检索结果-内蒙古大学图书馆

7th International Conference on Computer Information Science and Application Technology, CISAT 2024

作者： Zhang, Yujia Kong, Zheping Pang, Jianping Zhao, Jiayu Liu, Mandan East China University of Science and Technology School of Information Science and Engineering Shanghai China

ISBN: (纸本)9798350375107

The generation of facial expressions has long been a challenging problem. In order to generate user-satisfactory facial expressions, this paper proposes an expression generation method based on an interactive evolutionary algorithm. The method employs an interactive evolutionary algorithm to optimize expression parameters in order to obtain satisfactory face expression parameters. Different face parameters express the fusion of predefined expressions in different parts of the face. By designing the face expression coding, it is possible to achieve a diversity of fusion effects in time and space, thus enabling the realization of a rich animation process of face expressions. © 2024 IEEE.

关键词： face expression generation interactive evolutionary algorithm multi-expression fusion

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Task interactive evolutionary Optimization algorithm with Search Space Alignment 13

Dynamic Multi-Task Interactive Evolutionary Optimization Alg...

引用

13th IEEE Congress on evolutionary Computation, CEC 2024

作者： Wu, Weidong Sun, Xiaoyan Zhang, Yong Song, Wei School of Information and Control Engineering China University of Mining and Technology Xuzhou China School of Artifical Intelligence and Computer Science Jiangnan University Wuxi China

ISBN: (纸本)9798350308365

The interactive evolutionary multi-task optimization approach assisted by surrogate models has proven successful in enhancing individualized recommendation performance. However, in light of the dynamically changing user preferences, it becomes imperative to further develop more powerful knowledge sharing strategy to improve the interactive multi-task optimization efficiency. A probability model-assisted search space alignment among multiple tasks method is proposed for knowledge transfer across multi-task environment. Additionally, a diversity maintaining mechanism of the transferred population is proposed to improve the quality and diversity of the initial population in a preference varied multi-task environment. The research demonstrates the effectiveness of the proposed approach in achieving effective knowledge transfer across multi-task environmen. Furthermore, the utilization of a high-quality initial population not only enhances the evolutionary search efficiency of the algorithm but also significantly improves the accuracy, diversity., and novelty of personalized recommendation. © 2024 IEEE.

关键词： Dynamic optimization interactive evolutionary algorithm Multi-task optimization Personalized recommendation Subspace alignment

来源：评论

学校读者我要写书评

暂无评论

Generating Kranok patterns with an interactive evolutionary algorithm

引用

APPLIED SOFT COMPUTING 2020年第0期89卷 106121-000页

作者： Leelathakul, Nutthanon Rimcharoen, Sunisa Burapha Univ Fac Informat Saen Suk Thailand

The kranok pattern is a classical Thai pattern, often seen in the ornamentation of Thai religious artifacts such as Tripitaka cabinets, temple doors and coffins. All Thai trainee artists must practice drawing the kranok pattern because it is a fundamental motif in Thai traditional decorative art. Individual skilled artists and instructors have their own preferred ways of drawing the pattern, and their styles differ in ornamental details. Nevertheless, all make use of similar basic structures. Most trainees learn a range of styles by observing experienced artists. After exploring the methods of drawing used by experts and published in textbooks, we designed an algorithm for automatically generating kranok patterns. We used an interactive evolutionary algorithm (IEA) to improve the aesthetic appeal of the generated patterns in response to users' feedback. The aim of our work was not to replace artists with machines, but to enhance human artistic expression. Specifically, the work aimed to help users without artistic skills to create kranok patterns in their own style. The algorithm facilitated the creation of a variety of personalized kranok patterns - diverse in their expressive curvature, refinement and proportions - that were satisfying to the varying preferences of a range of users. We also analyzed the proposed algorithm's behavior in terms of its convergence to generate specific shapes. The proposed method was examined by 28 respondents (27 Thai and 1 foreign) who were selected to include representatives of both sexes as well as experts in both Thai drawing and evolutionary algorithms. The results from our questionnaires showed that all respondents were satisfied with the generated kranok patterns: one respondent was 'completely satisfied', seventeen 'very satisfied', seven 'moderately satisfied', and three 'slightly satisfied'. (C) 2020 Elsevier B.V. All rights reserved.

关键词： interactive evolutionary algorithm Thai drawing Kranok pattern Bezier curve Generated art

来源：评论

学校读者我要写书评

暂无评论

An interactive evolutionary algorithm with Adaptive Evaluation Mechanism 27

An Interactive Evolutionary Algorithm with Adaptive Evaluati...

