检索结果-内蒙古大学图书馆

A dynamic multi-objective optimization algorithm based on probability-driven prediction and correlation-guided individual transfer

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-47页

作者： Ge, Fangzhen Zhao, Xuan Chen, Debao Shen, Longfeng Liu, Huaiyu Huaibei Normal Univ Sch Comp Sci & Technol Huaibei 235000 Peoples R China Huaibei Normal Univ Anhui Engn Res Ctr Intelligent Comp & Applicat Cog Huaibei 235000 Peoples R China Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei Peoples R China Huaibei Normal Univ Sch Phys & Elect Informat Huaibei 235000 Peoples R China

The primary challenge in addressing dynamic multi-objective optimization problems (DMOPs) is the rapid tracking of optimal solutions. Although methods based on transfer learning have shown remarkable performance in tackling DMOPs, most existing methods overlook the potential relationships between individuals within the population and those from historical environments. Consequently, they fail to adequately exploit historical information. To this end, this study proposes a dynamic multi-objective optimization algorithm based on probability-driven prediction and correlation-guided individual transfer (PDP&CGIT), which consists of two strategies: probability-driven prediction (PDP) and correlation-guided individual transfer (CGIT). Specifically, the PDP strategy analyzes the distribution of population characteristics and constructs a discriminative predictor based on a probability-annotation matrix to classify high-quality solutions from numerous randomly generated solutions within the decision space. Moreover, from the perspective of individual evolution, the CGIT strategy analyzes the correlation between current elite individuals and those from the previous moment. It learns the dynamic change pattern of the individuals and transfers this pattern to new environments. This is to maintain the diversity and distribution of the population. By integrating the advantages of these two strategies, PDP&CGIT can efficiently respond to environmental changes. Extensive experiments were performed to compare the proposed PDP&CGIT with five state-of-the-art algorithms across the FDA, F, and DF test suites. The results demonstrated the superiority of PDP&CGIT.

关键词： Dynamic multi-objective optimization Transfer learning evolutionary algorithms Prediction

来源：评论

学校读者我要写书评

暂无评论

Multi-objective optimization of work package scheme problem to minimize project carbon emissions and cost

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2025年 200卷

作者： Zhang, Yaning Li, Xiao Teng, Yue Shen, Geoffrey Q. P. Bai, Sijun Hong Kong Polytech Univ Dept Bldg & Real Estate Hong Kong Peoples R China Northwestern Polytech Univ Sch Management Xian Peoples R China Univ Hong Kong Dept Civil Engn Hong Kong Peoples R China

The construction industry accounts for around 30% of global energy consumption and 33% of CO2 emissions. For the carbon neutrality initiative, reducing carbon emissions from construction projects become a critical objective for project success. However, a dilemma arises in balancing carbon emissions and project cost, particularly during the work package-based project planning phase. To address this issue, this article presents a novel multiobjective optimization model for the work package scheme problem, aimed at minimizing both project carbon emissions and cost. Multi-objective evolutionary algorithms (EAs) are developed to solve the model. Firstly, a multi-objective Mixed-Integer Programming (MIP) model is developed to establish the functional relation between work package attributes (duration and work content) and optimization objectives (carbon emissions and cost). Secondly, two multi-objective optimization EAs, NSGA-II and SPEA2, are developed to obtain the Pareto frontier. The experimental results indicate that NSGA-II and SPEA2 exhibit superior trade-off capabilities compared to the Gurobi and the state-of-the-art heuristic algorithm. Compared to Gurobi, the proposed EAs achieve an approximately 68% reduction in carbon emissions, accompanied by about an 11% cost increase. Compared to the heuristic algorithm, the EAs achieve around 10% reductions in carbon emissions with an approximately 5% cost increase. Additionally, sensitivity analysis conducted on a project instance dataset demonstrates the robustness of the proposed model and algorithms. This article paves the way for achieving lowcarbon and sustainable construction project management in the context of carbon neutrality.

