A5055284175- Service-Oriented Architecture and Web Services
- IoT and Edge/Fog Computing
- Cloud Computing and Resource Management
- Caching and Content Delivery
- Business Process Modeling and Analysis
- Blockchain Technology Applications and Security
- Recommender Systems and Techniques
- Advanced Software Engineering Methodologies
- Software System Performance and Reliability
- Semantic Web and Ontologies
- Privacy-Preserving Technologies in Data
- Distributed and Parallel Computing Systems
- Context-Aware Activity Recognition Systems
- Web Data Mining and Analysis
- Software Engineering Research
- Advanced Database Systems and Queries
- Mobile Agent-Based Network Management
- Topic Modeling
- Age of Information Optimization
- Advanced Graph Neural Networks
- Distributed systems and fault tolerance
- Music and Audio Processing
- Advanced Data Storage Technologies
- Cloud Data Security Solutions
- Anomaly Detection Techniques and Applications
Zhejiang University
2016-2025
Zhejiang University of Science and Technology
2016-2025
Ningbo University
2023-2025
First Affiliated Hospital Zhejiang University
2020-2024
Sanya Central Hospital
2024
Sanya University
2023
Alibaba Group (China)
2019-2023
Hangzhou City University
2023
Hangzhou Dianzi University
2010-2023
TU Wien
2023
Edge Computing provides mobile and Internet-of-Things (IoT) app vendors with a new distributed computing paradigm which allows an vendor to deploy its at hired edge servers near users the of cloud. This way, can be allocated nearby minimize network latency energy consumption. A cost-effective user allocation (EUA) requires maximum served minimum overall system cost. Finding centralized optimal solution this EUA problem is NP-hard. Thus, we propose EUAGame, game-theoretic approach that...
With the emergence of online social networks, network-based recommendation approach is popularly used. The major benefit this ability dealing with problems cold-start users. In addition to user trust information also plays an important role obtain reliable recommendations. Although matrix factorization (MF) becomes dominant in recommender systems, largely relies on initialization and item latent feature vectors. Aiming at addressing these challenges, we develop a novel trust-based for...
The development of cloud computing and virtualization techniques enables mobile devices to overcome the severity scarce resource constrained by allowing them offload computation migrate several parts an application powerful servers. A device should judiciously determine whether as well what portion be offloaded cloud. This paper considers a offloading problem where multiple services in workflows can invoked fulfill their complex requirements makes decision on workflow offloaded. Due mobility...
Along with the rapid developments in communication technologies and surge use of mobile devices, a brand-new computation paradigm, Edge Computing, is surging popularity. Meanwhile, Artificial Intelligence (AI) applications are thriving breakthroughs deep learning many improvements hardware architectures. Billions data bytes, generated at network edge, put massive demands on processing structural optimization. Thus, there exists strong demand to integrate Computing AI, which gives birth...
The dramatically increasing of mobile applications make it convenient for users to complete complex tasks on their devices. However, the latency brought by unstable wireless networks and computation failures caused constrained resources limit development computing. A popular approach solve this problem is establish a service provisioning system based edge computing (MEC) paradigm. In MEC paradigm, plenty machines are placed at network so that performance can be optimized using involved...
Edge computing (EC) is now emerging as a key paradigm to handle the increasing Internet-of-Things (IoT) devices connected edge of network. By using services deployed on service provisioning system which made up servers nearby, these IoT are enabled fulfill complex tasks effectively. Nevertheless, it also brings challenges in trustworthiness management. The volatile environment will make difficult comply with service-level agreement (SLA), an important index declared by services. In this...
Abstract Background Anthocyanins are a group of natural products widely found in plants. They have been to alleviate the disorders glucose metabolism type 2 diabetes mellitus (T2DM), while underlying mechanisms remain unclear. Methods HepG2 and L02 cells were incubated with 0.2 mM PA 30 for 24 h induce IR, treated 5 used as control. C57BL/6 J male mice db/db fed chow diet gavaged pure water or cyanidin-3-O-glucoside (C3G) solution (150 mg/kg/day) 6 weeks. Results In this study, anthocyanin...
In this study, the authors propose a mobility-based clustering (MBC) protocol for wireless sensor networks with mobile nodes. proposed protocol, node elects itself as cluster-head based on its residual energy and mobility. A non-cluster-head aims at link stability cluster head during according to estimated connection time. Each is allocated timeslot data transmission in ascending order time division multiple address (TDMA) schedule steady-state phase, transmits sensed broadcasts joint...
