检索结果-内蒙古大学图书馆

IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe)

作者： Morquecho, Edgar G. Torres, Santiago P. Espinoza, Juan L. Lopez, Julio C. Quizhpe, Klever L. Sempertegui, Rodrigo E. Solano, Lizandro D. Univ Cuenca Dept Elect Elect & Telecommun Engn Cuenca Ecuador

ISBN: (纸本)9781538645055

This paper proposes to solve the transmission network expansion planning problem (TNEP) using the AC model formulated with full non-linear load flow equations, incorporating the cost of losses in the transmission network. Additionally, the decomposed formulation finds the location and amount of the reactive compensation needed in the system. A comparison between evolutionary programming (EP) and a variation of EP with a Cultural Algorithm (CEP) is presented to solve this very complex optimization problem. The results are obtained using Garver's 6-bus test system and IEEE 24-bus test system.

关键词： AC model Cultural Algorithm evolutionary programming Optimization Transmission network expansion planning

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter tuning using Quantum Genetic Algorithms 31

Hyperparameter tuning using Quantum Genetic Algorithms

引用

31st IEEE International Conference on Tools with Artificial Intelligence (ICTAI)

作者： Lentzas, Athanasios Nalmpantis, Christoforos Vrakas, Dimitris Aristotle Univ Thessaloniki Sch Informat Thessaloniki Greece

ISBN: (纸本)9781728137988

Correctly tuning the hyperparameters of a machine learning model can improve classification results. Typically hyperparameter tuning is made by humans and experience is needed to fine tune them. Algorithmic approaches have been extensively studied in the literature and can find better results. In our work we employ a quantum genetic algorithm to address the hyperparameter optimization problem. The algorithm is based on qudits instead of qubits, allowing more available states. Experiments were performed on two datasets MNIST and CIFAR10 and results were compared against classic genetic algorithms.

关键词： hyperparameter tuning quantum genetic algorithms evolutionary programming machine learning optimization

来源：评论

学校读者我要写书评

暂无评论

Identifying Gene Knockout Strategies Using a Hybrid of Bees Algorithm and Flux Balance Analysis for in Silico Optimization of Microbial Strains

Identifying Gene Knockout Strategies Using a Hybrid of Bees ...

引用

9th International Symposium on Distributed Computing and Artificial Intelligence (DCAI 2012)

作者： Choon, Yee Wen Mohamad, Mohd Saberi Deris, Safaai Chong, Chuii Khim Chai, Lian En Ibrahim, Zuwairie Omatu, Sigeru Univ Teknologi Malaysia Fac Comp Sci & Informat Syst Artificial Intelligence & Bioinformat Grp Skudai 81310 Johor Malaysia Univ Teknol Malaysia Fac Engn CAIRO Skudai 81310 Malaysia Osaka Inst Technol Informat & Commun Engn Dept Elect Osaka 5358585 Japan

ISBN: (纸本)9783642287640;9783642287657

Genome-scale metabolic networks reconstructions from different organisms have become popular in recent years. Genetic engineering is proven to be able to obtain the desirable phenotypes. Optimization algorithms are implemented in previous works to identify the effects of gene knockout on the results. However, the previous works face the problem of falling into local minima. Thus, a hybrid of Bees Algorithm and Flux Balance Analysis (BAFBA) is proposed in this paper to solve the local minima problem and to predict optimal sets of gene deletion for maximizing the growth rate of certain metabolite. This paper involves two case studies that consider the production of succinate and lactate as targets, by using E-coli as model organism. The results from this experiment are the list of knockout genes and the growth rate after the deletion. BAFBA shows better results compared to the other methods. The identified list suggests gene modifications over several pathways and may be useful in solving challenging genetic engineering problems.

关键词： evolutionary programming Metabolic Engineering Bees Algorithm Gene Knockout Optimization

来源：评论

学校读者我要写书评

暂无评论

Application of evolutionary Computation techniques for generation expansion planning

Application of Evolutionary Computation techniques for gener...

引用

IEEE PES Transmission and Distribution Conference and Exposition

作者： Kannan, S Slochanal, SMR Padhy, NP Thiagarajar Coll Engn Dept Elect Engn Madurai Tamil Nadu India

ISBN: (纸本)0780381106

This paper presents the application of evolutionary Computation (EC) techniques, Improved evolutionary Strategies (IES), Improved evolutionary programming (IEP) and Improved Genetic Algorithm (IGA) to least cost Generation Expansion Planning (GEP) problem. Least-cost GEP problem is a highly constrained nonlinear discrete dynamic optimization problem. Several conventional non-linear optimization methods have been used to solve the GEP problem. These methods may fail to provide global optima due to involvement of discrete variables in the constraints. Recently EC techniques are used to solve the combinatorial optimization GEP problems, due to its global search characteristics. The GEP problem is illustrated for a synthetic reliable test system with 4, 6 and 14 years planning horizon. The results obtained using IES, IEP and IGA are verified using Dynamic programming (DP) for 4 and 6 year planning horizon. The problem with 14 year planning horizon is simulated using IES, IEP and IGA.

