检索结果-内蒙古大学图书馆

IEEE 74th Vehicular Technology Conference (VTC)

作者： Ali, H. M. Ashrafinia, Saeed Liu, Jiangchuan Lee, Daniel C. Simon Fraser Univ Sch Engn Sci Burnaby BC V5A 1S6 Canada Simon Fraser Univ Sch Comp Sci Burnaby BC V5A1S6 Canada

ISBN: (纸本)9781424483273

The latest increase in mobile data usage and emergence of new applications such as Multimedia Online Gaming (MMOG), mobile TV and streaming contents have motivated advances in wireless broadband systems. Recently, the Long-Term Evolution (LTE) technology, which is based on the Universal Mobile Telecommunications System (UMTS) specifications, joins WiMAX as a competitor to achieve increasing demands of the broadband wireless access. Careful deployment of such a network is required to fulfill the high data rate demands with minimal cost of infrastructure and comprehensive coverage of the subscribers. In this paper, a multi-objective network planning problem is defined as utilizing the minimum number of infrastructure sites (i.e. Base Stations or eNode B in UMTS systems) while maximum number of users in service. We proposed a quantum inspired evolutionary algorithm (QIEA) in order to achieve optimized solution for this problem. The QIEA can be viewed as a probabilistic evolutionary algorithm and thus it is plausible to expect a reasonably good performance in solving combinatorial optimization problems. In this algorithm, each individual is represented by a string of Q-bits, where a Q-bit is the probabilistic representation inspired by the qubit concept in the quantum computing. Computational experiments show that our algorithm is fairly efficient to different scenarios of the network planning problem and performs better than the Genetic algorithm (GA).

关键词： facility location problem network planning quantum inspired evolutionary algorithm combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

quantum inspired High Dimensional Hyper-Parameter Optimization of Machine Learning Model

Quantum Inspired High Dimensional Hyper-Parameter Optimizati...

引用

International Smart Cities Conference (ISC2)

作者： Li, Yangyang Lu, Gao Zhou, Linhao Jiao, Licheng Xidian Univ Joint Int Res Lab Intelligent Percept & Computat Int Res Ctr Intelligent Percept & Computat Minist EducKey Lab Intelligent Percept & Image U Xian 710071 Shaanxi Peoples R China

ISBN: (纸本)9781538625248

The hyper-parameter optimization of machine learning model is not a completely solved problem. The exquisite combination of artificial tuning and grid search may be a good choice in the area where the dimension of hyper-parameters is very low. But for high-dimensional hyper-parameter optimization problems, artificial tuning and grid search are obviously helpless. In this paper, we propose a quantum inspired hyper-parameter search method, which employs a quantum inspired evolutionary algorithm integrated with the traditional neural network (NN) training technique to evolve a NN subject to accuracy on test set as the objective. We evaluate the proposed method on MNIST dataset and compare it with random search algorithm. Experimental results demonstrate the superiority of our proposed method.

关键词： quantum inspired evolutionary algorithm hyper-parameter optimization neural networks machine learning

来源：评论

学校读者我要写书评

暂无评论

A quantum-inspired evolutionary Approach for Non-Homogeneous Redundancy Allocation in Series-Parallel Multi-State Systems 10

A Quantum-Inspired Evolutionary Approach for Non-Homogeneous...

引用

10th International Conference on Reliability Maintainability and Safety

作者： Li, Yanfu Zio, Enrico Elect France Ecole Cent Paris Supelec European Fdn New Energy Chair Syst Sci & Energet Challenge Paris France

ISBN: (纸本)9781479966325

Redundancy allocation is a family of well-known reliability optimization problems. The non-homogeneous type of redundancy allocation in series-parallel multi-state systems is among the most difficult ones. evolutionary algorithms (EAs) are frequently applied to solve the problem, mainly due to the huge search space and the non-closed-form system reliability. This work proposes an efficient approach that combines a quantum-inspired evolutionary algorithm (QEA) with a newly designed local search strategy. Different from the existing EAs, it is able to evolve an explicit probabilistic model to explore the search space in an iterative way. The proposed method is tested on two benchmark problems with the comparisons to the published results. The results are promising in terms of both solution quality and computation efficiency.