The number of Web services on the Internet has been growing rapidly. This made it increasingly difficult for users to find right from a large functionally equivalent candidate services. Inspecting every service their quality value is impractical because very resource consuming. Therefore, problem prediction attracted lot attention in past several years, with focus application Matrix Factorization (MF) technique. Recently, researchers have started employ user similarity improve MF-based...
In modern commerce, both frequent changes of custom demands and the specialization business process require capacity modeling processes for enterprises effectively efficiently. Traditional methods improving modeling, such as workflow mining retrieval, still requires much manual work. To address this, based on structure a process, method called recommendation technique is proposed in this paper to provide designers with support automatically constructing new that under consideration. paper,...
Predicting the Quality of Service (QoS) values is important since they are widely applied to Service-Oriented Computing (SOC) research domain. Previous works on this problem do not consider influence user location information carefully, which we argue would contribute improving prediction accuracy due nature Web services invocation process. In paper, propose a novel collaborative QoS framework with location-based regularization (LBR). We first elaborate popular Matrix Factorization (MF)...
QoS as an important criterion has attracted more and attention in the service selection process. Various QoS-aware methods have been proposed recent years. However, few of them take into account correlations between services, causing several performance issues. can be defined that some attributes a are not only dependent on itself but also correlated to other services. Since such will affect values, it is study how select appropriate candidate services while taking when generating composite...
The advances in mobile technologies enable devices to perform tasks that are traditionally run by personal computers as well provide services the others. Mobile users can form a service sharing community within an area using their devices. This paper highlights several challenges involved building such compositions communities when both requesters and providers mobile. To deal with them, we first propose provisioning architecture named then composition approach utilizing Krill-Herd...
Fast charging stations are critical infrastructures to enable high penetration of plug-in electric vehicles (PEVs) into future distribution networks. They need be carefully planned meet demand as well ensure economic benefits. Accurate estimation PEV is the prerequisite such planning, but a nontrivial task. This paper addresses sizing (number chargers and waiting spaces) problem fast presents an optimal planning solution based on explicit temporal-state charge characterization demand. The...
As enterprises around the globe embrace globalization, strategic alliances among have become an important means to gain competitive advantages. Enterprises cooperate improve quality or lower prices of their services, which introduce correlations, i.e., a service is associated with other services. Existing approaches for composition not fully and systematically considered correlations between In this paper, we propose novel approach named Q <sup xmlns:mml="http://www.w3.org/1998/Math/MathML"...
With the development of medical technology, image semantic segmentation is great significance for morphological analysis, quantification and diagnosis human tissues. However, manual detection a time-consuming task. Especially biomedical image, only experts are able to identify tissues mark their contours. In recent years, deep learning has greatly improved accuracy computer automatic segmentation. This paper proposes network named Spatial-Channel Attention U-Net (SCAU-Net) based on current...
Multi-access edge computing (MEC) is booming as a promising paradigm to push the computation and communication resources from cloud network provide services perform computations. With container technologies, mobile devices with small memory footprint can run composite microservice-based applications without time-consuming backbone. Service placement at of importance put MEC theory into practice. However, current state-of-the-art research does not sufficiently take property consideration....
With the ever-increasing requirements of delay-sensitive and mission-critical applications, it becomes a popular research trend to incorporate edge computing in Internet Things (IoT) mitigate pressure traditional cloud-based IoT architecture. Edge delivers real-time computations communications for devices by leveraging servers deployed close users, which creates collaborative (CEC) paradigm. The capacity is beneficial but risky, as vulnerable can be exploited conduct surveillance or perform...
Abstract As one of the great survivors plant kingdom, barnyard grasses ( Echinochloa spp.) are most noxious and common weeds in paddy ecosystems. Meanwhile, at least two species have been domesticated cultivated as millets. In order to better understand genomic forces driving evolution toward weed crop characteristics, we assemble genomes three (allohexaploid E. crus-galli colona , allotetraploid oryzicola ) re-sequence 737 accessions millets from 16 rice-producing countries. Phylogenomic...
Machine learning (ML) is powering a rapidly-increasing number of web applications. As crucial part 5G, edge computing facilitates artificial intelligence (AI) by ML model training and inference at the network on servers. Compared with centralized cloud AI, AI enables low-latency which critical to many delay-sensitive applications, e.g., AR/VR, gaming Web-of-Things Existing studies focused resource performance optimization in inference, leveraging merely as tool accelerate processes. However,...