关键词： dynamic programming evolutionary computation evolutionary programming evolutionary strategy generation expansion planning and genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Strengths and Weaknesses of FSA Representation 07

Strengths and Weaknesses of FSA Representation

引用

Annual Conference of Genetic and evolutionary Computation Conference

作者： Petrovic, Pavel NTNU Dept Comp & Informat Sci N-7491 Trondheim Norway

ISBN: (纸本)9781595936974

Genetic programming and evolutionary programming are fields studying the application of artificial evolutionon evolving directly executable programs, in form of trees similar to Lisp expressions (GP-trees), or Finite State Automata (FSA).In this exercise, we study the performance of these methods on several example problems, and draw conclusionson the suitability of the representations with respect to the task structure and properties. We investigate the roleof incremental evolution and its bias in the context of FSA representation. The experiments are performed in simulation and/or confirmed on real robots.

关键词： evolutionary programming Finite State Automata Incremental Evolution

来源：评论

学校读者我要写书评

暂无评论

Synthesizing Broad Null in Linear Array by Amplitude-Only Control using Wind Driven Optimization Technique

Synthesizing Broad Null in Linear Array by Amplitude-Only Co...

引用

SAI Intelligent Systems Conference (IntelliSys)

作者： Mahto, Santosh Kumar Suman, Sushmita Choubey, Arvind Sinha, Rashmi Natl Inst Technol Dept Elect & Commun Engn Jamshedpur Bihar India Natl Inst Technol Dept Comp Sci Engn Jamshedpur Bihar India

ISBN: (纸本)9781467376068

This paper describes fast, efficient and global optimization method called wind driven optimization (WDO) algorithm for nulling pattern synthesis of uniformly spaced linear array having maximum side lobe level (SLL) suppression, restricted dynamic range ratio (DRR), beam width and null control by controlling the array elements amplitude-only. A broad null is placed in the direction of maximum interference by undesired signals while receiving signal from the desired direction. The WDO is a new nature-inspired evolutionary algorithm derived from to the point movement of the air parcel in the earth's atmosphere. It uses a new learning strategy to update the velocity and position of air packets based on their current pressure values to accelerate the convergence. The pressure (objective) function is based on an exact penalty method. The results are compared with those obtained by other evolutionary algorithm such as bacterial foraging optimization (BFO), plant growth simulation algorithm (PGSA) and bee algorithm. The simulation study demonstrates that the WDO outperforms the three algorithms particularly in terms of minimum SLL, beam width control, DRR, null control and the rate of convergence.

关键词： Antenna array particle swarm optimization (PSO) wind driven optimization (WDO) linear array design null control sidelobe level suppression (SLL) evolutionary programming interference

来源：评论

学校读者我要写书评

暂无评论

A novel approach for structural synthesis of zoom systems

A novel approach for structural synthesis of zoom systems

引用

Conference on Current Developments in Lens Design and Optical Engineering XI - and Advances in Thin Film Coatings VI

作者： Hazra, L. N. Pal, S. Univ Calcutta Dept Appl Opt & Photon Kolkata India

ISBN: (纸本)9780819482822

A new approach for 'ab initio' synthesis of thin lens structure of zoom lenses is reported. This is accomplished by an implementation of evolutionary programming, based on Genetic Algorithm, which explores the available configuration space formed by powers of individual components and inter-component separations. Normalization of the variables is carried out to get an insight on the optimum structures. The method has been successfully used to get thin lens structures of mechanically compensated, optically compensated, and linearly compensated zoom lens systems by suitable formulation of merit function of optimization. Investigations have been carried out on three component and four component zoom lens structures. Illustrative numerical results are presented.

