检索结果-内蒙古大学图书馆

Efficient multi-objective particle swarm optimisation based ranking system for cloud service selection

IET COMMUNICATIONS 2019年第3期13卷 297-304页

作者： Kunhambu, Dileep Varapravathu Balan, Rathnamani Vijayalakshmi Siva Noorul Islam Univ Dept Comp Sci & Engn Kumaracoil Tamil Nadu India Noorul Islam Univ Dept Comp Applicat Kumaracoil Tamil Nadu India

Cloud computing knowledge achieves the prominent role in elaborating the systems and distributing the applications throughout the internet. Currently, in a cloud computing environment, expedient service selection is essential, since cloud users dependably have assorted sorts of applications with various quality necessities. The cloud service ranking has four phases: receiving user's requirement, estimating the quality of service (QoS) attributes by monitoring, selecting candidate services and service ranking. Previously, a cloud service ranking based on QoS attributes employs both essential and non-essential requirements and both objective and subjective assessments. Existing cloud service ranking system experiences multifaceted nature issues. In order to overcome these issues the authors' proposed technique is introduced. Their system comprises of three stages which are screening, optimal pseudo services and clustering process. In the Screening, the appropriate candidate's services are selected. In the wake of screening, candidate's services are optimally chosen to utilisean enhanced multi-objective particle swarm optimisation algorithm. Finally, for the purpose of ranking the selected candidate's services are clustered by hierarchical clustering algorithm and pick the best services. The proposed technique is actualised in JAVA with CloudSim.

关键词： particle swarm optimisation cloud computing pattern clustering quality of service cloud users candidate services nonessential requirements cloud service ranking system optimal pseudoservices multiobjective particle swarm optimisation algorithm selected candidate cloud service selection cloud computing knowledge cloud computing environment service selection quality of service attributes QoS attributes JAVA CloudSim

来源：评论

学校读者我要写书评

暂无评论

Multi-objectives optimisation of features selection for the classification of thyroid nodules in ultrasound images

引用

IET IMAGE PROCESSING 2020年第9期14卷 1901-1908页

作者： Aboudi, Noura Guetari, Ramzi Khlifa, Nawres Univ Tuins El Manar Higher Inst Med Technol Tunis Lab Biophys & Med Technol Tunis 1006 Tunisia Univ Tuins El Manar Higher Inst Comp Sci Tunis LIMTIC Lab Ariana 2080 Tunisia

Ultrasound (US) imaging is the leading diagnostic method for assessing the early-stage thyroid nodule. However, the visual evaluation of nodules can be influenced by the subjectivity of radiologists' interpretations. Computer-aided Diagnostic (CAD) systems can be useful in classifying these nodules according to their benign or malignant nature. The extraction of the characteristics, which relate in the author's case to the US of thyroid nodules, is essential in the differentiation of these nodules. The complex nature of images, however, generates a significant number of features, many of which are either redundant or irrelevant. This study presents a new CAD system that has been developed to categorise thyroid nodules. In this survey, 447 US images of thyroid nodules were retained. These images were used to extract features using statistical features extraction methods. A feature selection method based on the multi objective particle swarm optimisation algorithm was used to choose the most relevant and non-redundant ones. Then, support vector machine (SVM) and random forests (RFs) were applied to classify these nodules. 10-fold cross-validation was used to assess the classification performance metrics. Their proposed CAD has reached a maximum accuracy of 94.28% for SVM;and 96.13% for RF using the contour-based ROI.

关键词： CAD biomedical ultrasonics feature extraction pattern classification image classification support vector machines cancer medical image processing biological organs image texture particle swarm optimisation multiobjectives optimisation features selection thyroid nodules ultrasound images ultrasound imaging leading diagnostic method early-stage thyroid nodule computer-aided diagnostic systems benign nature malignant nature 447 US images statistical features extraction methods feature selection method multiobjective particle swarm optimisation algorithm benign nodules malignant nodules

来源：评论

学校读者我要写书评

暂无评论

Expected security constrained reactive power planning

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2016年第10期10卷 2306-2315页

作者： Karami-Horestani, AliReza Golshan, Mohammad Esmail Hamedani Monsef, Hassan Isfahan Univ Technol Dept Elect & Comp Engn Esfahan *** Iran Univ Tehran Sch Elect & Comp Engn Tehran Iran

The adequate reactive power resources are expected to maintain system integrity under both normal and post contingency operations. Nowadays, the power systems are leading to high-risk operating points, hence, the number of probable contingencies, which should be considered in security constrained reactive power planning (SCRPP), has widely increased. However, considering a large number of contingencies in SCRPP is not practically possible. This study presents an index named expected violation index to consider numerous contingencies in SCRPP. At first, a multi-objective algorithm for the proposed expected SCRPP approach is presented. This novel algorithm uses the probability of each contingency to invest on them more efficiently. Next, it presents a method for selecting candidate buses to install reactive power resources. Then, the effectiveness of the proposed method is analysed using a multi-objective particle swarm optimisation algorithm on IEEE 30-bus test system. Finally, a reliability-based quantitative method is presented for selecting among final Pareto optimal solution. Using the proposed method, the system designers are capable to consider a large number of contingencies in their SCRPPs, to invest more purposefully in reactive power equipment, and to select their most appropriate option among different feasible choices in the optimal Pareto solution.

