检索结果-内蒙古大学图书馆

Automated vehicles in swarm configuration: Simulation and analysis

NEUROCOMPUTING 2022年 501卷 679-693页

作者： Echeto, Javier Santos, Matilde Romana, Manuel G. Natl Distance Univ UNED Comp Sci Sch Madrid 28040 Spain Univ Complutense Madrid Inst Knowledge Technol Madrid 28040 Spain Univ Politecn Madrid Escuela Ingn Caminos Madrid 28040 Spain

Driving automation is becoming an increasing trend in the automotive industry as vehicles become more and more intelligent, while information is shared among them and with the infrastructure via wireless communication. Vehicle organization in swarms is considered an interesting approach for future traffic management, since it could significantly improve road efficiency and safety, while saving resources and increasing system resiliency. In this work, modelling and simulation of swarm traffic flow have been addressed. A decision support simulation tool for swarm intelligence traffic flow modelling including different types of vehicles and roads has been implemented using MATLAB. Functionalities such as driving, lane changing, overtaking and swarm cooperation are included. The behaviour of swarms of multi-brand platooning vehicles on different roads and driving conditions has been analyzed. The parameters that define the automated vehicle swarm have also been studied, such as its size, desired speed, inter vehicle distance, etc., and how the swarm configuration depends on the application (highway traffic, traffic jam assist, ...). The result of this research shows how traffic flow can be maximized when vehicles are managed in a swarm configuration. (c) 2022 Published by Elsevier B.V.

关键词： evolutionary computation Swarm intelligence Platooning Car-following Automated vehicle Traffic management Traffic simulation

来源：评论

学校读者我要写书评

暂无评论

Deep evolutionary Learning for Molecular Design

引用

IEEE computationAL INTELLIGENCE MAGAZINE 2022年第2期17卷 14-28页

作者： Grantham, Karl Mukaidaisi, Muhetaer Ooi, Hsu Kiang Ghaemi, Mohammad Sajjad Tchagang, Alain Li, Yifeng Brock Univ St Catharines ON Canada Natl Res Council Canada Ottawa ON Canada

In this paper, a prototypical deep evolutionary learning (DEL) process is proposed to integrate deep generative model and multi-objective evolutionary computation for molecular design. Our approach enables (1) evolutionary operations in the latent space of the generative model, rather than the structural space, to generate promising novel molecular structures for the next evolutionary generation, and (2) generative model fine-tuning using newly generated high-quality samples. Thus, DEL implements a data-model co-evolution concept which improves both sample population and generative model learning. Experiments on public datasets indicate that the sample population obtained by DEL exhibits improvement on property distributions, and dominates samples generated by other baseline molecular optimization algorithms. Furthermore, comparisons with a range of deep generative models show that DEL is beneficial for improving sample populations.

关键词： computational modeling Social factors evolutionary computation Statistics Optimization Deep learning Generative adversarial networks Molecular computing

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Deep Reinforcement Learning for Recommendation Systems

引用

IEEE ACCESS 2022年 10卷 65011-65027页

作者： Keat, Ee Yeo Sharef, Nurfadhlina Mohd Yaakob, Razali Kasmiran, Khairul Azhar Marlisah, Erzam Mustapha, Norwati Zolkepli, Maslina Univ Putra Malaysia Dept Comp Sci Upm Serdang Selangor Malaysia

Most existing recommendation systems (RSs) are primarily concerned about the accuracy of rating prediction and only recommending popular items. However, other non-accuracy metrics such as novelty and diversity should not be overlooked. Existing multi-objective (MO) RSs employed collaborative filtering and combined with evolutionary algorithms to handle bi-objective optimization. Besides cold-start problem from collaborative filtering, it also vulnerable to highly sparse environment, while the evolutionary algorithm suffers from premature convergence and curse of dimensionality. These limitations have prompted this work to propose deep reinforcement learning (DRL) approaches for MO optimization in RSs. Several works in DRL are available but none has addressed MO RS problems. In this study, the performances of proposed DRL approaches that based on Deep Q-Network in MO recommendation problem were investigated. The approaches were evaluated with movie recommendation dataset by using three conflicting metrics, namely precision, novelty, and diversity. The results demonstrated that deep reinforcement learning approaches has superiority performance in MO optimization, and its capability of recommending precise item along with achieving high novelty and diversity against the benchmark that using probabilistic based multi-objective approach based on evolutionary algorithm (PMOEA). Although PMOEA algorithm secured higher average value in precision, it has lower values of novelty and diversity than the proposed DRL approaches. The DRL approaches surpassed the benchmark results in average of maximum novelty and the average of mean diversity metrics, the optimization between accuracy and non-accuracy metrics is inevitable. In addition, the experiments revealed that incorporation of user latent features enhanced the recommendation quality.

