检索结果-内蒙古大学图书馆

Metaheuristics for the feedforward artificial neural network (ANN) architecture optimization problem

NEURAL COMPUTING & APPLICATIONS 2011年第8期20卷 1273-1284页

作者： Carvalho, Adenilson R. Ramos, Fernando M. Chaves, Antonio A. Brazilian Natl Inst Space Res INPE Lab Comp & Appl Math LAC Sao Paulo Brazil

This article deals with evolutionary artificial neural network (ANN) and aims to propose a systematic and automated way to find out a proper network architecture. To this, we adapt four metaheuristics to resolve the problem posed by the pursuit of optimum feedforward ANN architecture and introduced a new criteria to measure the ANN performance based on combination of training and generalization error. Also, it is proposed a new method for estimating the computational complexity of the ANN architecture based on the number of neurons and epochs needed to train the network. We implemented this approach in software and tested it for the problem of identification and estimation of pollution sources and for three separate benchmark data sets from UCI repository. The results show the proposed computational approach gives better performance than a human specialist, while offering many advantages over similar approaches found in the literature.

关键词： Neural network architecture optimization algorithms Evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Segment-based dose optimization using a genetic algorithm

引用

PHYSICS IN MEDICINE AND BIOLOGY 2003年第18期48卷 2987-2998页

作者： Cotrutz, C Xing, L Stanford Univ Dept Radiat Oncol Sch Med Stanford CA 94305 USA

Intensity modulated radiation therapy (IMRT) inverse planning is conventionally done in two steps. Firstly, the intensity maps of the treatment beams are optimized using a dose optimization algorithm. Each of them is then decomposed into a number of segments using a leaf-sequencing algorithm for delivery. An alternative approach is to pre-assign a fixed number of field apertures and optimize directly the shapes and weights of the apertures. While the latter approach has the advantage of eliminating the leaf-sequencing step, the optimization of aperture shapes is less straightforward than that of beamlet-based optimization because of the complex dependence of the dose on the field shapes, and their weights. In this work we report a genetic algorithm for segment-based optimization. Different from a gradient iterative approach or simulated annealing, the algorithm finds the optimum solution from a population of candidate plans. In this technique, each solution is encoded using three chromosomes: one for the position of the left-bank leaves of each segment, the second for the position of the right-bank and the third for the weights of the segments defined by the first two chromosomes. The convergence towards the optimum is realized by crossover and mutation operators that ensure proper exchange of information between the three chromosomes of all the solutions in the population. The algorithm is applied to a phantom and a prostate case and the results are compared with those obtained using beamlet-based optimization. The main conclusion drawn from this study is that the genetic optimization of segment shapes and weights can produce highly conformal dose distribution. In addition, our study also confirms previous findings that fewer segments are generally needed to generate plans that are comparable with the plans obtained using beamlet-based optimization. Thus the technique may have useful applications in facilitating IMRT treatment planning.

关键词： Genetic Algorithm (GA) optimization algorithms field shape treatment planning Segments information exchange intensity modulated radiation therapy apertures

来源：评论

学校读者我要写书评

暂无评论

optimization-Based Strategies for Optimal Inverse Parameters Estimation for Heat Transfer Systems

引用

IEEE ACCESS 2021年 9卷 71328-71343页

作者： Matajira-Rueda, David Cruz-Duarte, Jorge Mario Avina-Cervantes, Juan Gabriel Ibarra-Manzano, Mario Alberto Correa, Rodrigo Univ Guanajuato Dept Elect Engn Telemat Res Grp CA Engn Div Campus Irapuato Salamanca Guanajuato 36885 Mexico Tecnol Monterrey Escuela Ingn & Ciencias Monterrey 64849 Mexico Univ Ind Santander Fac Ingn Fisicomecan Escuela Ingn Elect Elect & Telecomunicac Bucaramanga 680002 Colombia

