检索结果-内蒙古大学图书馆

14th international conference on High Performance computing and Simulation, HPCS 2016

作者： Tardivo, María Laura Caymes-Scutari, Paola Bianchini, Germán Méndez-Garabetti, Miguel Cortés, Ana Mendoza Argentina Spain Córdoba Argentina High Performance Computing Applications for Science and Engineering Research Group Universitat Autònoma de Barcelona Spain

ISBN: (纸本)9781509020881

Wildland fires at any location are a result of complex interactions between fuel, forest structure, topography, ignitions and weather conditions. Therefore, there is great interest in the development of computational tools for the prediction of these interactions during a wildland fire. A computational model that attempts to predict the spread of flames must provide a representation of the evolution of the fire over time. However, modelling any natural phenomenon is a difficult task, because models present a series of restrictions due to the need for a large number of input parameters. Moreover, there exist a degree of uncertainty in the input parameter values due to an inability to measure them in real time. To overcome this drawback and improve the quality of the prediction, several methods have been developed. This work presents a comparison of three methods for the reduction of uncertainty in the input parameter values, applied to the prediction of wildland fire behaviour. The three methods uses Parallel Evolutionary Algorithms to guide the search, Statistics to calibrate the results, and Parallelism to enhance the search in time and space terms. © 2016 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An Ensembled grid based Machine Learning Approach For PD Classification From MRI Images 4

An Ensembled Grid based Machine Learning Approach For PD Cla...

引用

4th international conference on Advances in Electrical, computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Redhya, M. Jayalakshmi, M. Kalasalingam Academy of Research and Education Department of Computer Applications Tamil Nadu India Kalasalingam Academy of Research and Education School of Computing Department of Computer Science and Engineering Tamil Nadu India

ISBN: (纸本)9798350343670

Parkinson's disease (PD) is a neuro-degenerative disease caused due to breakdown of brain cells in the central-part of the nervous system. As symptoms of PD appear only after 60% or more of these cells are destroyed, early detection is a tedious task. Several studies have proven that PD can be effectively diagnosed from MR-Images (MRI). This paper provides an ensembled machine learning model, Stacked-EG model, for MRI-image based PD classification. The dataset was obtained from PPMI (Parkinson's Progression Markers Initiative) online repository which included 134 PD subjects (80 males and 54 females) and 126 healthy patients (60 males and 66 females) around 60 years old on average. Feature extraction is performed through the application of filters, including wavelet transformations and intensity-based enhancements. Feature selection is conducted using optimised XGBoost model's feature significance scores. For classification, a Stacking Classifier which combines the strengths of XGBoost, SVM, and a Random Forest classifier was used. The model obtained an accuracy of 98.41% in classifying PD from healthy controls. © 2024 IEEE.

关键词： gridSearch Optimization Magnetic Resonance Imaging (MRI) Random Forest Stacking SVM XGBoost

来源：评论

学校读者我要写书评

暂无评论

grid Interoperability at the Application Level Using SAGA

Grid Interoperability at the Application Level Using SAGA

引用

IEEE international conference on e-Science and grid computing

作者： Shantenu Jha Hartmut Kaiser Andre Merzky Ole Weidner Center for Computation and Technology Louisiana State University Baton Rouge LA USA Vrije University Amsterdam Netherlands

SAGA is a high-level programming abstraction, which significantly facilitates the development and deployment of grid-aware applications. The primary aim of this paper is to discuss how each of the three main components of the SAGA landscape - interface specification, specific implementation and the different adaptors for middleware distribution - facilitate application-level interoperability. We discuss SAGA in relation to the ongoing GIN Community Group efforts and show the consistency of the SAGA approach with the GIN Group efforts. We demonstrate how interoperability can be enabled by the use of SAGA, by discussing two simple, yet meaningful applications: in the first, SAGA enables applications to utilize interoperability and in the second example SAGA adaptors provide the basis for interoperability.

关键词： grid computing Application software USA Councils Middleware Computer networks Computer science Next generation networking Supercomputers Distributed computing

来源：评论

学校读者我要写书评

暂无评论

Facilitating Collaboration and Application Sharing with MAST and the Access grid Development Infrastructures

Facilitating Collaboration and Application Sharing with MAST...

