检索结果-内蒙古大学图书馆

Annual Streamflow Time Series Prediction Using Extreme Learning Machine Based on gravitational search algorithm and Variational Mode Decomposition

引用

JOURNAL OF HYDROLOGIC ENGINEERING 2020年第5期25卷

作者： Niu, Wen-jing Feng, Zhong-kai Chen, Yu-bin Zhang, Hai-rong Cheng, Chun-tian ChangJiang Water Resources Commiss Bur Hydrol Jiefang Ave 1863 Wuhan 430010 Peoples R China Huazhong Univ Sci & Technol Sch Hydropower & Informat Engn Wuhan 430074 Hubei Peoples R China China Yangtze Power Co Ltd Dept Water Resources Management Jianshe Rd 1 Yichang 443000 Peoples R China Dalian Univ Technol Dept Inst Hydropower & Hydroinformat Key Lab Ocean Energy Utilizat & Energy Conservat Minist Educ Dalian 116024 Peoples R China

Accurate annual runoff prediction plays an important role in modern water resources planning and management. Here, a hybrid model using evolutionary extreme learning machine and variational mode decomposition (VMD) is developed to forecast annual runoff time series. In the proposed method, the VMD method is first used to decompose the original streamflow into a series of disjoint subcomponents;second, each subcomponent is forecasted by constructing an appropriate extreme learning machine model while the gravitational search algorithm is adopted to tune the model parameters;finally, the aggregated output generated by the forecasting results of all the models is treated as the final simulated output. The annual runoff data series of three huge hydropower reservoirs in China are chosen to testify the performance of the proposed forecasting model. The results show that the developed model can outperform several traditional methods with respect to the employed statistical indexes. Thus, the decomposition-ensemble idea is helpful to yield accurate and stable forecasting results, while the proposed forecasting method can provide strong technical support for operators in water resources and power systems.

关键词： Hydrological time series forecasting Variational mode decomposition Evolutionary extreme learning machine gravitational search algorithm Decomposition and ensemble

来源：评论

学校读者我要写书评

暂无评论

Automatic clustering and feature selection using gravitational search algorithm and its application to microarray data analysis

引用

NEURAL COMPUTING & APPLICATIONS 2019年第8期31卷 3647-3663页

作者： Kumar, Vijay Kumar, Dinesh Thapar Univ Comp Sci & Engn Dept Patiala Punjab India GJUS&T Comp Sci & Engn Dept Hisar Haryana India

This paper proposes a novel approach that selects the number of clusters along with relevant features automatically and simultaneously. gravitational search algorithm is used as metaheuristic. A novel agent representation scheme is used for encoding cluster centers and number of features. The algorithm is able to find the optimal number of clusters and the relevant features corresponding to the clusters during the run time. A new concept of threshold setting is used. The variance (statistical property) of the dataset has been exploited. To make the search efficient, a novel clustering criterion is used. The proposed approach is compared with recently developed well-known clustering techniques. This approach is further applied for analysis of microarray data. The statistical and biological significance tests are performed to demonstrate the efficiency of proposed approach. The results prove the effectiveness and the accuracy of the proposed algorithm.

关键词： gravitational search algorithm Clustering Feature selection Variance Metaheuristics

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-based control using Q-learning and gravitational search algorithm with experimental validation on a nonlinear servo system

引用

INFORMATION SCIENCES 2022年 583卷 99-120页

作者： Zamfirache, Iuliu Alexandru Precup, Radu-Emil Roman, Raul-Cristian Petriu, Emil M. Politehn Univ Timisoara Dept Automat & Appl Informat Bd V Parvan 2 Timisoara 300223 Romania Univ Ottawa Sch Elect Engn & Comp Sci 800 King Edward Ottawa ON K1N 6N5 Canada

