检索结果-内蒙古大学图书馆

Decision variable classification based multi-objective multifactorial memetic algorithm for multi-objective multi-task optimization problem

引用

APPLIED SOFT COMPUTING 2024年 152卷

作者： Xu, Zhiwei Xu, Jiafeng Zhang, Kai Xu, Xin He, Juanjuan Wu, Ni Wuhan Univ Sci & Technol Sch Comp Sci & Technol Wuhan 430065 Peoples R China Hubei Prov Key Lab Intelligent Informat Proc & Rea Wuhan 430065 Peoples R China China Univ Geosci Sch Automat Wuhan 430074 Peoples R China

multi-task multi-objective optimization problems need to consider the algorithm's convergence and the population's diversity. The information transfer of decision variables with different characteristics may harm the effect of knowledge reuse. This paper proposes a novel hybrid multi-objective multifactorial memetic algorithm to address this issue. The proposed variable classification method will classify decision variables into convergence-related and diversity-related decision variables. Only the same type of decision variables in the source and target tasks can transfer information to avoid negative transfer. Different evolutionary operators are adopted according to the characteristics of decision variables during individual recombination. In addition, the proposed algorithm hybridizes the immune algorithm as the global evolutionary operator and the evolutionary gradient search algorithm as the local search operator into the multifactorial framework to enhance the searching ability. Finally, the proposed algorithm is compared with the state-of-the-art multi-objective evolutionary multitasking algorithms. The results of the experiments show that the proposed algorithm can achieve promising performance on the classical and complex multi-task multi-objective benchmark test suites.

关键词： evolutionary multitasking multi-objective evolutionary algorithm evolutionary gradient search Decision variable classification multi-objective multi-task optimization problem

来源：评论

学校读者我要写书评

暂无评论

Optimization of RNN-LSTM Model Using NSGA-II algorithm for IOT-based Fire Detection Framework

引用

IETE JOURNAL OF RESEARCH 2024年第7期70卷 6239-6254页

作者： Roy, Tanushree Shome, Saikat kumar Govt India Cent Mech Engn Res Inst Minist Sci & Technol CSIR Durgapur 713209 India

The occurrence of fire leads to unparalleled loss of resources as well as human life and hence, fire detection systems must be trustworthy and less erroneous. Real-time assessment of fire conditions through predictive learning models could lead to easier decision-making and timely rescue operations. Reported works are often restricted to the use of singular rule-based algorithms which can hardly offer a comprehensive solution by adapting to changing dynamics of fire conditions due to their static features, mostly leading to inaccurate classification. In this research, an efficient fire prediction framework has been proposed by efficiently combining the outputs of recurrent neural networks which bear the advantages of short-term predictions with long short-term memory that takes care of long-term predictions. Weights to combine multi-objective optimization functions to minimize mean absolute error and root mean square error have been designed using non-dominated sorting genetic algorithm II (NSGA-II) which offers a lower time complexity. The benchmark dataset from the NIST website has been chosen for analysis and performance validation of the proposed classifier on experimental data pertaining to different fire scenarios. A Pareto optimal front has been obtained from the proposed algorithm which represents the optimum solutions. The performance of the proposed model has been exhaustively evaluated through different factors such as accuracy, RMSE, MAE, F-Measure, binary classification rate, negative predictive value, recall and precision which justifies its contribution. The proposed model reduced RMSE by 14.95-19.88% compared to baseline machine learning models along with an enhanced accuracy of 95.05% and reduced false positive rate which is better compared to reported works along with improvement in F-Measure. Results show that the proposed NSGA-II-based RNN LSTM model accurately predicts the occurrence of fire events with reduced false alarms while maintaining a l

关键词： Fire alarm Long short-term memory multi-objective evolutionary algorithm Nondominated sorting genetic algorithm Recurrent neural network Time series

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning for decision-making under deep uncertainty

