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

被引:16
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
[31]   The Modeling and Prediction of Strapdown Inertial Measurement Unit based on Support Vector Regression and Particle Swarm Optimization [J].
Li, Shuying ;
Xuan Diwu ;
Li, Yiran .
2019 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2019), 2019, :1314-1318
[32]   Rotation-invariant texture image retrieval using particle swarm optimization and support vector regression [J].
Tsai, Hung-Hsu ;
Chang, Bae-Muu ;
Liou, Shin-Hung .
APPLIED SOFT COMPUTING, 2014, 17 :127-139
[33]   Hybrid wavelet ν-support vector machine and chaotic particle swarm optimization for regression estimation [J].
Qi Wu .
EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (12) :14624-14632
[34]   Forecasting Groundwater Levels using a Hybrid of Support Vector Regression and Particle Swarm Optimization [J].
Mozaffari, Saeed ;
Javadi, Saman ;
Moghaddam, Hamid Kardan ;
Randhir, Timothy O. .
WATER RESOURCES MANAGEMENT, 2022, 36 (06) :1955-1972
[35]   Forecasting Groundwater Levels using a Hybrid of Support Vector Regression and Particle Swarm Optimization [J].
Saeed Mozaffari ;
Saman Javadi ;
Hamid Kardan Moghaddam ;
Timothy O. Randhir .
Water Resources Management, 2022, 36 :1955-1972
[36]   Intrusion Detection Quantitative Analysis with Support Vector Regression and Particle Swarm Optimization Algorithm [J].
Tian, WenJie ;
Liu, JiCheng .
PROCEEDINGS OF THE 2009 INTERNATIONAL CONFERENCE ON WIRELESS NETWORKS AND INFORMATION SYSTEMS, 2009, :133-136
[37]   Constrained Motion Particle Swarm Optimization and Support Vector Regression for Non-Linear Time Series Regression and Prediction Applications [J].
Sapankevych, Nicholas I. ;
Sankar, Ravi .
2013 12TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2013), VOL 2, 2013, :473-477
[38]   A HYBRID SUPPORT VECTOR REGRESSION APPROACH FOR RAINFALL FORECASTING USING PARTICLE SWARM OPTIMIZATION AND PROJECTION PURSUIT TECHNOLOGY [J].
Wu, Jiansheng ;
Liu, Mingzhe ;
Jin, Long .
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND APPLICATIONS, 2010, 9 (02) :87-104
[39]   Hybridizing nonlinear independent component analysis and support vector regression with particle swarm optimization for stock index forecasting [J].
Chi-Jie Lu .
Neural Computing and Applications, 2013, 23 :2417-2427
[40]   Hybridizing nonlinear independent component analysis and support vector regression with particle swarm optimization for stock index forecasting [J].
Lu, Chi-Jie .
NEURAL COMPUTING & APPLICATIONS, 2013, 23 (7-8) :2417-2427