关键词： parallel multi-state system redundancy allocation problem quantum inspired evolutionary algorithm local search

来源：评论

学校读者我要写书评

暂无评论

Fuzzy logic-based thermal generation scheduling strategy with solar-battery system using advanced quantum evolutionary method

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2014年第3期8卷 410-420页

作者： Chakraborty, Shantanu Ito, Takayuki Senjyu, Tomonobu Nagoya Inst Technol Dept Comp Sci & Engn Nagoya Aichi Japan Univ Ryukyus Fac Engn Nakagami Okinawa 9030213 Japan

This study presents a fuzzy logic-based strategy to solve thermal generation scheduling [namely unit commitment (UC)] problem integrated with an equivalent solar-battery system using quantum inspired evolutionary algorithm. Solar-battery system is included with this model as a measure of green-house effect. The crisp formulations of UC are modified utilising fuzzy logics, because of the inherent intermittency involved in solar energy integration and other uncertain variables. An evolutionary algorithm based on the concept and principle of quantum computation is applied to solve the resultant fuzzy logic-based UC problem. Conventional quantum evolutionary algorithm (QEA) is modified by incorporating a hierarchy-group oriented scheme to deal with the non-linear and multi-peak nature of the problem. QEA is further advanced facilitating some genetic algorithm operators and a new binary differential operator along with rotation operator with a redefined rotational angle look-up table. The probabilities of using such operators on individual solution(s) are fuzzified by defining membership function based on associated fitness of that individual. The fitness function is then determined by combining the objective function, penalty function and the aggregated fuzzy membership function. The proposed fuzzy logic-based QEA (FLQEA) is applied to UC problem in two different scaled power systems. Provided simulation results will show the effectiveness of FLQEA.

关键词： air pollution evolutionary computation fuzzy logic fuzzy set theory power generation scheduling quantum computing solar cells table lookup thermal power stations fuzzy logic-based thermal generation scheduling strategy advanced quantum evolutionary method equivalent solar-battery system quantum inspired evolutionary algorithm green-house effect solar energy integration quantum computation resultant fuzzy logic-based UC problem QEA hierarchy- group oriented scheme multipeak nature genetic algorithm operators redeflned rotational angle look-up table objective function penalty function aggregated fuzzy membership function scaled power systems FLQEA

来源：评论

学校读者我要写书评

暂无评论

Base Station and Relay Station Broadband Network Planning Using Immune quantum evolutionary algorithm

Base Station and Relay Station Broadband Network Planning Us...

引用

IEEE 78th Vehicular Technology Conference (VTC Fall)

作者： Ali, H. M. Oberoi, J. S. Liu, Jiangchuan Lee, Daniel Simon Fraser Univ Sch Engn Sci Burnaby BC V5A 1S6 Canada

ISBN: (纸本)9781467361873

In this paper, we present simultaneous planning technique for Base Stations (BSs) and Relay Stations (RSs) for a broadband wireless network while taking data flow also known as link flow into consideration. Infrastructure cost (BS cost, RS cost and their operational costs) of a wireless network proves to be a key factor for network service providers while planning a network. The objective of this study is to help determine the set of BSs and RSs that can serve all the subscribed users and fulfill their demands at the lowest cost to the utility firm. This problem setup can be used for laying new networks as well as enhancing the already existing ones. The combinatorial optimization problem at hand is NP-hard in nature. We formulate this problem as a non-linear discrete optimization problem and compare two recent evolutionary algorithms (EAs) in providing approximate solution to this problem. The quantum inspired evolutionary algorithm (QEA) is a probabilistic algorithm based on quantum computing with the concept of qubits and superposition of states. The Immune theory based Immune quantum evolutionary algorithm (IQEA) adopts immune operator to raise the fitness and prevent deterioration during the evolutionary process. Simulation results show better performance of IQEA as compared to QEA.

关键词： Link Rate Allocation quantum inspired evolutionary algorithm Immune Operator Base Station Relay Station

来源：评论

学校读者我要写书评

暂无评论

Base Station and Relay Station Broadband Network Planning Using Immune quantum evolutionary algorithm

Base Station and Relay Station Broadband Network Planning Us...

引用

IEEE Vehicular Technology Conference

作者： H. M. Ali J. S. Oberoi Jiangchuan Liu Daniel Lee Simon Fraser University Burnaby BC Canada School of Engineering Science School of Computing Science

ISBN: (纸本)9781467361866

关键词： Link Rate Allocation quantum inspired evolutionary algorithm Immune Operator Base Station Relay Station BASE STATION Relay stations evolutionary algorithm network service providers Wireless networks Broadband networks STATIONS Immunity data flow quantum computing Manufacturing costs quanta

来源：评论

学校读者我要写书评

暂无评论

Nuclear reactor reload using quantum inspired algorithm

引用

PROGRESS IN NUCLEAR ENERGY 2012年 55卷 40-48页

作者： Nicolau, Andressa dos Santos Schirru, Roberto Monteiro de Lima, Alan Miranda UFRJ COPPE Rio De Janeiro Brazil

