检索结果-内蒙古大学图书馆

Cognitive Diagnosis-Based Personalized Exercise Group Assembly via a Multi-Objective evolutionary Algorithm

IEEE TRANSACTIONS ON EMERGING TOPICS IN computationAL INTELLIGENCE 2023年第3期7卷 829-844页

作者： Yang, Shangshang Wei, Haoyu Ma, Haiping Tian, Ye Zhang, Xingyi Cao, Yunbo Jin, Yaochu Anhui Univ Sch Artificial Intelligence Key Lab Intelligent Comp & Signal Proc Minist Educ Hefei 230039 Peoples R China Anhui Univ Inst Phys Sci & Informat Technol Key Lab Intelligent Comp & Signal Proc Minist Educ Hefei 230601 Peoples R China Tencent Technol Beijing Co Ltd Beijing 100080 Peoples R China Bielefeld Univ Fac Technol Bielefeld 336019 Germany

Exercise group recommendation plays an important role in many intelligent education tasks. However, existing approaches make recommendations based on the intrinsic features of exercises without considering students' learning abilities, or make selections from several pre-built exercise groups at the expense of flexibility. Furthermore, although many cognitive diagnosis approaches have successfully revealed students' abilities, how to leverage the diagnosis results for exercise group recommendation is hardly explored. To flexibly recommend suitable exercise groups to students, this paper proposes to assemble personalized exercises as a group based on students' abilities, called Personalized Exercise Group Assembly (PEGA). To solve the PEGA task, we first formulate it as a constrained multi-objective problem (CMOP), where three objectives are designed for enabling the assembled exercises to enhance students' abilities on both weak and new knowledge concepts. Then, we devise an extended neural cognitive diagnosis model to learn student's ability/proficiency on all knowledge concepts to compute the weakness consolidation objective. Besides, we propose a dual-encoding and dual-population based co-evolutionary algorithm to tackle the CMOP, where the main population with binary encoding is used to search which exercises are selected, and the auxiliary population with integer encoding is responsible for accelerating the convergence of the main population via guiding offspring generation of the main population. Experiments on three popular datasets demonstrate the effectiveness of exercises assembled by the proposed algorithm compared to state-of-the-art exercise group recommendation approaches, where our assembled exercises can enhance students' proficiency on both poorly mastered and new knowledge concepts.

关键词： Task analysis Statistics Sociology Genetics evolutionary computation computational modeling Adaptation models Exercise group recommendation assemble exercises personalized exercise group assembly multi-objective problem co-evolutionary algorithm

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Deep Decomposition for Overlapping Large-Scale Optimization Problems

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2023年第4期53卷 2374-2386页

作者： Zhang, Xin Ding, Bo-Wen Xu, Xin-Xin Li, Jian-Yu Zhan, Zhi-Hui Qian, Pengjiang Fang, Wei Lai, Kuei-Kuei Zhang, Jun Jiangnan Univ Sch Artificial Intelligence & Comp Sci Jiangsu Key Lab Media Design & Software Technol Wuxi 214122 Peoples R China Ocean Univ China Sch Comp Sci & Technol Qingdao 266100 Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Guangdong Prov Key Lab Computat Intelligence & Cyb Guangzhou 510006 Peoples R China Chaoyang Univ Technol Dept Business Adm Taichung 413 Taiwan Zhejiang Normal Univ Jinhua 321004 Peoples R China Hanyang Univ Ansan 15588 South Korea

Decomposition methods play a critical role in cooperative co-evolutionary algorithms (CCEAs) for solving large-scale optimization problems. Although some well-performing decomposition methods have been designed based on the interactions among variables (IaV), their grouping accuracy is still limited due to the poor performance on the overlapping problems and the computational roundoff errors of IaV in the implementation. To deal with these limitations, a graph-based deep decomposition (GDD) method is proposed to obtain more accurate grouping results, especially for the overlapping problems. On the one hand, the GDD mines the IaV information and obtains the minimum vertex separator of the interaction graph of variables, so as to group variables deeply and recursively. On the other hand, the GDD has the ability of fault tolerance to deal with the computational roundoff errors of IaV and can improve the grouping accuracy. For better experimental studies of overlapping problems, a novel overlapping function generator is designed with the random and complicate overlap type, and two new metrics are proposed to evaluate the grouping accuracy. Comprehensive experiments show that GDD can greatly improve the grouping accuracy and help CCEAs perform better than other existing algorithms, especially on the overlapping problems. In addition, the GDD is highly fault tolerant and can divide problems accurately even on the inaccurate IaV.