引用

27th Chinese Control and Decision Conference (CCDC)

作者： Wei, Bo Xia, Xuewen Xie, Chengwang Yu, Fei East China Jiaotong Univ Sch Software Nanchang 330013 Peoples R China East China Jiaotong Univ Intelligent Optimizat & Informat Proc Lab Nanchang 330013 Peoples R China Minnan Normal Univ Coll Phys & Elect Informat Engn Zhangzhou 363000 Fujian Peoples R China

ISBN: (纸本)9781479970162

In this paper, an interactive evolutionary algorithm with adaptive evaluation mechanism(SVM-IEA), which based on multiclass support vector machine, is presented to solve the key problem of interactive evolutionary algorithm: the fatigue problem of user. The key to this algorithm lies in multiclass SVM using individuals evaluated by user as the training data set, then it is learned, SVM-IEA achieve the ability of displacing user to evaluate newly generated individuals. In the middle-later period of algorithm running, the user can decide whether to participate in the algorithm again until SVM-IEA obtains the optimum solutions. The proposed SVM-IEA algorithm, which can directly reduce the number of user evaluating individuals, is applied to a poster design system to empirically demonstrate its strength in alleviating user fatigue.

关键词： interactive evolutionary algorithm Support vector machine Adaptive evaluation mechanism Implicit optimization problem

来源：评论

学校读者我要写书评

暂无评论

An interactive evolutionary algorithm with Adaptive Evaluation Mechanism

An Interactive Evolutionary Algorithm with Adaptive Evaluati...

引用

第27届中国控制与决策会议

作者： Bo Wei Xuewen Xia Chengwang Xie Fei Yu School of Software East China Jiaotong University Intelligent Optimization & Information Processing Lab East China Jiaotong University College of Physics and Electronic Information Engineering Minnan Normal University

ISBN: (纸本)9781479970186

In this paper,an interactive evolutionary algorithm with adaptive evaluation mechanism(SVM-IEA),which based on multiclass support vector machine,is presented to solve the key problem of interactive evolutionary algorithm:the fatigue problem of *** key to this algorithm lies in multiclass SVM using individuals evaluated by user as the training data set,then it is learned,SVM-IEA achieve the ability of displacing user to evaluate newly generated *** the middle-later period of algorithm running,the user can decide whether to participate in the algorithm again until SVM-IEA obtains the optimum *** proposed SVM-IEA algorithm,which can directly reduce the number of user evaluating individuals,is applied to a poster design system to empirically demonstrate its strength in alleviating user fatigue.

关键词： interactive evolutionary algorithm Support vector machine Adaptive evaluation mechanism Implicit optimization problem

来源：评论

学校读者我要写书评

暂无评论

Creative collaboration with interactive evolutionary algorithms: a reflective exploratory design study

引用

GENETIC PROGRAMMING AND EVOLVABLE MACHINES 2024年第1期25卷 4-4页

作者： Uusitalo, Severi Kantosalo, Anna Salovaara, Antti Takala, Tapio Guckelsberger, Christian Aalto Univ Dept Design Espoo Finland Univ Helsinki Dept Comp Sci Helsinki Finland Aalto Univ Dept Comp Sci Espoo Finland Queen Mary Univ London Sch Elect Engn & Comp Sci London England Finnish Ctr Artificial Intelligence Helsinki Finland

Progress in AI has brought new approaches for designing products via co-creative human-computer interaction. In architecture, interior design, and industrial design, computational methods such as evolutionary algorithms support the designer's creative process by revealing populations of computer-generated design solutions in a parametric design space. Because the benefits and shortcomings of such algorithms' use in design processes are not yet fully understood, the authors studied the intricate interactions of an industrial designer employing an interactive evolutionary algorithm for a non-trivial creative product design task. In an in-depth report on the in-situ longitudinal experiences arising between the algorithm, human designer, and environment, from ideation to fabrication, they reflect on the algorithm's role in inspiring design, its relationship to fixation, and the stages of the creative process in which it yielded perceived value. The paper concludes with proposals for future research into co-creative AI in design exploration and creative practice.

关键词： Human-computer co-creativity interactive evolutionary algorithm Introspection Autoethnography Longitudinal study Design

来源：评论

学校读者我要写书评

暂无评论

Co-creative Product Design with interactive evolutionary algorithms: A Practice-Based Reflection 11th

Co-creative Product Design with Interactive Evolutionary Alg...

引用

11th International Conference on Artificial Intelligence in Music, Sound, Art and Design (EvoMUSART) Held as Part of EvoStar Conference

ISBN: (纸本)9783031037894;9783031037887

Progress in AI has brought about new approaches for designing products via co-creative human-computer interaction. In architecture, interior design, and industrial design, computational methods such as evolutionary algorithms support the designer's creative process by revealing populations of generated design solutions in a parametric design space. However, the benefits and shortcomings of such algorithms for designers are not yet fully understood. This paper reports the in-depth, in-situ and longitudinal experiences of one industrial designer using an interactive evolutionary algorithm in a non-trivial creative product design task. Our study sheds light on the intricate interaction between algorithm, human designer and their environment. It identifies, amongst others, the algorithm's contributions to design inspiration and to overcoming fixation. We contribute concrete proposals for the future study of co-creative AI in design exploration and creative practice.