关键词： Multi-objective optimization Project planning Work packages Carbon emissions evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Totipotent neural controllers for modular soft robots: Achieving specialization in body-brain co-evolution through Hebbian learning

引用

NEUROCOMPUTING 2025年 614卷

作者： Ferigo, Andrea Iacca, Giovanni Medvet, Eric Nadizar, Giorgia Univ Trento Dept Informat Engn & Comp Sci Trento Italy Univ Trieste Dept Engn & Architecture Trieste Italy Univ Trieste Dept Math & Geosci Trieste Italy

Multi-cellular organisms typically originate from a single cell, the zygote, that then develops into a multitude of structurally and functionally specialized cells. The potential of generating all the specialized cells that make up an organism is referred to as cellular "totipotency", a concept introduced by the German plant physiologist Haberlandt in the early 1900s. In an attempt to reproduce this mechanism in synthetic organisms, we present a model based on a kind of modular robot called Voxel-based Soft Robot (VSR), where both the body, i.e ., the arrangement of voxels, and the brain, i.e ., the Artificial Neural Network (ANN) controlling each module, are subject to an evolutionary process aimed at optimizing the locomotion capabilities of the robot. In an analogy between totipotent cells and totipotent ANN-controlled modules, we then include in our model an additional level of adaptation provided by Hebbian learning, which allows the ANNs to adapt their weights during the execution of the locomotion task. Our in silico experiments reveal two main findings. Firstly, we confirm the common intuition that Hebbian plasticity effectively allows better performance and adaptation. Secondly and more importantly, we verify for the first time that the performance improvements yielded by plasticity are in essence due to a form of specialization at the level of single modules (and their associated ANNs): thanks to plasticity, modules specialize to react indifferent ways to the same set of stimuli, i.e ., they become functionally and behaviorally different even though their ANNs are initialized in the same way. This mechanism, which can be seen as a form of totipotency at the level of ANNs, can have, in our view, profound implications in various areas of Artificial Intelligence (AI) and applications thereof, such as modular robotics and multi-agent systems.

关键词： Hebbian learning Neural plasticity Voxel-based Soft Robots evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Synchronous Remote Calibration for Electricity Meters: Application and Optimization

引用

APPLIED SCIENCES-BASEL 2025年第3期15卷

作者： Zha, Zhiyong Ge, Hanfang Zou, Chengcheng Long, Fei He, Xingfeng Wu, Geng Dong, Chenxi Deng, Tianping Xu, Jiaxiang State Grid Hubei Informat & Telecommun Co Wuhan 430048 Peoples R China Huazhong Univ Sci & Technol Sch Elect Informat & Commun Hubei Key Lab Smart Internet Technol Wuhan 430074 Peoples R China

Remote calibration is an advanced methodology that leverages electricity meters, intelligent detection, and computing technologies to enhance calibration efficiency and precision significantly. However, current research predominantly focuses on isolated calibration architectures tailored to single-laboratory environments. In contrast, distributed remote calibration systems that integrate multiple nodes remain in their early developmental stages, despite their considerable potential for improving scalability and operational efficiency. The purpose of this paper is to propose a multi-point collaborative distributed remote calibration model that improves scalability and operational efficiency for remote sensing devices. It addresses the challenge of resource allocation for synchronous calibration across distributed nodes by introducing a hybrid genetic algorithm that optimises scheduling and resource management. Experimental results reveal that the proposed algorithm surpasses other comparable methods in its category, highlighting its capability to improve resource efficiency in distributed remote calibration systems. Additionally, the hybrid genetic algorithm offers profound insights and effective solutions to the intricate challenges of task scheduling in dual-container synchronisation, enhancing both scheduling performance and system dependability.

关键词： calibration systems distributed systems resource management evolutionary algorithms task scheduling

来源：评论

学校读者我要写书评

暂无评论

Phase-Based Neuron Training using evolutionary algorithms

Phase-Based Neuron Training using Evolutionary Algorithms

引用

2014 International Symposium on Fundamentals of Electrical Engineering (ISFEE)

作者： Stanescu, Sorin Laurentiu Otanocha, Omonigho Benedict Univ Manchester Manchester M13 9PL Lancs England

ISBN: (纸本)9781479968213

Complex Valued Neural Networks play an increasing role in machine learning due to their capability to characterize intricate problems and to their appropriateness to engineering fields which use complex number or phasor representations. This paper presents a new method for training the Phase-Based Neurons, a new type of Complex Valued Neural Networks that uses just the phase of the complex activation for operation and representation. The paper investigates also the capabilities this type of neural network to solve the N bit parity problem and its efficiency in doing this.