This paper presents a novel Reinforcement Learning (RL)-based control approach that uses a combination of a Deep Q-Learning (DQL) algorithm and a metaheuristic gravitational search algorithm (GSA). The GSA is employed to initialize the weights and the biases of the Neural Network (NN) involved in DQL in order to avoid the instability, which is the main drawback of the traditional randomly initialized NNs. The quality of a particular set of weights and biases is measured at each iteration of the GSA-based initialization using a fitness function aiming to achieve the predefined optimal control or learning objective. The data generated during the RL process is used in training a NN-based controller that will be able to autonomously achieve the optimal reference tracking control objective. The proposed approach is compared with other similar techniques which use different algorithms in the initialization step, namely the traditional random algorithm, the Grey Wolf Optimizer algorithm, and the Particle Swarm Optimization algorithm. The NN-based controllers based on each of these techniques are compared using performance indices specific to optimal control as settling time, rise time, peak time, overshoot, and minimum cost function value. Real-time experiments are conducted in order to validate and test the proposed new approach in the framework of the optimal reference tracking control of a nonlinear position servo system. The experimental results show the superiority of this approach versus the other three competing approaches. (c) 2021 Elsevier Inc. All rights reserved.

关键词： gravitational search algorithm NN training Optimal reference tracking control Q-learning Reinforcement learning Servo systems

来源：评论

学校读者我要写书评

暂无评论

A prototype classifier based on gravitational search algorithm

引用

APPLIED SOFT COMPUTING 2012年第2期12卷 819-825页

作者： Bahrololoum, Abbas Nezamabadi-Pour, Hossein Bahrololoum, Hamid Saeed, Masoud Shahid Bahonar Univ Kerman Dept Elect Engn Kerman Iran

In recent years, heuristic algorithms have been successfully applied to solve clustering and classification problems. In this paper, gravitational search algorithm (GSA) which is one of the newest swarm based heuristic algorithms is used to provide a prototype classifier to face the classification of instances in multi-class data sets. The proposed method employs GSA as a global searcher to find the best positions of the representatives (prototypes). The proposed GSA-based classifier is used for data classification of some of the well-known benchmark sets. Its performance is compared with the artificial bee colony (ABC), the particle swarm optimization (PSO), and nine other classifiers from the literature. The experimental results of twelve data sets from UCI machine learning repository confirm that the GSA can successfully be applied as a classifier to classification problems. (C) 2011 Elsevier B. V. All rights reserved.

关键词： Classification Prototype classifier Swarm intelligence gravitational search algorithm UCI machine learning repository

来源：评论

学校读者我要写书评

暂无评论

Piecewise function based gravitational search algorithm and its application on parameter identification of AVR system

引用

NEUROCOMPUTING 2014年 124卷 139-148页

作者： Li, Chaoshun Li, Hongshun Kou, Pangao Huazhong Univ Sci & Technol Sch Hydropower & Informat Engn Wuhan 430074 Peoples R China Zhongnan Univ Econ & Law Wuhan 430074 Peoples R China Hunan Elect Power Co Sci Res Inst Changsha 410007 Hunan Peoples R China

Heuristic optimization has shown its superiority in handling identification problem of complicated system, for methods based on heuristic optimization do not have special requirements on model structures of the target system. In this paper, a piecewise function based gravitational search algorithm (PFGSA) is proposed and applied in parameter identification of automatic voltage regulator (AVR) system. In the proposed algorithm, a piecewise function is designed as the gravitational constant function to replace the traditional exponential equation. The piecewise function provides more rational gravitational constant to control the convergence of algorithm, and thus excellent searching ability is likely to be achieved. Moreover a new weighted objective function is proposed in the identification frame. Comparative experimental studies are conducted to test the searching ability of PFGSA and to verify the performance of proposed identification strategy, while genetic algorithm, particle swarm optimization and GSA are employed for comparison. The experimental results show that PFGSA performs the best on term of accuracy and stability in the parameter identification of AVR system, and the proposed identification strategy is effective. (C) 2013 Elsevier B.V. All rights reserved.

关键词： AVR system Parameter identification gravitational search algorithm Piecewise function

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a hybrid MLP-GSA model with multi-layer perceptron-gravitational search algorithm for monthly lake water level forecasting