关键词： Co-creativity interactive evolutionary algorithm Introspection Autoethnography Longitudinal study Design

来源：评论

学校读者我要写书评

暂无评论

Designing origami tessellations composed of quadrilateral meshes and degree-4 vertices for engineering applications

引用

AUTOMATION IN CONSTRUCTION 2022年 142卷

作者： Meloni, Marco Zhang, Qian Pak, Joonseok Bilore, Manish Naresh Ma, Ruijun Ballegaard, Emil Lee, Daniel Sang-Hoon Cai, Jianguo Southeast Univ Natl Prestress Engn Res Ctr Key Lab C & PC Struct Minist Educ Nanjing 211189 Peoples R China Royal Danish Acad Inst Architecture & Technol Sch Architecture Design & Conservat DK-1435 Copenhagen Denmark

Origami-based designs have been successfully adopted to solve engineering problems at different scales of application. This article proposes a method for designing origami tessellations composed of quadrilateral meshes and degree -4 vertices. Crease patterns are generated starting from base units to which are applied tailored generation functions. The theoretical framework is further implemented in a parametric design workflow and automated with the aid of an interactive evolutionary algorithm (IEA). The proposed workflow is a flexible tool that could be applied to design and analyse both rigid and non-rigid foldable origami patterns. The design domain could be investigated without pre-defined design goals and with the support of user-defined performance values.

关键词： Origami-based engineering Explorative design interactive evolutionary algorithm Computer-aided design Design automation

来源：评论

学校读者我要写书评

暂无评论

An interactive Differential Evolution algorithm Based on Backtracking Strategy Applied in Interior Layout Design

引用

algorithmS 2023年第6期16卷 275-275页

作者： Yu, Fei Liang, Bang Tang, Bo Wu, Hongrun Minnan Normal Univ Sch Phys & Informat Engn Zhangzhou 363000 Peoples R China Minnan Normal Univ Sch Comp Sci Zhangzhou 363000 Peoples R China

The Interior layout model is to optimize the arrangement position of each room to maximize the comfort and quality of life of residents. Due to the complexity of the Interior layout problem, the computation of fitness function costs lots of time. To reduce the high computational cost while maintaining the solution performance. An interactive differential evolution algorithm based on Backtracking operator (IDE-BO) is proposed as the solver of the Interior layout model. The human-computer interaction mechanism of IDE benefits the automatic adjustment of fitness parameters that best meet the user's subjective preferences to achieve the optimal solution. At the same time, the backtracking strategy can also help jump out when the algorithm falls into local optimization. The IDE is compared to other two conventional optimization methods based on two different layout scenarios. The experimental results show that in interior layout model IDE-BO is better than conventional interactive genetic algorithm (IGA) and IDE which do not use BO strategy, the super-performance of IDE-BO in complex situations in terms of execution time and convergence rate.

关键词： interactive evolutionary algorithm differential evolution algorithm interior design spatial distribution

来源：评论

学校读者我要写书评

暂无评论

Language model based interactive estimation of distribution algorithm

引用

KNOWLEDGE-BASED SYSTEMS 2020年 200卷 105980-105980页

作者： Chen, Yang Jin, Yaochu Sun, Xiaoyan China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Jiangsu Peoples R China Univ Surrey Dept Comp Sci Guildford GU4 7YX Surrey England Nanyang Technol Univ Sch Comp Sci & Engn 50 Nanyang Ave Singapore 639798 Singapore

It is very hard, if not impossible to use analytical objective functions for optimization of personalized search due to the difficulties in mathematically describing qualitative problems. To solve such optimization problems, interactive evolutionary algorithms, which can make use of human preferences, are highly desirable. However, due to the lack of effective encoding methods, interactive evolutionary algorithms have been limited to numerically encoded optimization problems. In practice, however, linguistic terms (words) are the most natural expression of human preferences, and they are also commonly used to describe items in personalized search or E-commerce;therefore, language models better suit encoding, and the optimization of personalized search is converted into a dynamic document matching problem. To optimize word-described personalized search, we propose a novel interactive estimation of distribution algorithm. This algorithm combines a language model-based encoding approach, a Dirichlet-Multinomial compound distribution-based preference expression, and a Bayesian inference mechanism. The proposed algorithm is applied to two personalized search cases to demonstrate the capability of the algorithm in ensuring a more efficient and accurate search with less user fatigue. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Estimation of distribution algorithm interactive evolutionary algorithm Language model Personalized search Bayesian inference

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：