Thermal design for electronic devices approached through the solution analysis of the Inverse Heat Transfer Problem (IHTP) has not been extensively explored. This article proposes an alternative strategy and a contrasting approach for the optimal inverse parameters' estimation of heat transfer systems, particularly in designing heat sinks. A framework to tackle a Rectangular Microchannel Heat Sink (RMCHS) design modeled by the Entropy Generation Minimization (EGM) criterion is developed. This framework comprises two strategies to be compared. The serial proposal works sequentially depending on the parameters' sensitivity into the RMCHS model, backpropagating estimated parameters to all processes. The parallel strategy processes all parameters simultaneously. Instead of focusing efforts on a typical optimization process, a sequential procedure takes advantage of the most influential parameters in the heat sink model and the excellent exploration-exploitation rate of Metaheuristic optimization algorithms (MOAs). The most sensitive design variables are prioritized in the serial strategy. The implemented estimation-optimization strategies are addressed through an IHTP's inverse analysis. Thereby, global MOAs are implemented to solve the specific application and become an alternative to the gradient-based methods when their efficiency and effectiveness are at stake. MOAs show overall relative errors related to minimal entropy generation rate inferior to 0.07% for data with 30 dB of SNR and less than 7.63% of error for data with 10 dB of SNR compared with the Levenberg-Marquardt method. Numerical results show that serial strategy provided a stable and reliable design solution even with contaminated data, obtaining better performances than the multiparametric strategy. Additionally, parametric and nonparametric statistical tests were used to validate the appropriate optimization algorithm and the most reliable strategy. The statistical tests confirmed the optimal-inverse p

关键词： optimization Heat transfer Heat sinks Electromagnets Thermal analysis Analytical models Thermodynamics Inverse heat transfer problem Levenberg-Marquardt metaheuristics optimization algorithms Rectangular Microchannel Heat Sink

来源：评论

学校读者我要写书评

暂无评论

Film Cooling optimization Using Numerical Computation of the Compressible Viscous Flow Equations and Simplex Algorithm

引用

INTERNATIONAL JOURNAL OF AEROSPACE ENGINEERING 2013年第1期2013卷 11.1-11.24页

作者： Elsayed, Ahmed M. Owis, Farouk M. Rahman, M. Madbouli Abdel Inst Aviat Engn & Technol Giza Egypt Cairo Univ Fac Engn Dept Aerosp Engn Giza 12211 Egypt

Film cooling is vital to gas turbine blades to protect them from high temperatures and hence high thermal stresses. In the current work, optimization of film cooling parameters on a flat plate is investigated numerically. The effect of film cooling parameters such as inlet velocity direction, lateral and forward diffusion angles, blowing ratio, and streamwise angle on the cooling effectiveness is studied, and optimum cooling parameters are selected. The numerical simulation of the coolant flow through flat plate hole system is carried out using the "CFDRC package" coupled with the optimization algorithm "simplex" to maximize overall film cooling effectiveness. Unstructured finite volume technique is used to solve the steady, three-dimensional and compressible Navier-Stokes equations. The results are compared with the published numerical and experimental data of a cylindrically round-simple hole, and the results show good agreement. In addition, the results indicate that the average overall film cooling effectiveness is enhanced by decreasing the streamwise angle for high blowing ratio and by increasing the lateral and forward diffusion angles. Optimum geometry of the cooling hole on a flat plate is determined. In addition, numerical simulations of film cooling on actual turbine blade are performed using the flat plate optimal hole geometry.

关键词： Cooling effects Cooling hole Angle compressible numerical simulation air blowing ratio numerical calculation optimization algorithms Film cooling Flat slabs TURBINE BLADE Simplex Film cooling effectiveness

来源：评论

学校读者我要写书评

暂无评论

Handling uncertainty issue in software defect prediction utilizing a hybrid of ANFIS and turbulent flow of water optimization algorithm

引用

NEURAL COMPUTING & APPLICATIONS 2024年第9期36卷 4583-4602页

作者： Elsabagh, M. A. Emam, O. E. Gafar, M. G. Medhat, T. Kafrelsheikh Univ Fac Artificial Intelligence Dept Machine Learning & Informat Retrieval Kafrelsheikh Egypt Helwan Univ Fac Comp & Artificial Intelligence Dept Informat Syst Cairo Egypt Kafrelsheikh Univ Fac Engn Dept Elect Engn Kafrelsheikh Egypt