关键词： Cooperative co-evolutionary algorithms (CCEAs) decomposition methods evolutionary computation large-scale optimization problems (LSOPs)

来源：评论

学校读者我要写书评

暂无评论

A knowledge learning and random pruning-based memetic algorithm for user route planning in bike-sharing system

引用

MEMETIC COMPUTING 2023年第2期15卷 259-279页

作者： Du, Ke-Jing Li, Jian-Yu Wang, Hua Zhang, Jun Victoria Univ Inst Sustainable Ind & Liveable Cities Melbourne Vic 8001 Australia Hanyang Univ Ansan 15588 South Korea

In a bike-sharing system, the user route planning problem (URPP) is significant because it helps users to plan the route and to choose appropriate intermediate stations to transfer bikes, so as to reduce riding costs. To efficiently solve the URPP, this paper models it as a discrete optimization problem with constraints and proposes a knowledge learning and random pruning-based memetic algorithm (KLRP-MA), with three main contributions. First, the proposed URPP model is from the perspective of users and is suitable for not only static situations but also dynamic situations, which is novel from existing work that mainly focuses on the perspective of bike companies in a static situation. Second, three novel evolutionary operators named knowledge learning-based crossover, random pruning-based mutation, and two-phase local search are proposed and integrated into the KLRP-MA for dealing with the challenges of the URPP. Third, based on the dynamic URPP model, the KLRP-MA is further extended to a dynamic KLRP-MA (DyKLRP-MA) to quickly search for a reasonable route for users when the availability status of the bike stations changes over time, so as to deal with URPP in dynamic situations. Experimental results on 180 generated instances and 10 real-world instances show that when compared with the traditional and state-of-the-art methods, the KLRP-MA and the DyKLRP-MA can find the best solution in a short time. Moreover, in a dynamic situation, the DyKLRP-MA can quickly respond to changes and re-optimize the current planning route.

关键词： Bike-sharing system Memetic algorithm Route planning evolutionary computation Knowledge learning Two-phrase local search

来源：评论

学校读者我要写书评

暂无评论

On the effect of particle update modes in particle swarm optimisation

引用

INTERNATIONAL JOURNAL OF BIO-INSPIRED computation 2023年第4期21卷 230-239页

作者： Dong, Nanjiang Wang, Rui Zhang, Tao Ou, Junwei Natl Univ Def Technol Coll Syst Engn Changsha Peoples R China

Particle swarm optimisation has been successfully applied in various single- and multi-objective optimisation problems. Through the literature review, it is shown that in PSO-based algorithms particles are updated mainly in two different modes. Specifically, the first mode denoted as PSO-a uses random vectors in [0, 1](n) in the particle update process. The second mode denoted as PSO-b uses random variables in [0, 1]. This study systematically analysed the effect of different modes on a varied set of benchmarks. Experimental results show that the PSO-a mode is more suitable for single-objective optimisation while the PSO-b has certain advantages for multi-objective optimisation due to the regularity of multi-objective problems. Also, the introduction of a mutation operator into PSO-b can overcome the limit of dimension. Moreover, to guarantee finding the optimal solution, the swarm size must be larger than the problem dimensionality when PSO-b is purely adopted.

关键词： evolutionary computation particle swarm optimisation PSO population size multi-objective optimisation

来源：评论

学校读者我要写书评

暂无评论

GA Approach to Optimize Training Client Set in Federated Learning

引用

IEEE ACCESS 2023年 11卷 85489-85500页

作者： Kang, Dongseok Ahn, Chang Wook Gwangju Inst Sci & Technol AI Grad Sch Gwangju 61005 South Korea

Federated learning, where the distribution of distributed data is unknown, is more difficult and costly to train a central model with than traditional machine learning. In this study, we propose Federated Learning with Genetic Algorithm, which enables faster central model training at lower cost by providing an appropriate client selection method. A client can have its own communication cost depending on its data sharing preference, and based on this cost and the result of the client's local update, we can select the appropriate combination of clients each round with a genetic algorithm. In each round, the client's combinations are evaluated anew, which are continually explored. To evaluate the algorithm, we distributed the image dataset and communication costs in two ways and conducted federated learning for the image classification model. Experiments showed that the proposed algorithm can find a more efficient client combination and accelerate the training of federated learning.

