
Daqing Normal University
2025
China Railway Group (China)
2024
China International Engineering Design & Research Institute
2024
Fudan University
2024
Yunnan University
2023
Agricultural Information Institute
2012-2023
Chinese Academy of Agricultural Sciences
2012-2023
Northwest Normal University
2023
Advances in virtualization technology have focused mainly on strengthening the isolation barrier between virtual machines (VMs) that are co-resident within a single physical machine. At same time, large category of communication intensive distributed applications and software components exist, such as web services, high performance grid applications, transaction processing, graphics rendering, often wish to communicate across this with other endpoints VMs. State art inter-VM mechanisms do...
Most of existing e-commerce recommender systems aim to recommend the right product a user, based on whether user is likely purchase or like product. On other hand, effectiveness recommendations also depends time recommendation. Let us take who just purchased laptop as an example. She may replacement battery in 2 years (assuming that laptop's original often fails work around time) and new another years. In this case, it not good idea after laptop. It could hurt user's satisfaction system if...
With the broad adoption of service-oriented architecture, many software systems have been developed by composing loosely-coupled Web services. Service discovery, a critical step building service-based (SBSs), aims to find set candidate services for each functional task be performed an SBS. The keyword-based search technology adopted existing service registries is insufficient retrieve semantically similar queries. Although semantics-aware discovery approaches proposed, they are hard apply in...
As service-oriented computing (SOC) technologies gradually mature, developing service-based systems (such as mashups) has become increasingly popular in recent years. Faced with the rapidly increasing number of Web services, recommending appropriate component services for developers on demand is a vital issue development mashups. In particular, since new mashup to develop contains no it "user" service recommender system. To address this cold-start problem, we propose multiplex...
Tenure is a critical factor for an individual to consider when making job transition. For instance, software engineers make transition senior in span of 2 years on average, or it takes approximately 3 realtors switch brokers. While most existing work recommender systems focuses finding what recommend user, this paper places emphasis appropriate recommendations and its impact the item selection context system. The approach we propose, however, general can be applied any recommendation...
In this paper, we design a recommender system for the post-purchase stage, i.e., after user purchases product. Our method combines both behavioral and content aspects of recommendations. We first find most related categories active product in stage. Among these categories, products with high relevance are recommended to user. addition, our algorithm considers temporal factor, purchase time recommendation time. apply on random sample data from eBay. Comparing baseline item-based collaborative...
With the rapid development of service-oriented computing, a large number software applications have been developed based on services computing framework. It is well known that engineering knowledge-intensive activity, and thus effective management service-related knowledge facilitates development. Although many methodologies proposed for management, little attention has paid to mining (especially domain-specific functionalities) from service resources. To address this issue, we propose an...
Autoscaling is critical for ensuring optimal performance and resource utilization in cloud applications with dynamic workloads. However, traditional autoscaling technologies are typically no longer applicable microservice-based due to the diverse workload patterns complex interactions between microservices. Specifically, propagation of anomalies through leads a high number abnormal microservices, making it difficult identify root bottlenecks (PBs) formulate appropriate scaling strategies. In...
Recommending API sequences is crucial in software development, saving developers time and effort. While previous studies primarily focus on accuracy, often recommending popular APIs, they tend to overlook less frequent, or ‘tail,’ APIs. This oversight, a result of limited historical data, consequently diminishes the diversity recommender systems. In this paper, we propose DDASR, framework for containing both tail To accurately capture developer intent, utilize recent Large Language Models...
<div class="section abstract"><div class="htmlview paragraph">High-speed railway (HSR) hubs play a pivotal role in the integrated transport system, efficiently connecting various modes of and facilitating integration. Characterized by their large scale, complex functional spatial layouts, diverse interchange types, these see growing proportion passenger traffic annually. Thus, studying impedance high-speed is crucial for enhancing efficiency service quality. However, current...
Non-ribosomal peptide synthetases (NRPSs) are key enzymes in pharmaceutical synthesis, with condensation (C) domains catalyzing amide bond formation between aminoacyl substrates. However, recent research has elucidated that the catalytic capabilities of C extend beyond traditional bonds. In this study, we elucidate cyclization mechanism NRPS-derived natural products hangtaimycin (HTM), characterized by a 2,5-diketopiperazine (DKP) moiety which involves an intramolecular vinylamide-mediated...
Abstract Non‐ribosomal peptide synthetases (NRPSs) are key enzymes in pharmaceutical synthesis, with condensation (C) domains catalyzing amide bond formation between aminoacyl substrates. However, recent research has elucidated that the catalytic capabilities of C extend beyond traditional bonds. In this study, we elucidate cyclization mechanism NRPS‐derived natural products hangtaimycin (HTM), characterized by a 2,5‐diketopiperazine (DKP) moiety which involves an intramolecular...
The automatic identification and three-dimensional reconstruction of house plans has emerged as a significant research direction in intelligent building smart city applications. Three-dimensional models reconstructed from two-dimensional floor provide more intuitive visualization for safety assessments spatial suitability evaluations. To address the limitations existing public datasets—including low quality, inaccurate annotations, poor alignment with residential architecture...
Traditional recommendation algorithms often select products with the highest predicted ratings to recommend. However, earlier research in economics and marketing indicates that a consumer usually makes purchase decision(s) based on product's marginal net utility (i.e., minus product price). Utility is defined as satisfaction or pleasure user u gets when purchasing corresponding product. A rational chooses order maximize total utility. In contrast rating, of depends user's history changes...
The integration of deep learning techniques in pediatric neuroimaging has shown significant promise advancing various aspects the field. This paper provides a comprehensive exploration applications neuroimaging, focusing on image processing and reconstruction, segmentation classification, brain abnormalities detection, development maturation analysis. It discusses key deep-learning their relevance neuroimaging. also addresses challenges limitations such as lack standardization, ethical...
Networked software, a special kind of applications in service-oriented computing and ultra-large-scale systems, is complex software system deploying on network environment. Requirements engineering networked poses many problems owing to the dynamic topology structure, users' uncertainty, continuous growing requirements. Towards these problems, unified requirements meta-modeling frame for named RGPS proposed by merging functional nonfunctional Particularly, two kinds requirements, context...
Web services have attracted much attention from distributed application designers and developers because of their roles in abstraction interoperability among heterogeneous software systems, a growing number applications been published as on the Internet. Faced with increasing numbers service users, researchers computing field attempted to address challenging issue, i.e., how quickly find suitable ones according user queries. Many previous studies reported towards this direction. In paper,...