关键词： artificial neural networks phase-based neuron evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Features Are Effective for Multi-Modal Classification: An Architecture Search Viewpoint

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第2期35卷 1070-1083页

作者： Fu, Pinhan Liang, Xinyan Qian, Yuhua Guo, Qian Zhang, Yayu Huang, Qin Tang, Ke Shanxi Univ Inst Big Data Sci & Ind Taiyuan 030006 Shanxi Peoples R China Taiyuan Univ Sci & Technol Sch Comp Sci & Technol Taiyuan 030024 Shanxi Peoples R China Southern Univ Sci & Technol Shenzhen Key Lab Comp Intelligence Shenzhen 518055 Guangdong Peoples R China Southern Univ Sci & Technol Dept Comp Sci & Engn Shenzhen 518055 Guangdong Peoples R China

Multi-modal neural architecture search (MNAS) is an effective approach to obtain task-adaptive multi-modal classification models. Deep neural networks, as currently main-stream feature extractors, can provide hierarchical features for each modality. Existing MNAS methods face difficulty in exploiting such hierarchical features due to their different form coexistence such as tensorial multi-scale features and vectorized penultimate features. Moreover, existing methods always focus on the evolution of fusion operators or vectorized features of all modalities, constraining search space. In this paper, a novel two-stage method called multi-modal multi-scale evolutionary neural architecture search (MM-ENAS) is proposed. The first stage unifies the representation form of hierarchical features by the proposed evolutionary statistics strategy. The second stage identifies the optimal combination of basic fusion operations for all unified hierarchical features by the evolutionary algorithm. MM-ENAS increases search space by simultaneously searching for feature statistical extraction methods, basic fusion operators and feature representation set consisting of tensorial multi-scale features and vectorized penultimate features. Experimental results on three multi-modal tasks demonstrate that the proposed method achieves competitive performance in terms of accuracy, search time, and number of parameters compared to existing representative MNAS methods. Additionally, the method exhibits fast adaptation to various multi-modal tasks.

关键词： Feature extraction Vectors Computer architecture Adaptation models Tensors Computational modeling Manuals Data mining Circuits and systems Transforms Multi-modal fusion feature statistics neural architecture search evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

2-Step evolutionary Algorithm for the generation of dungeons with lock door missions using horizontal symmetry

2-Step Evolutionary Algorithm for the generation of dungeons...

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Dumont, Felipe Cristina Riff, Maria Univ Tecn Federico Santa Maria Valparaiso Chile

ISBN: (纸本)9798400704949

This paper introduces a novel two-step evolutionary algorithm (2-Step EA) for the procedural generation of dungeons in video games. Our approach is designed to address the complex challenge of generating dungeons that are not only structurally coherent and navigable with strategically placed keys and barriers. The algorithm divides the dungeon generation process in two phases: the initial phase focuses on the formation of dungeon layout considering room quantity and linear coefficient and the second phase deals with the allocation of keys and barriers within this structure. We compare our algorithm with existing methods, emphasizing efficiency and adherence to specified dungeon parameters. Our results show the effectiveness of the 2-Step EA in generating diverse and engaging dungeons. This research contributes to the field of procedural content generation in games, offering insights into the optimization of dungeon generation algorithms.

关键词： evolutionary algorithms Games Entertainment and media

来源：评论

学校读者我要写书评

暂无评论

A generalized bilevel optimization model for large-scale task scheduling in multiple agile earth observation satellites

引用

KNOWLEDGE-BASED SYSTEMS 2025年 309卷

作者： Chen, Jiawei Wang, Feiran Chen, Yingguo He, Lei Du, Yonghao Wu, Jian Chen, Yingwu Natl Univ Def Technol Coll Syst Engn Changsha 410073 Peoples R China Xidian Univ Hangzhou Res Inst Hangzhou 310000 Peoples R China

