A5016100324- Cloud Computing and Resource Management
- IoT and Edge/Fog Computing
- Caching and Content Delivery
- Software System Performance and Reliability
- Data Visualization and Analytics
- Scientific Computing and Data Management
- Metabolomics and Mass Spectrometry Studies
- Distributed and Parallel Computing Systems
- Graph Theory and Algorithms
- Peer-to-Peer Network Technologies
- Robotics and Sensor-Based Localization
- Advanced Image and Video Retrieval Techniques
- Corporate Social Responsibility Reporting
- Bioinformatics and Genomic Networks
- Network Security and Intrusion Detection
- Cancer Genomics and Diagnostics
- Cloud Data Security Solutions
- Gene expression and cancer classification
- Multimodal Machine Learning Applications
- Radiomics and Machine Learning in Medical Imaging
- Anomaly Detection Techniques and Applications
- RNA Research and Splicing
- Parallel Computing and Optimization Techniques
Huazhong University of Science and Technology
2021
European Bioinformatics Institute
2016-2019
Imperial College London
2011-2014
Virtual machine (VM) based virtual infrastructure has been adopted widely in cloud computing environment for elastic resource provisioning. Performing management using VMs, however, is a heavyweight task. In practice, we have identified two scenarios where VM less feasible and resource-efficient. this paper, propose lightweight model that called Elastic Application Container (EAC). EAC unit delivering better efficiency more scalable applications. We describe the system architecture...
Resource provisioning based on virtual machine (VM) has been widely accepted and adopted in cloud computing environments. A key problem resulting from using static scheduling approaches for allocating VMs different physical machines (PMs) is that resources tend to be not fully utilised. Although some existing reconfiguration algorithms have developed address the problem, they normally result high migration costs low resource utilisation due ignoring multi-dimensional characteristics of PMs....
High-throughput transcriptomic data generated by microarray experiments is the most abundant and frequently stored kind of currently used in translational medicine studies. Although supported warehouses such as tranSMART, when querying relational databases for hundreds different patient gene expression records queries are slow due to poor performance. Non-relational models, key-value model implemented NoSQL databases, hold promise be more performant solutions. Our motivation improve...
Improving the performance of corporate social responsibility (CSR) is often contemplated in terms quality improvement taking CSR. In this context, measuring CSR viewed as a foundational step. Given qualitative essence CSR, improving should extend beyond measurement performance—quantitative metrics. Nevertheless, within academic discourse, there notable absence methodologies for evaluating alongside measurement. This paper aims to develop framework by treating service directed towards various...
An Infrastructure-as-a-Service (IaaS) provider is usually assumed to own a large data centre with significant computational resources. For small or medium sized Internet Data Centre (IDC), offering cloud computing service nature of business model but there are technical barriers which need be resolved. One the key issues ineffective resource management given such an IDC has only limited resource. In this paper, we propose efficient solution specially designed for helping and IaaS providers...
Abstract Motivation Developing a robust and performant data analysis workflow that integrates all necessary components whilst still being able to scale over multiple compute nodes is challenging task. We introduce generic method based on the microservice architecture, where software tools are encapsulated as Docker containers can be connected into scientific workflows executed using Kubernetes container orchestrator. Results developed Virtual Research Environment (VRE) which facilitates...
Simplifying the process of deploying applications is almost essential in cloud. However, existing techniques can automate applications' initial deployment but have not yet adequately addressed their scaling problem. In this paper, a platform to enable novel dynamic technique introduced. This employs: (i) an extensible specification that describes all aspects applications, (ii) flexible analytical model determines how many servers be deployed for application each scaling. The platform's...
We present a novel security monitoring framework for intrusion detection in IaaS cloud infrastructures. The uses statistical anomaly techniques over data monitored both inside and outside each Virtual Machine instance. the architecture of our describe implementation real-time monitors detectors. also how is used three different attack scenarios. For scenarios, we itself works it could be detected. what conducted using methods. evaluation synthetic real sets. Our experimental across all...
The computing resource level architecture allows end-users to directly control its underlying computer resources, such as VM (virtual machine) operations, scaling, networking, etc. However, setting up and maintaining a working environment is complex time consuming for management also heavy-weight task the providers. In contrast, application automatically controls resources so that can concentrate on their core business. this paper, we propose new called Elastic Application Container (EAC)...
Developing a robust and performant data analysis workflow that integrates all necessary components whilst still being able to scale over multiple compute nodes is challenging task. We introduce generic method based on the microservice architecture, where software tools are encapsulated as Docker containers can be connected into scientific workflows executed in parallel using Kubernetes container orchestrator. The access point virtual research environment which launched on-demand cloud...
Abstract Motivation TranSMART has a wide range of functionalities for translational research and large user community, but it does not support imaging data. In this context, data typically includes 2D or 3D sets magnitude metadata information. Imaging may summarise complex feature descriptions in less biased fashion than defined plain texts numeric numbers. also is contextualised by other be analysed jointly with that can explain features their variation. Results Here we describe the...
Abstract Cross-view geo-localization aims to find images containing the same geographic target from obtained different platforms. The extreme viewpoint variations bring challenges this task. Existing methods usually focus on mining fine-grained features of targets in images, ignoring potential contextual information around them. In paper, we consider that background regions can be used as auxiliary information, which make image representation for more discriminative. Specifically, designed a...