During the development cycle of software projects, numerous defects and challenges have been identified, leading to prolonged project durations and escalated costs. As a result, both product delivery and defect tracking have become increasingly complex, expensive, and time-consuming. Recognizing the challenge of identifying every software defect, it is crucial to foresee potential consequences and strive for the production of high-quality products. The goal of software defect prediction (SDP) is to identify problematic locations within software code. This study presents the first experimental investigation utilizing the turbulent flow of water optimization (TFWO) in conjunction with the adaptive neuro-fuzzy inference system (ANFIS) to enhance SDP. The TFWO_ANFIS model is designed to address the uncertainties present in software features and predict defects with feasible accuracy. Data are divided randomly at the beginning of the model into training and testing sets to avoid the local optima and over-fitting issues. By applying the TFWO approach, it adjusts the ANFIS parameters during the SDP process. The proposed model, TFWO_ANFIS, outperforms other optimization algorithms commonly used in SDP, such as particle swarm optimization (PSO), gray wolf optimization (GWO), differential evolution (DE), ant colony optimization (ACO), standard ANFIS, and genetic algorithm (GA). This superiority is demonstrated through various evaluation metrics for four datasets, including standard deviation (SD) scores (0.3307, 0.2885, 0.3205, and 0.2929), mean square error (MSE) scores (0.1091, 0.0770, 0.1026, and 0.0850), root-mean-square error (RMSE) scores (0.3303, 0.2776, 0.3203, and 0.2926), mean bias error (MBE) scores (0.1281, 0.0860, 0.0931, and 0.2310), and accuracy scores (87.3%, 90.2%, 85.8%, and 89.2%), respectively, for the datasets KC2, PC3, KC1, and PC4. These datasets with different instances and features are obtained from an open platform called OPENML. Additionally, multip

关键词： Software defect prediction Turbulent flow of water optimization algorithm Adaptive neuro-fuzzy inference system (ANFIS) optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

On optimal design of HDD suspension using topology optimization

引用

MICROSYSTEM TECHNOLOGIES-MICRO-AND NANOSYSTEMS-INFORMATION STORAGE AND PROCESSING SYSTEMS 2002年第1-2期9卷 137-146页

作者： Pan, L Lau, GK Du, H Ling, SF Nanyang Technol Univ Sch Mech & Prod Engn CMMS Singapore 639798 Singapore

This paper explores the use of topological optimization to systematically design suspensions for hard disk drives (HDD). The design problem is posed as a material distribution problem, which varies spatial thickness of suspensions so as to enhance their dynamic performance. Due to the requirements for specific motion characteristics, suspensions are designed to have higher torsional and lateral frequencies while maintaining an adequate but not too high frequency for transverse bending. The torsional and lateral frequencies are generally higher in order than the transverse frequencies. Due to their non-convex nature, the optimizations of higher-order frequencies were proven to be more difficult than that of the fundamental frequency. To tackle the problem, present work adopted mode-tracking techniques, and attempted two different optimization algorithms to solve the design problem. With reference to the topological results obtained, it is found that the implementation based on sequential quadratic programming (SQP) performed better than that based on optimal criteria (OC). It was also found that the present design method could tremendously improve the dynamic performance of suspensions.

关键词： design problems design approach optimization algorithms Topology optimization transverse bending Optimal design dynamic characteristics

来源：评论

学校读者我要写书评

暂无评论

Real-Time Write Strategy optimization Method for Optical Discs

引用

JAPANESE JOURNAL OF APPLIED PHYSICS 2012年第8期51卷 08JA03-08JA03页

作者： Takeshita, Nobuo Kishigami, Tomo Ikuta, Koichi Tsujimoto, Hiroaki Mitsubishi Electr Corp Adv Technol R&D Ctr Nagaokakyo Kyoto 6178550 Japan Mitsubishi Electr Corp Adv Technol R&D Ctr Amagasaki Hyogo 6618661 Japan Osaka City Univ Fac Engn Osaka 5588585 Japan

An optimization method of the write strategy for optical discs to realize stable recording within the whole area of each optical disc is proposed. In this method, the write strategy is continuously optimized in the real-time base during the recording operation against the variation of recording characteristics in optical discs, in accordance with the recording position in the radial direction and environmental conditions. The optimization algorithm to select the suitable write strategy parameters to be optimized was established with reference to the database previously prepared. The effectiveness and lack of side effects in this method are experimentally confirmed using optical discs. (C) 2012 The Japan Society of Applied Physics

关键词： RECORD CHARACTER time bases Side Effect optimization algorithms radial direction optimization method