引用

IEEE international conference on e-Science and grid computing

作者： Gareth Lewis S Mehmood Hasan Vassil N Alexandrov Martin T Dove Advanced Computing and Emerging Technology Centre School of Systems Engineering University of Reading UK Department of Earth Sciences University of Cambridge Cambridge UK

ISBN: (纸本)9781424430116

Multicast Application Sharing Tool (MAST) allows geographically distributed participants to share arbitrary legacy applications. MAST supports scalable group to group collaboration by using Multicast. It is being used within the eMinerals project to augment the Access grid functionality. In this paper we describe how MAST has taken advantage of the Node Service and Shared Application infrastructure provided by the Access grid Toolkit to facilitate flexible and convenient sharing of applications within the eMinerals Virtual Organisation.

关键词： Collaboration Collaborative work Collaborative tools Network servers grid computing Distributed computing Peer to peer computing Video sharing Videoconference Humans

来源：评论

学校读者我要写书评

暂无评论

The GRelC Portal: A Ubiquitous and Seamless Way to Manage grid Databases

The GRelC Portal: A Ubiquitous and Seamless Way to Manage Gr...

引用

IEEE international conference on Parallel and Distributed computing, applications and Technologies (PDCAT)

作者： Sandro Fiore Alessandro Negro Salvatore Vadacca Emanuele Verdesca Alessio Leone Giovanni Aloisio University of Salerno Lecce Italy Euro Mediterranean Centre for Climate Change Italy

grid portals are web gateways aiming at providing a pervasive and ubiquitous access in grid to computational resources, tools, instruments, datasets and metadata via standard Web protocols. Moreover, they provide enhanced problem solving capabilities to deal with modern, large scale scientific and engineering problems. Data grid management systems are becoming increasingly important in the context of the recently adopted service oriented paradigm. The grid relational catalog (GRelC) project is working towards ubiquitous, integrated, seamless and comprehensive grid database management solutions. This paper describes the GRelC Portal, a web based grid-enabled solution for grid-database access, management and integration built on top of the GRelC Data Access Service.

关键词： Portals grid computing Pervasive computing Instruments Access protocols Problem-solving Large-scale systems Context-aware services Relational databases Project management

来源：评论

学校读者我要写书评

暂无评论

3rd international conference on Cloud computing and Security, ICCCS 2017

3rd International Conference on Cloud Computing and Security...

引用

3rd international conference on Cloud computing and Security, ICCCS 2017

ISBN: (纸本)9783319685410

The proceedings contain 48 papers. The special focus in this conference is on Cloud computing and Security. The topics include: Coverless text information hiding method using the frequent words distance;Improved STDM watermarking using semantic information-based JND model;the categories of quantum information hiding protocol;coverless information hiding technology research based on news aggregation;SIEM based on big data analysis;Workload-Aware VM consolidation in cloud based on max-min ant system;parallel service selection method based on adaptive cloud model for mobile application;a Hybrid Artificial Bee Colony Algorithm to Solve Multi-objective Hybrid Flowshop in Cloud computing Systems;a group-based replica consistency schema for cloud storage;A New Universal Quantum Gates and Its Simulation on GPGPU;a multi-objective optimization scheduling method based on the improved differential evolution algorithm in cloud computing;a network calculus analysis for the baseband processing capacity in cloud radio access network;Live migration among cloudbased on MOOSE address;achieving proof of shared ownership for the shared file in collaborative cloud applications;design and test of the intelligent rubber tapping technology evaluation equipment based on cloud model;an affective computing and fuzzy logic framework to recognize affect for cloud-based e-learning environment using emoticons;cloud management systems and virtual desktop infrastructure load balancing algorithms -A survey;design and deployment of wireless sensor networks for flood detection in Indonesia;an android app recommendation approach by merging network traffic cost;A virtual grid-based routing protocol for mobile sink-based WSNs;data hiding-based video error concealment method using compressed sensing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of a SNAP-based grid resource broker

Performance evaluation of a SNAP-based grid resource broker

引用

international conference on Formal Techniques for Networked and Distributed Systems, FORTE 2004 held in conjuction with 1st international Workshop on Theory Building and Formal Methods in Electronic/Mobile Commerce, TheFormEMC 2004, 1st European Performance Engineering Workshop, EPEW 2004 and 1st international Workshop on Integration of Testing Methodologies, ITM 2004

作者： Gourlay, Iain Haji, Mohammed Djemame, Karim Dew, Peter School of Computing University of Leeds LeedsLS2 9JT United Kingdom

ISBN: (纸本)9783540302339

Resource brokering is an essential component in building effective grid systems. The paper discusses the performance evaluation of a broker that is designed within the SNAP (Service Negotiation and Acquisition Protocol) framework and focuses on applications that require resources on demand. The performance evaluation is carried out using a combination of mathematical modelling and simulation. Initial results are presented, indicating that the simulation and modelling are in good agreement. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

On data analysis in forest fire induced breakdown of the transmission line 2nd

On data analysis in forest fire induced breakdown of the tra...