引用

JOURNAL OF ENVIRONMENTAL MANAGEMENT 2024年 359卷 120968页

作者： Pei, Zhihao Rojas-Arevalo, Angela M. de Haan, Fjalar J. Lipovetzky, Nir Moallemi, Enayat A. Univ Melbourne Fac Engn & Informat Technol Sch Comp & Informat Syst Melbourne Australia Univ Melbourne Melbourne Ctr Data Sci Melbourne Australia Commonwealth Sci & Ind Res Org CSIRO Melbourne Australia 700 Swanston St Carlton Vic 3053 Australia

Planning under complex uncertainty often asks for plans that can adapt to changing future conditions. To inform plan development during this process, exploration methods have been used to explore the performance of candidate policies given uncertainties. Nevertheless, these methods hardly enable adaptation by themselves, so extra efforts are required to develop the final adaptive plans, hence compromising the overall decisionmaking efficiency. This paper introduces Reinforcement Learning (RL) that employs closed -loop control as a new exploration method that enables automated adaptive policy -making for planning under uncertainty. To investigate its performance, we compare RL with a widely -used exploration method, multi -objective evolutionary algorithm (MOEA), in two hypothetical problems via computational experiments. Our results indicate the complementarity of the two methods. RL makes better use of its exploration history, hence always providing higher efficiency and providing better policy robustness in the presence of parameter uncertainty. MOEA quantifies objective uncertainty in a more intuitive way, hence providing better robustness to objective uncertainty. These findings will help researchers choose appropriate methods in different applications.

关键词： Deep uncertainty Exploratory modeling Reinforcement learning multi-objective evolutionary algorithm Adaptation Robustness

来源：评论

学校读者我要写书评

暂无评论

A data-driven optimisation method for a class of problems with redundant variables and indefinite objective functions

引用

INFORMATION SCIENCES 2024年 656卷

作者： Zhou, Jin Zhou, Kang Zhang, Gexiang Neri, Ferrante Shen, Wangyang Jin, Weiping Wuhan Polytech Univ Sch Math & Comp Sci Wuhan 430023 Peoples R China Chengdu Univ Informat Technol Sch Automat Chengdu 610225 Peoples R China Univ Surrey Sch Comp Sci & Elect Engn NICE Grp Guildford GU27XH England Nanjing Univ Informat Sci & Technol Sch Software Nanjing 210000 Peoples R China Wuhan Polytech Univ Sch Food Sci & Engn Wuhan 430023 Peoples R China

In the realm of practical problem-solving, multi-objective optimisation problems with redundant variables and indefinite objective functions (MOPRVIF) are becoming increasingly prevalent. MOPRVIF involve determining the optimal decision variables that optimise multiple objectives, leveraging the relational data of a set of variables and multiple objectives. For these problems, this paper focuses on the following two issues: one is the demand for a unified computational model to solve this problem;the other is how to improve the algorithm's deep intelligent search capability. In this regard, this paper designs a dual data-driven multi-objective optimisation method. The method used consisted of four parts: elimination of redundant variables (ERV), objective function construction (OFC), selection evolution operator (SEO), and multi-objective evolutionary algorithm (MOEA). MOEA was the main focus of the method. ERV is data preparation and variable selection according to multiple objectives. OFC involves constructing the relationship model between variables and objectives, and a high-accuracy model is important for guaranteeing reliable results. Furthermore, SEO can adjust the evolution operator during a deep search. This is an important guarantee for deep, intelligent search. MOEA combined OFC and SEO to form the final solution algorithm-Dual Data Driven multi-objective evolutionary algorithm (DDMOEA). DDMOEA was explored using two different disciplinary problems of drug compound optimisation and wild blueberry cultivation and benchmarks were selected. The first two problem domains are distinct. The first problem is more complex than the second;however, both encompass redundant variables and indefinite objective functions. Benchmarks are utilised independently to gauge the profound intelligent search capability. The experiments affirm that the dual data -driven optimization approach proposed in this paper is effective, practical, and scalable.