关键词： Machine learning evolutionary computation federated learning evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

A Multiscenario Optimization evolutionary Algorithm Based on Transfer Framework

引用

IEEE TRANSACTIONS ON evolutionary computation 2023年第6期27卷 1663-1677页

作者： Jiang, Shanlin Yen, Gary G. He, Zhenan Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Oklahoma State Univ Sch Elect & Comp Engn Stillwater OK 74075 USA

Multiscenario optimization problems involve multiple scenarios to be optimized simultaneously, where each scenario corresponds to a multiobjective optimization problem with specific operating conditions. The goal is to find a group of public compromised optimal solutions (PCOSs) achieving compromised optimal in every scenario. This type of optimization problems widely exists in real-world applications, but the research on it is few. In this article, a Multiscenario Optimization evolutionary Algorithm based on a transfer framework is proposed. In one iteration, for each scenario, its knee solutions are recognized as its transfer candidates and are used to construct a constraint hyperplane, which determines whether transfer candidates from other scenarios can be the transferable solutions in this underlying scenario. Then, among all transfer candidates, those accepted by all scenarios are identified as the PCOSs and stored in archive. Afterwards, the archive updating process is applied to guarantee the optimality of solutions in archive and control the size of archive. Finally, each scenario's accepted transferable solutions are utilized in its offspring generation, thus achieving information transfer between different scenarios. Experimental results on a group of benchmark functions verify the superiority of the proposed design in terms of both optimality and computational efficiency over existing approaches.

关键词： Optimization Task analysis evolutionary computation Statistics Sociology Uncertainty Tropical cyclones Knowledge transfer multiobjective evolutionary algorithm (MOEA) multiscenario optimization problem (MSOP)

来源：评论

学校读者我要写书评

暂无评论

LoNAS: Low-Cost Neural Architecture Search Using a Three-Stage evolutionary Algorithm

引用

IEEE computationAL INTELLIGENCE MAGAZINE 2023年第2期18卷 78-93页

作者： Fang, Wei Zhu, Zhenhao Zhu, Shuwei Sun, Jun Wu, Xiaojun Lu, Zhichao Jiangnan Univ Wuxi Peoples R China Sun Yat Sen Univ Guangzhou Peoples R China

Neural architecture search (NAS) has been widely studied to design high-performance network architectures automatically. However, existing approaches require more search time and substantial resource consumption due to their intensive architecture evaluations. Moreover, recently developed NAS algorithms are noncompetitive when combining multiple competing and conflicting objectives, e.g., the test accuracy and the number of parameters. In this paper, a low-cost NAS (LoNAS) method is proposed to address these problems. First, a variable-architecture encoding strategy based on a novel Reg Block is designed to construct high accuracy network architectures with few parameters. Second, a training-free proxy based on the neural tangent kernel (NTK) is proposed to accelerate the search process efficiently. Finally, a three-stage evolutionary algorithm (EA) based on multiple-criteria environmental selection and a set of block-based mutation operators are designed to balance exploration and exploitation better. The experimental results show that LoNAS finds network architectures with competitive performance compared to the state-of-the-art architectures in test accuracy and the number of parameters. Moreover, LoNAS uses less search time and fewer computational resources, consuming only 0.02 GPU Days with one GPU on CIFAR-10 and CIFAR-100. Furthermore, the architectures found by LoNAS on CIFAR-10 and CIFAR-100 exhibit good transferability to ImageNet-16-120, with the test accuracy surpassing that of the state-of-the-art network architectures.

关键词： Costs Graphics processing units Computer architecture evolutionary computation Manuals Network architecture Search problems

来源：评论

学校读者我要写书评

暂无评论

An Improved Many-Objective evolutionary Algorithm for Multi-Satellite Joint Large Regional Coverage

引用

IEEE ACCESS 2023年 11卷 45838-45849页

作者： Li, Feng Wan, Qiuhua He, Qien Zhong, Xing Xu, Kai Zhu, Ruifei Chinese Acad Sci Changchun Inst Opt Fine Mech & Phys Changchun 130033 Peoples R China Univ Chinese Acad Sci Daheng Coll Fine Mech & Phys Beijing 100049 Peoples R China Chang Guang Satellite Technol Co Ltd Changchun 130102 Peoples R China

Multi-satellite joint regional coverage aims to select the optimal combination of satellite resources to acquire the image information of the specified area. Meanwhile, more than three objectives are usually considered simultaneously during this process. Therefore, it is a typical many-objective optimization problem that is NP-hard. Most existing many-objective optimization algorithms cannot preserve extreme solutions due to the failure of Pareto dominance. In this paper, through introducing the idea of S-CDAS into the traditional NSGA-III, an improved many-objective evolutionary algorithm named NSGA-III for extreme solutions preservation (ESP-NSGA-III) is proposed with problem-specific genetic operations to generate regional coverage schemes. A comparative study is conducted with other six state-of-the-art many-objective evolutionary algorithms. Hypervolume (HV) and pure diversity (PD) metrics are used to evaluate the performance of algorithms. The simulation results show that ESP-NSGA-III has good comprehensive performance and improves the diversity of original algorithms. The maximum difference of the coverage rate between ESP-NSGA-III and other six algorithms is 0.2576 so that satisfactory regional coverage scheme can be obtained by ESP-NSGA-III. Our proposed methods are not only applicable to regional coverage tasks, but also have important reference significance for solving other real-world problems.