关键词： Optimization Measurement Genetic algorithms evolutionary computation Convergence Motion pictures Licenses Deep reinforcement learning machine learning multiobjective recommendation system

来源：评论

学校读者我要写书评

暂无评论

GOZDE: A novel metaheuristic algorithm for global optimization

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2022年 136卷 128-152页

作者： Kuyu, Yigit Cagatay Vatansever, Fahri Bursa Uludag Univ Elect Elect Engn Dept Bursa Turkey

This study proposes a new metaheuristic algorithm, called "Geometric Octal Zones Distance Estimation" (GOZDE) algorithm to solve global optimization problems. The presented GOZDE employs a search scheme with the information sharing between the zones considering the distance of the zones utilizing median values. The whole population represents the eight zones that are the combination of different search strategies to guide knowledge dissemination from one zone to others in the search space. To demonstrate the effectiveness of the proposed optimizer, it is compared with two classes of metaheuristics, which are (1) GA, PSO, DE, CS and HS as the classical metaheuristics and (2) BWO, SSA, MVO, HHO, ChOA, AOA and EBOwithCMAR as the up-to-date metaheuristics. The search capability of the proposed algorithm is tested on two different numerical benchmark sets including low and high dimensional problems. The developed algorithm is also adapted to ten realworld applications to handle constraint optimization problems. In addition, to further analyse the results of the proposed algorithm, three well-known statistical metrics, Friedman, Wilcoxon ranksum and Whisker-Box statistical tests are conducted. The experimental results statistically show that GOZDE is significantly better than, or at least comparable to the twelve metaheuristic algorithms with outstanding performance in solving numerical functions and real-world optimization problems. (C) 2022 Elsevier B.V. All rights reserved.

关键词： evolutionary computation Global optimization Real-world problems Metaheuristic algorithms Population-based method GOZDE

来源：评论

学校读者我要写书评

暂无评论

Action Command Encoding for Surrogate-Assisted Neural Architecture Search

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 2022年第3期14卷 1129-1142页

作者： Tian, Ye Peng, Shichen Yang, Shangshang Zhang, Xingyi Tan, Kay Chen Jin, Yaochu Anhui Univ Inst Phys Sci & Informat Technol Minist Educ Key Lab Intelligent Comp & Signal Proc Hefei 230601 Peoples R China Anhui Univ Sch Comp Sci & Technol Minist Educ Key Lab Intelligent Comp & Signal Proc Hefei 230601 Peoples R China Anhui Univ Sch Artificial Intelligence Minist Educ Key Lab Intelligent Comp & Signal Proc Hefei 230601 Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China Univ Surrey Dept Comp Sci Guildford GU2 7XH Surrey England

With the development of neural architecture search, the performance of deep neural networks has been considerably enhanced with less human expertise. While the existing work mainly focuses on the development of optimizers, the design of encoding scheme is still in its infancy. This article thus proposes a novel encoding scheme for neural architecture search, termed action command encoding (ACEncoding). Inspired by the gene expression process, ACEncoding defines several action commands to indicate the addition and clone of layers, connections, and local modules, where an architecture grows from empty according to multiple action commands. ACEncoding provides a compact and rich search space that can be explored by various optimizers efficiently. Furthermore, a surrogate-assisted performance evaluator is tailored for ACEncoding, termed sequence-to-rank (Seq2Rank). By integrating the Seq2Seq model with RankNet, Seq2Rank embeds the variable-length encoding of ACEncoding into a continuous space, and then predicts the rankings of architectures based on the continuous representation. In the experiments, ACEncoding brings improvement to neural architecture search with existing encoding schemes and Seq2Rank shows better accuracy than existing performance evaluators. The neural architectures obtained by ACEncoding and Seq2Rank have competitive test errors and complexities on image classification tasks, and also show high transferability between different data sets.