引用

STOCHASTIC ENVIRONMENTAL REsearch AND RISK ASSESSMENT 2019年第1期33卷 125-147页

作者： Ghorbani, Mohammad Ali Deo, Ravinesh C. Karimi, Vahid Kashani, Mahsa H. Ghorbani, Shahryar Univ Tabriz Fac Agr Dept Water Engn Tabriz Iran Near East Univ Engn Fac Mersin 10 TR-99138 Nicosia North Cyprus Turkey Univ Southern Queensland Sch Agr Computat & Environm Sci Ctr Sustainable Agr Syst Springfield Qld 4300 Australia Univ Southern Queensland Inst Life Sci & Environm Ctr Appl Climate Sci Springfield Qld 4300 Australia Univ Tabriz Dept Water Engn Tabriz Iran Univ Mohaghegh Ardabili Dept Water Engn Ardebil Iran Istanbul Gedik Univ Grad Sch Social Sci Istanbul Turkey

Lakes are primitive water holding geographicstructures containing most thefresh water on the Earth's surface, but the recent trends show that climate change can potentiallylead to a significant aberration in the Lake water level and itsoverall pristine state, and therefore, could alsothreaten the source of freshwater. The ability to forecast thelake water is a paramount decision-making and risk-reduction task, and this isrequired to retain the sustainability of the natural environment, and to reduce the risk tothe local and globalfood chain, recreationactivities, agriculture and ecosystems. In this study, we have designed and evaluated a new hybrid forecasting model, integrating the gravitational search algorithm (GSA), as a heuristic optimization tool, with the Multilayer Perceptron (MLP-GSA) algorithm to forecast water level in Winnipesaukee and Cypress Lakes in the United States of America. The performance of the resulting hybrid MLP-GSA model is benchmarked and compared with the traditional MLP trained with Levenberg-Marquadt back propagation learning algorithm, two other intelligent hybrid models (MLP-PSO and MLP-FFA) and also two stochastic models namely, ARMA and ARIMA models. In this case study, the monthly time scale water level data from 1938 to 2005 and 1942 to 2011 for the Lakes Winnipesaukee and Cypress, respectively, were applied to train and evaluate the MLP-GSA model. The best input combinations of the standalone (MLP) and the hybrid MLP-GSA forecasting models were determined by sensitivity analysis of historical water level training data for 1-month lead forecasting. The hybrid MLP-GSA model was evaluated independently with statistical score metrics: coefficient of correlation, coefficient of efficiency, the root mean square and relative root mean square errors, and the Bayesian Information Criterion. The results showed that the hybrid MLP-GSA4 and MLP-GSA5 model (where the 4 and 5months' of lagged input combinations of Lake water level data were ut

关键词： MLP gravitational search algorithm Hybrid models ARMA ARIMA Lake Winnipesaukee Lake Cypress Water level

来源：评论

学校读者我要写书评

暂无评论

Constrained gravitational search algorithm for large scale reservoir operation optimization problem

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2017年 62卷 222-233页

作者： Moeini, R. Soltani-nezhad, M. Daei, M. Univ Isfahan Fac Civil Engn & Transportat Dept Civil Engn Esfahan *** Iran

The gravitational search algorithm (GSA) is used in this paper to solve large scale reservoir operation optimization problem. Here, two constrained versions of GSA are proposed to solve this problem in which masses may be forced to satisfy problem constraints during solution building. This approach is very useful when attempting to solve large scale optimization problem as it will lead to a considerable reduction of the search space size. Here, in the second version of GSA, the storage volume bounds of the reservoir are modified prior to the main search to recognize the infeasible components of the search space and exclude from the search process before the main search starts. Two formulations are also proposed here for each proposed algorithm considering water releases or storage volumes at each operation time period as decision variable of the problem. Proposed algorithms are used to solve the simple and hydropower operation problem of "Dez" reservoir in Iran and the results are presented and compared with using original form of the GSA and any available results. The results indicate the ability of the proposed algorithm and especially the second constrained version of GSA to optimally solve the reservoir operation optimization problem.

关键词： Evolutionary algorithm Optimal operation of reservoir gravitational search algorithm Explicitly constraints handling Water releases Storage volumes

来源：评论

学校读者我要写书评

暂无评论

Hybridization of the gravitational search algorithm and Big Bang-Big Crunch algorithm for Data Clustering

引用

FUNDAMENTA INFORMATICAE 2013年第4期126卷 319-333页

作者： Hatamlou, Abdolreza Hatamlou, Masoumeh Islamic Azad Univ Khoy Branch Tehran Iran