关键词： power system security reactive power power system planning probability busbars particle swarm optimisation power system reliability Pareto optimisation security constrained reactive power planning reactive power resource high-risk operating point expected violation index expected SCRPP approach contingency probability bus selection multiobjective particle swarm optimisation algorithm IEEE 30-bus test system reliability-based quantitative method Pareto optimal solution reactive power equipment

来源：评论

学校读者我要写书评

暂无评论

MOPSO/FDMT-based Pareto-optimal solution for coordination of overcurrent relays in interconnected networks and multi-DER microgrids

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2018年第12期12卷 2871-2886页

作者： Baghaee, Hamid Reza Mirsalim, Mojtaba Gharehpetian, Gevork B. Talebi, Heidar Ali Amirkabir Univ Technol Dept Elect Engn Tehran Iran

The minimisation of discrimination time between main and backup overcurrent (OC) relays is one of the most important issues in power system relays coordination. On account of the massive computation burden and complexities for determining power system breakpoint, the implementation of the previously reported OC protection methods in large interconnected networks is almost impossible or at least cumbersome. In this regard, a variety of optimisation algorithms have been presented for coordination between relays and finding optimal operation time (OT) of the protection system. The previously reported single-objective optimisation algorithms have some limitations/drawbacks regarding OT of relays and their coordination. In this study, a new multi-objective optimisation algorithm is presented for coordination of OC relays in interconnected networks, based on multi-objective particle swarm optimisation (MOPSO) and fuzzy decision-making tool (FDMT). Then, using some useful assumption and recommendations of IEC-6090 and fault calculations for the microgrids including distributed energy resources, the proposed method is generalised for OC relay coordination in microgrids. Finally, the proposed method has been successfully implemented on different test systems and the obtained results have been compared with other reported methods to prove accuracy, authenticity, and efficiency of the MOPSO/FDMT-based protection and relay coordination algorithm.

关键词： Pareto optimisation overcurrent protection relay protection power system interconnection distributed power generation particle swarm optimisation decision making fuzzy set theory minimisation power generation faults fault diagnosis MOPSO FDMT-based Pareto-optimal solution overcurrent relay coordination algorithm interconnected network multiDER microgrid discrimination time minimisation OC relay coordination algorithm power system relay coordination optimal operation time OT single-objective optimisation algorithm multiobjective particle swarm optimisation algorithm fuzzy decision-making tool IEC-6090 standard fault calculation distributed energy resource

来源：评论

学校读者我要写书评

暂无评论

Prediction-based PSO algorithm for MIMO radar antenna deployment in dynamic environment

引用

JOURNAL OF ENGINEERING-JOE 2019年第20期2019卷 6646-6650页

作者： Wang, Ziqin Zhang, Tianxian Kong, Lingjiang Cui, Guolong Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu Sichuan Peoples R China

Under the circumstance of simultaneously scanning multiple regions in an environment which can change as time goes by, the authors study an optimal algorithm to solve antenna deployment problem for MIMO radar systems here. It is solved by multi-objective particle swarm optimisation algorithm (MOPSO) combining an autoregressive (AR) prediction model (MOPSO-AR). In a time period and dynamic environment, the MOPSO-AR method uses the previous optimal information to calculate the current deployment schemes before PSO optimisation starts up. It greatly reduces computational load and the error of the solutions. First, by discretising the time period into several time intervals, the problem in each time interval can be seen as a static problem. However, there may be relationship between these time intervals. Second, use the previous information and an AR model to predict temporally optimal solutions. Then, to get the exact optimal solutions, the predicted solutions and PSO method was applied to compute. Simulations show that the prediction strategy improves algorithm performance.

关键词： MIMO radar particle swarm optimisation radar antennas optimisation autoregressive prediction model multiobjective particle swarm optimisation algorithm MIMO radar systems antenna deployment problem optimal algorithm multiple regions MIMO radar antenna deployment prediction-based PSO algorithm prediction strategy PSO method predicted solutions exact optimal solutions temporally optimal solutions previous information static problem time interval time period PSO optimisation current deployment schemes previous optimal information MOPSO-AR method dynamic environment

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：