引用

2nd international conference on Intelligent and Interactive Systems and applications, IISA 2017

作者： Zhang, Jiaqing Zhang, Bosi Xie, Hui Fan, Minghao Wang, Liufang State Grid Anhui Electric Power Research Institute Hefei230601 China Department of Safety Engineering China University of Labor Relations Beijing100048 China Anhui Province Key Laboratory of Electric Fire and Safety Protection Hefei230022 China State Grid Laboratory of Fire Protection for Transmission and Distribution Facilities Hefei230022 China

ISBN: (纸本)9783319690957

The forest fire is one of the great threats to the operation of transmission line. The reasons and prevent measures of forest fire induced breakdown of the transmission line were investigated, and the application of data analysis in this field was discussed in the present study. According to the data statistics on the forest fire induced breakdown of the transmission line, the occurrence of transmission line trip has apparent time and space rules. The flow chart of big data analysis on transmission line breakdown induced by forest fires with the data analysis was proposed. By using big data analysis, important information can be derived, which is helpful to the design of early-warning system, as well as the proper strategic decisions to control the damage of transmission line in forest fires. © 2018, Springer international Publishing AG.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Grouped federated learning for time-sensitive tasks in industrial IoTs

引用

PEER-TO-PEER NETWORKING AND applications 2024年第2期17卷 819-833页

作者： Hao, Jiangshan Zhang, Linghao Zhao, Yanchao Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Jiangjun Ave Nanjing 211106 Jiangsu Peoples R China State Grid Sichuan Elect Power Res Inst Power Internet Things Key Lab Jinhui West Second St Chengdu 610094 Sichuan Peoples R China

The Industrial Internet of Things (IoT) is a crucial part of Industry 4.0 and constantly calls for intelligence to improve productivity. Meanwhile, the federated learning scheme has recently been proposed to provide both distributed learning ability and inherent privacy protection functions. Despite its original advantages, the unique features of industrial IoT posed several challenges to federated learning regarding efficiency and scalability. Due to the heterogeneity of data under IoT and the large difference in computing efficiency of each device, the training time of federated learning will be affected by stragglers. To this end, an effective device selection mechanism is urgently needed to improve the training efficiency of global model. Additionally, the communication coordination problem among various devices should be considered to accelerate global convergence. To solve the abovementioned problems, we proposed an Upper Confidence Bound (UCB)-based grouping federated learning (UGFL) where a data scheduling method effectively reduces the stragglers. We combined Lyapunov optimization with the UCB (Garivier and Moulines in international conference on Algorithmic Learning Theory, pp. 178-188, 2011) algorithm to design an efficient device selection method to choose the best device to participate in each global epoch. In addition, we theoretically analyzed the upper bound of convergence of our proposed method. Experimental results show that our method has higher accuracy and faster convergence speed than the existing methods.

关键词： Internet of things Federated learning Device selection Data scheduling

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Data Intensive Heterogeneous Task Scheduling Method Based on Parallel GATS-TS Algorithm 4

Large-Scale Data Intensive Heterogeneous Task Scheduling Met...

引用

4th international conference on Communications, Information System and Computer Engineering, CISCE 2022

作者： Xu, Xuelai Tian, Qingyang Xing, Yun Yin, Baolin Hu, Andong Zhiyang Innovation Technology Co. Ltd. Zibo China State Grid Liaoning Electric Power Company Limited Shenyang China State Grid Liaoning Electric Power Co. Ltd. Liaoyang Power Supply Company Liaoyang China

ISBN: (数字)9781665498487

ISBN: (纸本)9781665498487

Data-intensive applications need to process ever-increasing massive data, which puts forward high requirements on the performance of computing resources. Traditional scheduling methods can no longer adapt to the randomness of heterogeneous tasks, so a large-scale data-intensive heterogeneous task scheduling method based on parallel GATS-TS algorithm is proposed. According to the large-scale data task scheduling strategy, the tasks of the whole workflow are divided into various stages according to the data dependence, and then the task scheduling is carried out step by step. Large-scale data-intensive heterogeneous tasks are classified and the performance of each node is dynamically evaluated according to the different task types. According to the classification results of heterogeneous tasks, the completion time of tasks to be assigned at each stage was determined, and the scheduling model was established by using the parallel GATS-TS algorithm. The fitness function of the algorithm was the reciprocal of the completion time, and the model output the optimization results of intensive heterogeneous task scheduling. The test results show that the design method can shorten the task completion time and reduce the scheduling length ratio, and achieve good scheduling results under the condition of large number of tasks © 2022 IEEE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：