Nuclear Reactor Reload Optimization Problem (NRROP), which focuses on the economics and safety of the Nuclear Power Plant (NPP), is a classical problem in Nuclear Engineering that has been studied for more than 40 years. For decades, the NRROP was carried out by specialists that used their knowledge and experience to build configurations of the reactor core aiming at fulfilling the safety regulations of the NPR Since the 1980s, however, researchers have proposed metaheuristics optimization to automate this process. Recently, new researches have shown that quantum inspired evolutionary algorithms are among the best alternatives to deal with optimization problems in Nuclear Engineering. In the present work, quantum evolutionary algorithm (QEA) is used for optimizing the NRROP of a Brazilian "2-loop" Pressurized Water Reactor (PWR) Nuclear Power Plant. Angra 1. The main goal of this research is to show the performance of QEA to solve the NRROP compared with its classical counterpart, the Genetic algorithm (GA). In addition, manual reload and other optimization methods are also used to demonstrate the feasibility of QEA to solve cycle 7 of Angra 1. The performance of QEA, such as search ability and fast convergence, is better than GA and compatible with other quantum inspired evolutionary algorithms presented in the literature. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： PWR nuclear reactor reload In-Core fuel Management optimization quantum inspired evolutionary algorithm

来源：评论

学校读者我要写书评

暂无评论

EVALUATION OF SEVERAL quantum GENETIC algorithmS IN MEDICAL IMAGE REGISTRATION APPLICATIONS

EVALUATION OF SEVERAL QUANTUM GENETIC ALGORITHMS IN MEDICAL ...

引用

2012 IEEE International Conference on Computer Science and Automation Engineering（CSAE 2012）

作者： XiuJie Zhang ShiYong Li Yi Shen ShenMin Song Department of Control Science and Engineering Harbin Institute of Technology Harbin 150001 China

Registration is an important problem and a fundamental task in image ***,quantum-inspired evolutionary algorithms（QEA） have been proposed and applied to many optimization ***,few people study the application of QEA for image *** paper evaluate three kinds of QGAs in medical image registration applications,in which QGAs are implemented to find approximate solutions that maximizes the maximum mutual information（MI）,and the experimental results are compared and analyzed.

关键词： medical image image registration quantum inspired evolutionary algorithm quantum genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

To spike or not to spike: A probabilistic spiking neuron model

引用

NEURAL NETWORKS 2010年第1期23卷 16-19页

作者： Kasabov, Nikola Auckland Univ Technol KEDRI Auckland New Zealand

Spiking neural networks (SNN) are promising artificial neural network (ANN) models as they utilise information representation as trains of spikes, that adds new dimensions of time, frequency and phase to the structure and the functionality of ANN. The current SNN models though are deterministic, that restricts their applications for large scale engineering and cognitive modelling of stochastic processes. This paper proposes a novel probabilistic spiking neuron model (pSNM) and suggests ways of building pSNN for a wide range of applications including classification, string pattern recognition and associative memory. It also extends previously published computational neurogenetic models. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Spiking neural networks Probabilistic modelling quantum inspired evolutionary algorithm Classification Computational neurogenetic models

来源：评论

学校读者我要写书评

暂无评论

Full-body Joint Trajectory Generation Using an evolutionary Central Pattern Generator for Stable Bipedal Walking

Full-body Joint Trajectory Generation Using an Evolutionary ...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： Park, Chang-Soo Hong, Young-Dae Kim, Jong-Hwan Korea Adv Inst Sci & Technol Dept Elect Engn Taejon 305701 South Korea

ISBN: (纸本)9781424466757

Central pattern generator (CPG) is used to control the locomotion of vertebrate and invertebrate animals, such as walking, running or swimming. It consists of biological neural networks that can produce coordinated rhythmic signals by using simple input signals. In this paper, a full-body joint trajectory generator is proposed for stable bipedal walking by using an evolutionary optimized CPG. Sensory feedback pathways are proposed in the CPG structure, which uses force sensing resistor (FSR) signals. In order to optimize the parameters of CPG, quantum-inspired evolutionary algorithm is employed. Then, controller is developed to control the position of both ankles and pelvis and the pitching angles of shoulders. The proposed trajectory generator controls the position of the center of pelvis along lateral direction, and the pitch ping angle of both shoulders in addition to the position of both ankles for stable biped locomotion. The stability of biped locomotion along lateral direction is improved by controlling the position of the center of pelvis along lateral direction. To reduce yawing momentum, the pitching angle of both shoulders are controlled. The effectiveness is demonstrated by simulations with the Webot model of a small-sized humanoid robot, HSR-IX and real experiments with HSR-IX.

关键词： Webot model biological neural network biped locomotion stability coordinated rhythmic signal evolutionary central pattern generator evolutionary computation evolutionary optimized CPG force sensing resistor signal force sensors full body joint trajectory generation humanoid robot humanoid robots invertebrate animal lateral direction legged locomotion locomotion control pitching angle position control position control quantum inspired evolutionary algorithm sensory feedback pathway stability stable bipedal walking trajectory control trajectory generator vertebrate animal yawing momentum

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：