Clustering is a very important technique in knowledge discovery. It has been widely used in data mining, image processing, machine learning, bioinformatics, marketing and other fields. Clustering discern the objects into groups called clusters, based on certain criteria. The similarity of objects is high within the clusters, but low between the clusters. In this work, we investigate a hybridization of the gravitational search algorithm (GSA) and big bang-big crunch algorithm (BB-BC) on data clustering. In the proposed approach, namely GSA-BB, GSA is used to explore the search space for finding the optimal locations of the clusters centroids. Whenever GSA loses its exploration, BB-BC algorithm is used to diversify the population. The performance of the proposed method is compared with GSA, BB-BC and K-means algorithms using six standard and real datasets taken from the UCI machine learning repository. Experimental results indicate that there is significant improvement in the quality of the clusters obtained by the proposed hybrid method over the non-hybrid methods.

关键词： Data Clustering gravitational search algorithm Big Bang-Big Crunch algorithm

来源：评论

学校读者我要写书评

暂无评论

Solution of reactive power dispatch of power systems by an opposition-based gravitational search algorithm

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2014年 55卷 29-40页

作者： Shaw, Binod Mukherjee, V. Ghoshal, S. P. Asansol Engn Coll Dept Elect Engn Asansol W Bengal India Indian Sch Mines Dept Elect Engn Dhanbad 826004 Jharkhand India Natl Inst Technol Dept Elect Engn Durgapur W Bengal India

gravitational search algorithm (GSA) is based on law of gravity and the interaction between masses. In GSA, searcher agents are collection of masses and their interactions are based on Newtonian laws of gravity and motion. In this paper, to further improve the optimization performance of GSA, opposition-based learning is employed in opposition-based gravitational search algorithm (OGSA) for population initialization and also for generation jumping. In the present work, OGSA is applied for the solution of optimal reactive power dispatch (ORPD) of power systems. Traditionally, ORPD is defined as the minimization of active power transmission losses by controlling a number of control variables. ORPD is formulated as a non-linear constrained optimization problem with continuous and discrete variables. In this work, OGSA is used to find the settings of control variables such as generator voltages, tap positions of tap changing transformers and amount of reactive compensation to optimize certain objectives. The study is implemented on IEEE 30-, 57- and 118-bus test power systems with different objectives that reflect minimization of either active power loss or that of total voltage deviation or improvement of voltage stability index. The obtained results are compared to those yielded by the other evolutionary optimization techniques surfaced in the recent state-of-the-art literature including basic GSA. The results presented in this paper demonstrate the potential of the proposed approach and show its effectiveness and robustness for solving ORPD problems of power systems. (C) 2013 The Authors. Published by Elsevier Ltd. All rights reserved.

关键词： gravitational search algorithm Opposition-based learning Optimal reactive power dispatch Power systems Optimization

来源：评论

学校读者我要写书评

暂无评论

Enhance chaotic gravitational search algorithm (CGSA) by balance adjustment mechanism and sine randomness function for continuous optimization problems

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2020年 537卷

作者： Jiang, Jianhua Yang, Xi Meng, Xianqiu Li, Keqin Jilin Univ Finance & Econ Dept Data Sci Changchun 130117 Jilin Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Changchun 130012 Jilin Peoples R China SUNY Coll New Paltz Dept Comp Sci New Paltz NY 12561 USA

The gravitational search algorithm (GSA) is a population-based meta-heuristic optimization algorithm which finds the optimal solution by the law of gravity and attraction between objects. However, as the number of iterations increases, the increase of the quality of the agents makes GSA fall into the local optimal solution more easily, which greatly reduces the exploration capability of the algorithm. Although the chaotic gravitational search algorithm (CGSA) uses chaotic maps for improving diversity to solve this problem, it still has problems with the balance of exploration and exploitation. This paper proposes the balance adjustment based chaotic gravitational search algorithm (BA-CGSA), which introduces the sine randomness function and the balance mechanism to solve the above problem. 30 benchmark functions of IEEE CEC 2014 are adopted to evaluate the performance of the proposed algorithm in terms of exploration and exploitation. Meanwhile, a real engineering design problem is used to illustrate the ability of the algorithm to solve practical application problems. The experimental results demonstrate its good performance in continuous optimization problems. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Optimization algorithm gravitational search algorithm Sine cosine algorithm Balance adjustment mechanism

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：