关键词： Satellite communication evolutionary computation Simulation Resource management Performance evaluation Algorithm design and analysis Many-objective optimization multi-satellite joint NSGA-III regional coverage S-CDAS

来源：评论

学校读者我要写书评

暂无评论

An evolutionary Algorithm With Constraint Relaxation Strategy for Highly Constrained Multiobjective Optimization

引用

IEEE TRANSACTIONS ON CYBERNETICS 2023年第5期53卷 3190-3204页

作者： Sun, Zhichao Ren, Hang Yen, Gary G. Chen, Tianfu Wu, Junjie An, Hongyang Yang, Jianyu Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China Oklahoma State Univ Sch Elect & Comp Engn Stillwater OK 74078 USA

Highly constrained multiobjective optimization problems (HCMOPs) refer to constrained multiobjective optimization problems (CMOPs) with complex constraints and small feasible regions, which are commonly encountered in many real-world applications. Current constraint-handling techniques will face two difficulties when dealing with HCMOPs: 1) feasible solution is hard to be found and too much search effort is spent in locating the feasible region and 2) since the total feasible region of an HCMOP can consist of several disconnected subregions, the search process might be stuck in the comparatively larger feasible subregion, which does not contain the whole Pareto front (PF). To address these two issues, an evolutionary algorithm with constraint relaxation strategy based on differential evolution algorithm, that is, CRS-DE, is proposed in this article. In each generation, the CRS-DE relaxes the constraints by dividing the infeasible solutions into two subpopulations based on total constraint violation, that is, the "semifeasible" subpopulation (SF) and "infeasible" subpopulation (IF), respectively. The SF provides information on the promising regions of finding the feasible solution and is the driving force for convergence toward the PF, while the IF focuses on global exploration for new promising regions. Corresponding reproduction and selection strategies are devised for the SF, IF, and feasible subpopulations, which create a clear division of labor with cooperation to facilitate the search for feasible solutions. To leverage the influence of CRS and prevent the population from premature convergence, a mobility restriction mechanism is developed to restrict the individuals in the SF and IF from entering the feasible subpopulation and enhance the diversity of the whole population. Comprehensive experiments on a series of benchmark test problems and a real-world CMOP demonstrate the competitiveness of our method compared with other representative algorithms in terms of

关键词： Statistics Sociology Search problems Convergence Optimization evolutionary computation Sun Constraint-handling techniques differential evolution evolutionary algorithms multiobjective optimization problems (MOPs)

来源：评论

学校读者我要写书评

暂无评论

A Learning-Based Multipopulation evolutionary Optimization for Flexible Job Shop Scheduling Problem With Finite Transportation Resources

引用

IEEE TRANSACTIONS ON evolutionary computation 2023年第6期27卷 1590-1603页

作者： Pan, Zixiao Wang, Ling Zheng, Jie Chen, Jing-Fang Wang, Xing Tsinghua Univ Dept Automat Beijing 100084 Peoples R China

In many practical manufacturing systems, transportation equipment such as automated guided vehicles (AGVs) is widely adopted to transfer jobs and realize the collaboration of different machines, but is often ignored in current researches. In this article, we address the flexible job shop scheduling problem with finite transportation resources (FJSP-Ts). Considering the difficulties caused by the introduction of transportation and the NP-hard nature, the evolutionary algorithm (EA) is adopted as a solution approach. To this end, a learning-based multipopulation evolutionary optimization (LMEO) is proposed to deal with the FJSP-T. First, the multipopulation strategy is introduced and a cooperation-based initialization is designed by combining several heuristics to guarantee the quality and diversity of the initial population. Second, a reinforcement learning (RL)-based mating selection is proposed to realize the cooperation of different subpopulations by selecting appropriate individuals for evolutionary search. Then, a specific local search inspired by the problem properties is designed to enhance the exploitation capability of the LMEO. Moreover, a statistical learning-based replacement is designed to maintain the quality and diversity of the population. Extensive experiments are conducted to test the performances of the LMEO. The statistical comparison shows that the LMEO is superior to the state-of-the-art algorithms in solving the FJSP-T in terms of solution quality and robustness.

关键词： Transportation Task analysis Job shop scheduling Optimization Statistics Sociology evolutionary computation Finite transportation resource flexible job shop scheduling multipopulation reinforcement learning (RL) statistical learning

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：