Scheduling large-scale tasks within a multi-agile earth observation satellite system poses a formidable challenge. Given the complexity of this optimization problem, the responding solving strategy should exhibit both efficiency and effectiveness in terms of computational time and solution quality. The current strategies can broadly be categorized into all-in-one and two-stage methodologies. The latter, more conducive to real- world scenarios, owing to reducing the problem complexity and practical operational flexibility, dissects this challenge into task allocation and single-satellite scheduling. However, existing two-stage strategies still consider the objectives and constraints at the equivalent level and only adapt to specific algorithms. In this way, the pivotal issues concerning the solution complexity and strategy compatibility remain fundamentally unaddressed. To address this limitation, we proposed a generalized bilevel optimization model called Question- and-Answer model, which establishes two distinct optimization model with different contains and objectives. In this model, the upper questions are highly indispensable in the response from the lower level and constraints are considered separately at two stages. To ascertain the generalization of this framework, we conduct a comprehensive range of experiments employing various proposed strategies and algorithms in two stages. Diverse algorithms ranging from heuristic principles, and evolutionary strategies, to reinforcement learning can be seamlessly combined and integrated within this framework. The results demonstrate that the scale of scenarios does not affect the effectiveness of any amalgamated algorithms within this framework. Furthermore, the transition of upper questions according to the lower answers indeed improves the objectives but concurrently intensify the computational time.

关键词： Large-scale scheduling evolutionary algorithms Reinforcement learning Bilevel optimization

来源：评论

学校读者我要写书评

暂无评论

PCA-ENHANCED METAMODEL-ASSISTED evolutionary algorithms FOR AERODYNAMIC OPTIMIZATION 11

PCA-ENHANCED METAMODEL-ASSISTED EVOLUTIONARY ALGORITHMS FOR ...

引用

11th World Congress on Computational Mechanics (WCCM) / 5th European Conference on Computational Mechanics (ECCM) / 6th European Conference on Computational Fluid Dynamics (ECFD)

作者： Asouti, Varvara G. Kyriacou, Stylianos A. Giannakoglou, Kyriakos C. Natl Tech Univ Athens Parallel CFD & Optimizat Unit Iroon Polytechniou 9 Athens 15780 Greece

ISBN: (纸本)9788494284472

This paper deals with evolutionary algorithms (EAs) assisted by surrogate evaluation models or metamodels (Metamodel-Assisted EAs, MAEAs) which are further accelerated by exploiting the Principal Component Analysis (PCA) of the elite members of the evolving population. PCA is used to (a) guide the application of evolution operators and (b) train metamodels, in the form of radial basis functions networks, on patterns of smaller dimension. Compared to previous works by the same authors, this paper also proposes a new way to apply the PCA technique. In particular, the front of non-dominated solutions is divided into sub-fronts and the PCA is applied "locally" to each sub-front. The proposed method is demonstrated in multi-objective, constrained, aerodynamic optimization problems.

关键词： evolutionary algorithms Metamodels Principal Component Analysis Optimization Aerodynamics

来源：评论

学校读者我要写书评

暂无评论

Cooperative, collaborative, coevolutionary multi-objective optimization on CPU-GPU multi-core

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-26页

作者： Sun, Zhuoran Liu, Ying Ying Thulasiraman, Parimala Univ Manitoba Dept Comp Sci 66 Chancellors Circle Winnipeg MB R3T2N2 Canada

Coevolutionary multi-objective heuristics solve multi-objective optimization problems by evolving two different heuristics, simultaneously while exchanging information to produce diverse solutions and faster convergence. However, evolving two algorithms concurrently is computationally intensive and slow. In this research article, we study the parallelization of Cooperative, Concurrent, Coevolutionary for Multi-objective Optimization (COMO3\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\text{CO}}_{{{\text{MO}}}}<^>{{\textevolutionary}}$$\end{document}) algorithm, designed for dynamic problems. The two evolutionary algorithms, Non-dominated Sorting Genetic Algorithm II (NSGA-II) and Multi-objective evolutionary Algorithm based on Decomposition (MOEA/D) are parallelized on GPU and CPU architectures, respectively. The populations in MOEA/D are further partitioned forming an island topology to preserve diversity. Using the bi-objective traveling salesperson benchmark dataset, we analyze the performance of the individual algorithms and coevolutionary algorithm with respect to time and accuracy of the results.

关键词： Multi-core architectures evolutionary algorithms Parallel computing Multi-objective optimization

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：