关键词： Data-driven optimisation method multi-objective evolutionary algorithm Adaptive optimisation

来源：评论

学校读者我要写书评

暂无评论

Dynamic multi-objective Optimization of Grid-Connected Distributed Resources Along With Battery Energy Storage Management via Improved Bidirectional Coevolutionary algorithm

引用

IEEE ACCESS 2024年 12卷 58972-58992页

作者： Ali, Asif Liu, Zhizhen Ali, Aamir Abbas, Ghulam Touti, Ezzeddine Nureldeen, Waleed Shandong Univ Sch Elect Engn Jinan 250061 Peoples R China Quaid E Awam Univ Engn Sci & Technol Dept Elect Engn Nawabshah 67450 Sindh Pakistan Southeast Univ Sch Elect Engn Nanjing 210096 Peoples R China Northern Border Univ Coll Engn Dept Elect Engn Ar Ar 73222 Saudi Arabia Univ Business & Technol Coll Engn Dept Gen Subjects Jeddah 23435 Saudi Arabia

This paper explores the synergistic role of Distributed Resources (DR), including Distributed Generation (DG) and Battery Energy Storage Systems (BESS), in enhancing modern power systems' sustainability, reliability, and flexibility. It addresses the gap in concurrent distribution network reconfiguration and DR allocation, especially under the variability of renewable energy. The study aims to minimize energy costs, losses, and voltage deviations by integrating wind and solar PV-type DGs with BESS. A novel multi-objective function and an improved bi-directional coevolutionary (I-BiCo) algorithm are employed to find the optimal RES and BESS placement and sizing, showing marked improvements over existing methods. Furthermore, statistical comparisons using hypervolume, objective function values (diversity), and near-global solutions (convergence) underscore the proposed algorithm's superiority over existing MOEAs. The final non-dominated solution, obtained through fuzzy set theory, highlights simulation results that minimize power loss, achieve substantial energy savings, and smooth demand, particularly with the integration of BESS devices. Moreover, optimal network reconfiguration (ONR) is a key strategy for balancing load demand. Simulation results affirm that minimizing bi-objective and tri-objective functions, coupled with optimal feeder reconfiguration, significantly reduces power loss and enhances voltage profiles, approaching unity across all buses. The proposed ONR formulation, in conjunction with DGs and BESS, maximizes the overall performance of power distribution networks. Furthermore, the paper addresses various time-dependent constraints of BESS, DG, and ONR, formulating and efficiently solving these constraints by integrating different constraint-handling techniques with the proposed multi-objective evolutionary algorithm. The study contributes to academic discourse and provides practical insights for designing more efficient and sustainable power systems

关键词： Distribution network distributed generation battery energy storage system multi-objective evolutionary algorithm

来源：评论

学校读者我要写书评

暂无评论

Protein multiple Conformation Prediction Using multi-objective Evolution algorithm

引用

INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES 2024年第3期16卷 519-531页

作者： Hou, Minghua Jin, Sirong Cui, Xinyue Peng, Chunxiang Zhao, Kailong Song, Le Zhang, Guijun Zhejiang Univ Technol Coll Informat Engn Hangzhou 310023 Peoples R China BioMap & MBZUAI Beijing 100038 Peoples R China

The breakthrough of AlphaFold2 and the publication of AlphaFold DB represent a significant advance in the field of predicting static protein structures. However, AlphaFold2 models tend to represent a single static structure, and multiple-conformation prediction remains a challenge. In this work, we proposed a method named multiSFold, which uses a distance-based multi-objective evolutionary algorithm to predict multiple conformations. To begin, multiple energy landscapes are constructed using different competing constraints generated by deep learning. Subsequently, an iterative modal exploration and exploitation strategy is designed to sample conformations, incorporating multi-objective optimization, geometric optimization and structural similarity clustering. Finally, the final population is generated using a loop-specific sampling strategy to adjust the spatial orientations. multiSFold was evaluated against state-of-the-art methods using a benchmark set containing 80 protein targets, each characterized by two representative conformational states. Based on the proposed metric, multiSFold achieves a remarkable success ratio of 56.25% in predicting multiple conformations, while AlphaFold2 only achieves 10.00%, which may indicate that conformational sampling combined with knowledge gained through deep learning has the potential to generate conformations spanning the range between different conformational states. In addition, multiSFold was tested on 244 human proteins with low structural accuracy in AlphaFold DB to test whether it could further improve the accuracy of static structures. The experimental results demonstrate the performance of multiSFold, with a TM-score better than that of AlphaFold2 by 2.97% and RoseTTAFold by 7.72%. The online server is at http://***/multiSFold.