关键词： Computer architecture Encoding Topology Optimization evolutionary computation Task analysis Reinforcement learning Encoding scheme neural architecture search optimizer performance evaluator

来源：评论

学校读者我要写书评

暂无评论

evolutionary Dual-Ensemble Class Imbalance Learning for Human Activity Recognition

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN computationAL INTELLIGENCE 2022年第4期6卷 728-739页

作者： Guo, Yinan Chu, Yaoqi Jiao, Botao Cheng, Jian Yu, Zekuan Cui, Ning Ma, Lianbo China Univ Min & Technol Beijing Sch Mech & Informat Engn Beijing 100083 Peoples R China China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Jiangsu Peoples R China China Coal Res Inst Xuzhou 100083 Jiangsu Peoples R China Fudan Univ Acad Engn & Technol Shanghai 200433 Peoples R China Northeastern Univ Coll Software Shenyang 110819 Peoples R China

Human activity recognition is an imbalance classification problem in essence since various human actions may occur at different frequencies. Traditional ensemble class imbalance learning methods integrate resampling technique with multi-classifier models, which obtain better generalization than single ones. However, the number of base classifiers is often determined in advance, resulting in the redundant structure of a multi-classifier and larger computational cost. Moreover, various combinations of base classifiers may have similar recognition accuracy, forming a multimodel optimization problem. To address the issue, a dual-ensemble class imbalance learning method is presented, in which two ensemble learning models are nested each other. For each sub-dataset, three heterogeneous sub-classifiers compose of internal ensemble learning model, and the one with the highest recognition accuracy is selected as base classifier. In external ensemble learning model, an optimal combination that contains the smallest number of base classifiers and identifies human actions most exactly is found by multimodal evolutionary algorithms. Based on seven imbalanced activity datasets derived from localization data for person activity, statistical experimental results show that the proposed evolutionary dual-ensemble class imbalance learning method provides the simplest ensemble structure with the best accuracy for imbalanced data that outperforms other five widely-used ensemble classification methods on all metrics.

关键词： Training Data models Learning systems Feature extraction evolutionary computation Costs computational modeling Class imbalance learning ensemble learning under-sampling multi-modal evolutionary algorithm human activity recognition

来源：评论

学校读者我要写书评

暂无评论

Multimodal Web Page Segmentation Using Self-organized Multi-objective Clustering

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2022年第3期40卷 1–49页

作者： Jayashree, Srivatsa Ramesh Dias, Gael Andrew, Judith Jeyafreeda Saha, Sriparna Maurel, Fabrice Ferrari, Stephane Indian Inst Technol Patna Patna 801103 Bihar India Normandie Univ UNICAEN ENSICAEN CNRSGREYC 6 Blvd Marechal Juin F-14000 Caen France Normandie Univ UNICAEN CRISCO F-14000 Caen France

Web page segmentation (WPS) aims to break a web page into different segments with coherent intra- and inter-semantics. By evidencing the morpho-dispositional semantics of a web page, WPS has traditionally been used to demarcate informative from non-informative content, but it has also evidenced its key role within the context of non-linear access to web information for visually impaired people. For that purpose, a great deal of ad hoc solutions have been proposed that rely on visual, logical, and/or text cues. However, such methodologies highly depend on manually tuned heuristics and are parameter-dependent. To overcome these drawbacks, principled frameworks have been proposed that provide the theoretical bases to achieve optimal solutions. However, existing methodologies only combine few discriminant features and do not define strategies to automatically select the optimal number of segments. In this article, we present a multi-objective clustering technique called MCS that relies on K-means, in which (1) visual, logical, and text cues are all combined in a early fusion manner and (2) an evolutionary process automatically discovers the optimal number of clusters (segments) as well as the correct positioning of seeds. As such, our proposal is parameter-free, combines many different modalities, does not depend on manually tuned heuristics, and can be run on any web page without any constraint. An exhaustive evaluation over two different tasks, where (1) the number of segments must be discovered or (2) the number of clusters is fixed with respect to the task at hand, shows that MCS drastically improves over most competitive and up-to-date algorithms for a wide variety of external and internal validation indices. In particular, results clearly evidence the impact of the visual and logical modalities towards segmentation performance.

