An evaluation and design method for Ming-style furniture integrating Kansei engineering with particle swarm optimization-support vector regression

被引:6
作者
Fu, Lei [1 ]
Lei, Yiling [1 ]
Zhu, Ling [1 ]
Lv, Jiufang [1 ,2 ]
机构
[1] Nanjing Forestry Univ, Coll Furnishings & Ind Design, Nanjing 210037, Peoples R China
[2] Nanjing Forestry Univ, Coinnovat Ctr Efficient Proc & Utilizat Forest Res, Nanjing 210037, Peoples R China
关键词
Design evaluation; Ming-style furniture; User emotional requirements; Kansei engineering; Game theory; Particle swarm optimization; Support vector regression; PRODUCT DESIGN;
D O I
10.1016/j.aei.2024.102822
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Traditional Kansei Engineering (KE) often relies heavily on the designers' prior knowledge to study user emotional requirements. However, cognitive differences between designers and users can result in Ming-style furniture failing to gain consumer acceptance when introduced to the market. To enhance the objectivity and accuracy of the design process, this study proposes an improved evaluation and design method that integrates Game Theory (GT) with Particle Swarm Optimization-Support Vector Regression (PSO-SVR) based on KE. This approach aims to identify truly critical emotional requirements and accurately translate them into design characteristics. First, emotional requirements are collected, and the product form is analyzed and deconstructed. Next, the Spherical Fuzzy Analytic Hierarchy Process (SFAHP) and Criteria Importance Through Intercriteria Correlation (CRITIC) are employed to calculate the subjective and objective weights of emotional requirements, respectively. Then, GT is used to find the optimal equilibrium weights to select the critical emotional requirements. Finally, an intelligent evaluation system is built using a combination of PSO and SVR to determine the relationship between critical user emotional requirements and product design characteristics, thereby identifying the optimal design parameters for Ming-style furniture. The results reveal that the most critical user emotional requirements are "concise", "ornate", and "dynamic". In addition, the user evaluation results of the optimal design closely match the system's predicted outcomes, validating the feasibility and advancement of the proposed method. Compared to most KE studies that focus solely on expert knowledge, this study better balances the subjective experience of designers with objective information of users, improving the accuracy of product design decisions and helping designers develop innovative products that align closely with user requirements.
引用
收藏
页数:14
相关论文
共 50 条
  • [11] Prediction of landslide deformation based on rough sets and particle swarm optimization-support vector machine
    Institute of Geophysics and Geomatics, China University of Geosciences, Wuhan
    430074, China
    不详
    100081, China
    不详
    430074, China
    不详
    443000, China
    Zhongnan Daxue Xuebao (Ziran Kexue Ban), 6 (2324-2332): : 2324 - 2332
  • [12] Integrating Particle Swarm Optimization and Support Vector Regression for Forecasting the Demand of Traveling between Mini-Three Links
    Hung, Ping Husan
    Chen, Wei Jen
    Kuo, Then I.
    INTERNATIONAL JOURNAL OF PSYCHOLOGY, 2016, 51 : 643 - 643
  • [13] Fault Diagnosis of PT Fuel System Based on Particle Swarm Optimization-Support Vector Machine
    Wang, Dong
    Wang, Xin-qing
    Wang, Xiao-long
    Liang, Sheng
    Zhao, Yang
    FRONTIERS OF MANUFACTURING AND DESIGN SCIENCE II, PTS 1-6, 2012, 121-126 : 2809 - 2813
  • [14] Blind image quality assessment method based on a particle swarm optimization support vector regression fusion scheme
    Eddine, Dakkar Borhen
    Fella, Hachouf
    Azeddine, Beghdadi
    JOURNAL OF ELECTRONIC IMAGING, 2016, 25 (06)
  • [15] The Model of Rainfall Forecasting by Support Vector Regression Based on Particle Swarm Optimization Algorithms
    Zhao, Shian
    Wang, Lingzhi
    LIFE SYSTEM MODELING AND INTELLIGENT COMPUTING, PT II, 2010, 6329 : 110 - +
  • [16] Forecasting Cryptocurrency Prices Using Support Vector Regression Enhanced by Particle Swarm Optimization
    Parvini, Navid
    Ahmadian, Davood
    Ballestra, Luca Vincenzo
    COMPUTATIONAL ECONOMICS, 2024,
  • [17] A fault diagnosis method combined with compound multiscale permutation entropy and particle swarm optimization-support vector machine for roller bearings diagnosis
    Xu, Fan
    Tse, Peter Wai Tat
    Fang, Yan-Jun
    Liang, Jia-Qi
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART J-JOURNAL OF ENGINEERING TRIBOLOGY, 2019, 233 (04) : 615 - 627
  • [18] PM10 Prediction Model by Support Vector Regression Based on Particle Swarm Optimization
    Arampongsanuwat, Saowalak
    Meesad, Phayung
    FUTURE INFORMATION TECHNOLOGY, 2011, 13 : 189 - 194
  • [19] Fault Diagnosis Analysis with Support Vector Regression and Particle Swarm Optimization Algorithm
    Tian, WenJie
    Liu, JiCheng
    2010 CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1-5, 2010, : 3370 - 3374
  • [20] Particle swarm optimization for parameters selection of twin bounded support vector regression
    College of Electronics and Information Engineering, CIMS Research Center, Tongji University, Shanghai, China
    J. Comput. Inf. Syst., 14 (5163-5170): : 5163 - 5170