关键词： Protein structure prediction multiple conformational states multi-objective evolutionary algorithm

来源：评论

学校读者我要写书评

暂无评论

Active broad learning with multi-objective evolution for data stream classification

引用

COMPLEX & INTELLIGENT SYSTEMS 2024年第1期10卷 899-916页

作者： Cheng, Jian Zheng, Zhiji Guo, Yinan Pu, Jiayang Yang, Shengxiang China Coal Res Inst Res Inst Mine Big Data Beijing 100013 Peoples R China Tiandi Sci & Technol Co Ltd Beijing 100013 Peoples R China China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Peoples R China Minist Educ China Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China China Univ Min & Technol Beijing Sch Mech Elect & Informat Engn Beijing 100083 Peoples R China Montfort Univ Sch Comp Sci & Informat Leicester LE1 9BH England

In a streaming environment, the characteristics and labels of instances may change over time, forming concept drifts. Previous studies on data stream learning generally assume that the true label of each instance is available or easily obtained, which is impractical in many real-world applications due to expensive time and labor costs for labeling. To address the issue, an active broad learning based on multi-objective evolutionary optimization is presented to classify non-stationary data stream. The instance newly arrived at each time step is stored to a chunk in turn. Once the chunk is full, its data distribution is compared with previous ones by fast local drift detection to seek potential concept drift. Taking diversity of instances and their relevance to new concept into account, multi-objective evolutionary algorithm is introduced to find the most valuable candidate instances. Among them, representative ones are randomly selected to query their ground-truth labels, and then update broad learning model for drift adaption. More especially, the number of representative is determined by the stability of adjacent historical chunks. Experimental results for 7 synthetic and 5 real-world datasets show that the proposed method outperforms five state-of-the-art ones on classification accuracy and labeling cost due to drift regions accurately identified and the labeling budget adaptively adjusted.

关键词： Concept drift Data stream mining Broad learning system Active learning multi-objective evolutionary algorithm

来源：评论

学校读者我要写书评

暂无评论

An optimization capacity design method of household integrated energy system based on multi-objective egret swarm optimization

引用

IET RENEWABLE POWER GENERATION 2023年第8期17卷 1993-2008页

作者： Liu, Yakui Yu, Chenhui Li, Dejun Wang, Longquan Li, Xing Li, Hongyun Wang, Fengchao Qingdao Univ Technol Sch Mech & Automot Engn Qingdao Peoples R China Xi An Jiao Tong Univ State Key Lab Elect Insulat & Power Equipment Xian Peoples R China

The construction of a household integrated energy system will reduce greenhouse gas emissions and promote sustainable development. Firstly, a household energy system is proposed, which consists of a photovoltaic, wind turbine, electrolysis cell, hydrogen storage tank, and hydrogen-fired gas turbine. The proposed system is modelled as a bi-objective optimization problem in which the minimum daily system economic cost, and the minimum loss of energy supply probability. Secondly, a novel multi-objective egret swarm optimization algorithm with strong search capability and fast convergence is proposed. Thirdly, a household load corresponding to a typical day in spring is chosen as the study case. The optimization results show that the daily system economic cost with the optimal number of devices is 97.48 RMB, and the loss of energy supply probability is 8.33% at the lowest. Finally, to validate the efficiency of the proposed method, the proposed method is compared with NSGA-II (a widely used multi-objective evolutionary algorithm). The comparison indicates that the proposed method has a better diversity due to the random searchability. As a consequence, the proposed method can be used in the optimization capacity design of the integrated energy system.