来源：评论

学校读者我要写书评

暂无评论

Automatic calibration of groundwater models using global optimization techniques

引用

HYDROLOGICAL SCIENCES JOURNAL-JOURNAL DES SCIENCES HYDROLOGIQUES 1999年第6期44卷 879-894页

作者： Solomatine, DP Dibike, YB Kukuric, N Int Inst Infrastruct Hydraul & Environm Engn IHE NL-2601 DA Delft Netherlands

The problem of a groundwater model calibration is posed as a multi-extremum (global) optimization problem, rather than the more widely considered single-extremum (local) optimization problem. Several algorithms of randomized search incorporated in the global optimization tool GLOBE are considered (including the canonical genetic algorithm and more recently developed adaptive cluster covering), and applied to the calibration of the groundwater model TRIWACO. The results show the usefulness of global optimization algorithms in the automatic calibration of even complex models having considerable running times.

关键词： .covering considerable Genetic algorithm optimization problem optimization algorithms groundwater models automatic calibration optimization techniques global optimization tool adaptive cluster TRIWACO running times

来源：评论

学校读者我要写书评

暂无评论

Hybrid optimization algorithm applied for selective harmonic elimination in multilevel inverter with reduced switch topology

引用

MICROSYSTEM TECHNOLOGIES-MICRO-AND NANOSYSTEMS-INFORMATION STORAGE AND PROCESSING SYSTEMS 2018年第8期24卷 3409-3415页

作者： Patil, Sarika D. Kadwane, Sumant G. Rajiv Gandhi Coll Engn & Res Dept Elect Engn Nagpur Maharashtra India Yeshwantrao Chavan Coll Engn Dept Elect Engn Nagpur Maharashtra India

This paper presents, ant colony optimization based hybrid algorithm for selective harmonic elimination in single phase seven level multilevel inverter with reduced switches. For high power and high voltage applications, multilevel structure with selective harmonic elimination (SHE) modulation scheme is used. The output voltage of multilevel inverter contains fundamental component along with harmonics. SHE technique aims to solve non-linear transcendental equations maintaining the fundamental harmonic component to its desired value and to eliminate lower order odd harmonics. Many optimization algorithms have been implemented to solve this problem. But these algorithms are complicated and time consuming. The Newton-Raphson algorithm is also very convergent for solving these non-linear equations. The main disadvantage of this method is, it requires strong initial guess. To overcome these drawbacks, hybrid optimization algorithm is used in this paper. This algorithm is performed in two stages, during first stage ant colony optimization has been run and in second stage the solutions obtained from ACO is used as a initial guess for Newton-Raphson algorithm which confirms the exact converged solution. Thus the drawback of Newton's method i.e. requirement of good initial guess is overcomed by proposed hybrid algorithm. The MATLAB/SlMULINK software is used for comprehensive simulation of seven-level inverter. Experimental results validate the simulated results.

关键词： Newton method output voltage optimization algorithms Ant colony optimization Guess algorithms SHE gene Harmonic reduction multilayers fundamental component Inventors Switches

来源：评论

学校读者我要写书评

暂无评论

optimization of thickness uniformity of optical coatings on a conical substrate in a planetary rotation system

引用

APPLIED OPTICS 2013年第4期52卷 B26-B32页

作者： Guo, Chun Kong, Mingdong Liu, Cunding Li, Bincheng Chinese Acad Sci Inst Opt & Elect Chengdu 610209 Peoples R China Univ Chinese Acad Sci Beijing 100039 Peoples R China

For a coating machine with a planetary rotation system and counterrotating shadowing mask configuration, a shadowing mask was designed using a numerical optimization algorithm to control the thickness uniformity of optical coatings formed on conical substrate. Single-layer magnesium fluoride (MgF2) and antireflective (AR) coating at 193 nm were fabricated on a convex conical substrate holder (with diameter 225 mm, apex angle 140 deg, and height 41 mm) by thermal evaporation. Thickness distribution determined from the transmittance spectra of single-layer MgF2 thin films on BK7 slices showed that uniformities better than 99.3% were experimentally achieved with the designed counterrotating shadowing mask. From the reflectance spectra, uniform optical performance was also obtained for the 193 nm AR coating deposited on fused-silica substrates. (C) 2013 Optical Society of America

关键词： Conical Antireflection coatings TRANSMISSION SPECTROSCOPY Reflection spectra Optical coatings Uniformity COUNTERROTATION optimization algorithms Substrates COATERS Shadowing (Histology) PLANETARY ROTATION

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：