关键词： Web page segmentation multimodal early fusion multi-objective optimization self-organizing maps evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Person Re-Identification With Multi-Features Based on evolutionary Algorithm

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN computationAL INTELLIGENCE 2022年第3期6卷 509-518页

作者： Zhang, Lixia Li, Kangshun Qi, Yu South China Agr Univ Coll Math & Informat Guangzhou 510642 Peoples R China Guangdong Key Lab Big Data Anal & Proc Guangzhou 510006 Peoples R China Guangdong Univ Sci & Technol Sch Comp Sci Dongguan 523083 Peoples R China

Person re-identification can identify a particular pedestrian automatically by computer in surveillance video, who has occurred in the monitoring network. It is one of the hot topics in the field of intelligent video surveillance. However, it faces many challenges. For example, robust feature representation model and ideal similarity measure method are both lacking, which will seriously affect the identification accuracy. These problems can be solved to some extent through applying appropriate optimization algorithm, which could optimize feature selection process, and guide similarity measure method design. evolutionary algorithm is a good optimization method, but two obvious drawbacks have been found in practical application, which are slow convergence speed and easy convergence to local optimal solution respectively. Therefore, traditional evolutionary algorithm is improved in this paper firstly. The existing problem will be solved by improving search efficiency and maintaining population diversity, after that, improved evolutionary algorithm is applied to optimize the process of person re-identification. Feature representation model with high robustness will be designed, and reasonable and effective similarity measure method will be obtained through learning. Thus, the identification accuracy and system performance will be improved. The algorithm proposed in this paper has been compared with some classical algorithms and the case without using evolutionary algorithm to optimize. Experimental results show that method in this paper is an effective person re-identification scheme.

关键词： evolutionary computation Feature extraction Image color analysis Statistics Sociology Convergence Search problems Person Re-identification evolutionary Algorithm Feature Representation Feature Matching

来源：评论

学校读者我要写书评

暂无评论

Difficulties in Fair Performance Comparison of Multi-Objective evolutionary Algorithms [Research Frontier]

引用

IEEE computationAL INTELLIGENCE MAGAZINE 2022年第1期17卷 86-101页

作者： Ishibuchi, Hisao Pang, Lie Meng Shang, Ke Southern Univ Sci & Technol Shenzhen Peoples R China

The performance of a newly designed evolutionary algorithm is usually evaluated by computational experiments in comparison with existing algorithms. However, comparison results depend on experimental setting;thus, fair comparison is difficult. Fair comparison of multi-objective evolutionary algorithms is even more difficult since solution sets instead of solutions are evaluated. In this paper, the following four issues are discussed for fair comparison of multi-objective evolutionary algorithms: (i) termination condition, (ii) population size, (iii) performance indicators, and (iv) test problems. Whereas many other issues related to computational experiments such as the choice of a crossover operator and the specification of its probability can be discussed for each algorithm separately, all the above four issues should be addressed for all algorithms simultaneously. For each issue, its strong effects on comparison results are first clearly demonstrated. Then, the handling of each issue for fair comparison is discussed. Finally, future research topics related to each issue are suggested.

关键词： Social factors evolutionary computation Robustness Statistics Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Using a small number of training instances in genetic programming for face image classification

引用

INFORMATION SCIENCES 2022年 593卷 488-504页

作者： Bi, Ying Xue, Bing Zhang, Mengjie Victoria Univ Wellington Sch Engn & Comp Sci POB 600 Wellington New Zealand

Classifying faces is a difficult task due to image variations in illumination, occlusion, pose, expression, etc. Typically, it is challenging to build a generalised classifier when the training data is small, which can result in poor generalisation. This paper proposes a new approach for the classification of face images based on multi-objective genetic programming (MOGP). In MOGP, image descriptors that extract effective features are automatically evolved by optimising two different objectives at the same time: the accuracy and the distance measure. The distance measure is a new measure intended to enhance generalisation of learned features and/or classifiers. The performance of MOGP is evaluated on eight face datasets. The results show that MOGP significantly outperforms 17 competitive methods. (C) 2022 Elsevier Inc. All rights reserved.

关键词： Genetic programming Image classification Fitness measure Small data evolutionary computation

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：