关键词： energy management systems energy storage multi-objective evolutionary algorithm

来源：评论

学校读者我要写书评

暂无评论

Applying the new multi-objective algorithms for the operation of a multi-reservoir system in hydropower plants

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-27页

作者： Hashemi, Syed Mohsen Samare Robati, Amir Kazerooni, Mohammad Ali Islamic Azad Univ Dept Civil Engn Kerman Branch Kerman Iran

The optimal operation of the multi-purpose reservoir system is a difficult, and, sometimes, non-linear problem in multi-objective optimization. By simulating biological behavior, meta-heuristic algorithms scan the decision space and can offer a set of points as a group of solutions to a problem. Because it is essential to simultaneously optimize several competing objectives and consider relevant constraints as the main problem in many optimization problems, researchers have improved their ability to solve multi-objective problems by developing complementary multi-objective algorithms. Because the AHA algorithm is new, its multi-objective version, MOAHA (multi-objective artificial hummingbird algorithm), was used in this study and compared with two novel multi-objective algorithms, MOMSA and MOMGA. Schaffer and MMF1 were used as two standard multi-objective benchmark functions to gauge the effectiveness of the proposed method. Then, for 180 months, the best way to operate the reservoir system of the Karun River basin, which includes Karun 4, Karun 3, Karun 1, Masjed-e-Soleyman, and Gotvand Olia dams to generate hydropower energy, supply downstream demands (drinking, agriculture, industry, environmental), and control flooding was examined from September 2000 to August 2015. Four performance appraisal criteria (GD, S, Delta, and MS) and four evaluation indices (reliability, resiliency, vulnerability, and sustainability) were used in Karun's multi-objective multi-reservoir problem to evaluate the performance of the multi-objective algorithm. All three algorithms demonstrated strong capability in criterion problems by using multi-objective algorithms' criteria and performance indicators. The large-scale (1800 dimensions) of the multi-objective operation of the Karun Basin reservoir system was another problem. With a minimum of 1441.71 objectives and an average annual hydropower energy manufacturing of 17,166.47 GW, the MOAHA algorithm demonstrated considerable ability co

关键词： multi-objective evolutionary algorithm multi-reservoir systems Karun basin

来源：评论

学校读者我要写书评

暂无评论

A fast nondominated sorting-based MOEA with convergence and diversity adjusted adaptively

引用

JOURNAL OF SUPERCOMPUTING 2024年第2期80卷 1426-1463页

作者： Gao, Xiaoxin He, Fazhi Zhang, Songwei Luo, Jinkun Fan, Bo Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Zhengzhou Inst Elect & Mech Engn Zhengzhou 450015 Peoples R China Wuhan Univ Inst Sci & Technol Dev Wuhan 430072 Peoples R China

In the past few decades, to solve the multi-objective optimization problems, many multi-objective evolutionary algorithms (MOEAs) have been proposed. However, MOEAs have a common difficulty: because the diversity and convergence of solutions are often two conflicting conditions, the balance between the diversity and convergence directly determines the quality of the solutions obtained by the algorithms. Meanwhile, the nondominated sorting method is a costly operation in part Pareto-based MOEAs and needs to be optimized. In this article, we propose a multi-objective evolutionary algorithm framework with convergence and diversity adjusted adaptively. Our contribution is mainly reflected in the following aspects: firstly, we propose a nondominated sorting-based MOEA framework with convergence and diversity adjusted adaptively;secondly, we propose a novel fast nondominated sorting algorithm;thirdly, we propose a convergence improvement strategy and a diversity improvement strategy. In the experiments, we compare our method with several popular MOEAs based on two widely used performance indicators in several multi-objective problem test instances, and the empirical results manifest the proposed method performs the best on most test instances, which further demonstrates that it outperforms all the comparison algorithms.

关键词： Nondominated sorting multi-objective evolutionary algorithm Convergence Diversity Adjusted adaptively

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：