关键词： Optically compensated zoom lenses mechanically compensated zoom lenses evolutionary programming genetic algorithm thin lens design

来源：评论

学校读者我要写书评

暂无评论

On Rotor Aeroacoustic Optimization for Urban Air Mobility 28

On Rotor Aeroacoustic Optimization for Urban Air Mobility

引用

28th AIAA/CEAS Aeroacoustics Conference

作者： Pinto, Olivia L. Bossotto, Gabriele Afonso, Frederico Lau, Fernando P. Univ Lisbon Inst Super Tecn P-1049001 Lisbon Portugal Politecn Torino I-10129 Turin Italy Univ Lisbon Inst Super Tecn IDMEC P-1049001 Lisbon Portugal Deloitte New York NY USA Brembo SpA Curno Italy

ISBN: (数字)9781624106644

ISBN: (纸本)9781624106644

This article presents an optimization study of the noise produced by rotors in the context of Urban Air Mobility (UAM). The importance of this study is based on the expected growth of UAM in larger cities across the globe and on the consequent effort to decrease the noise emitted by this type of aircraft. Provided that rotors constitute a major part of the noise produced by this aviation segment, given the fact that the aircraft are intended to be fully electric, the design of these components is of paramount importance for noise minimization. Herein, the focus is on small rotors given the availability of experimental data to compare the numerical results. For the simulation accomplished within the optimization process, an open-source aerodynamic and aeroacoustic code (FLOWUnsteady, or FLight, Optimization, and Wind Unsteady) was integrated within an optimization module created specifically for the current work. These tools are based on the Formulation 1A of Farassat (PSU-WOPWOP) and the Brooks-Pope-Marcolini airfoil noise model (FLOWNoise), being utilized for the prediction of the tonal and atonal noise, respectively. The simulation code is applied to predict rotor noise which is posteriorly reduced by the means of a gradient-free optimization algorithm, leading to the proposed optimal rotor design, with a reduction of 16,21% of the Energy Averaged Overall Sound Pressure Level (EAOSPL) having been achieved.

关键词： Urban Air Mobility Overall Sound Pressure Level Cambered Airfoil Gradient Free Optimization Aviation Strouhal Number Aerodynamic Coefficients Turbulent Boundary Layer Blade Element Momentum Theory evolutionary programming

来源：评论

学校读者我要写书评

暂无评论

Beyond Black-Scholes: A neural networks-based approach to options pricing

引用

International Journal of Theoretical and Applied Finance 2003年第5期6.0卷 469-489页

作者： Zapart, Christopher A. Adv. Fin. Trading Solutions Ltd. Middlesex Enfield EN3 6YA 9 Dundas Mews United Kingdom

The paper presents two alternative schemes for pricing European and American call options, both based on artificial neural networks. The first method uses binomial trees linked to an innovative stochastic volatility model. The volatility model is based on wavelets and artificial neural networks. Wavelets provide a convenient signal/noise decomposition of the volatility in the non-linear feature space. Neural networks are used to infer future volatility levels from the wavelets feature space in an iterative manner. The bootstrap method provides the 95% confidence intervals for the options prices. In the second approach neural networks are trained with genetic algorithms in order to reverse-engineer the Black-Scholes formulae. The standard Black-Scholes model provides a starting point for an evolutionary training process, which yields improved options prices. Market options prices as quoted on the Chicago Board Options Exchange are used for performance comparison between the Black-Scholes model and the proposed options pricing schemes. The proposed models produce as good as and often better options prices than the conventional Black-Scholes formulae.

关键词： Artificial Neural Networks Binomial Trees Black-Scholes Formulae Bootstrap Delta-Hedging evolutionary programming Genetic Algorithms Options Pricing Statistical Arbitrage Stochastic Volatility Wavelets

来源：评论

学校读者我要写书评

暂无评论

Genetic algorithm for broadcast scheduling in packet radio networks

Genetic algorithm for broadcast scheduling in packet radio n...

引用

IEEE International Conference on evolutionary Computation

作者： Chakraborty, G Hirano, Y Univ Aizu Aizu Wakamatsu 96580 Japan

ISBN: (纸本)0780348699

Packet Radio (PR) networks are to provide data communication among a set of nodes distributed over a region. A time division multiple access (TDMA) protocol is adopted for conflict free communication. The goal is to find a conflict free transmission schedule for different nodes at different time slots of a fixed length time cycle, called TDMA cycle. The optimization criterion is primarily to minimize the TDMA cycle length, and then to maximize the number of transmissions. First classical Genetic Algorithm is tried to solve this NP-complete problem, which showed poor performance for bigger networks. Then we proposed some special crossover operators suitable for this kind of problem. This modified operator could deliver very good quality of results even for big networks and in few generations. Some study on the dependence of the result on population:ion size etc. are studied. The results are empirically compared with other approaches, a greedy-heuristic algorithm and mean field annealing.

关键词： genetic algorithm evolutionary programming broadcast 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：