Multilayer feedforward networks are universal approximators
Neural Networks
Intelligent Optimisation Techniques: Genetic Algorithms, Tabu Search, Simulated Annealing and Neural Networks
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fitting Superellipses to Incomplete Contours
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 4 - Volume 04
Form design of product image using grey relational analysis and neural network models
Computers and Operations Research
Object Decomposition based on Superellipses
ICICIC '06 Proceedings of the First International Conference on Innovative Computing, Information and Control - Volume 3
Introduction to Neural Networks with Java
Introduction to Neural Networks with Java
Advanced Engineering Informatics
Multiclass SVM-RFE for product form feature selection
Expert Systems with Applications: An International Journal
Macro-informatics of cognition and its application for design
Advanced Engineering Informatics
Advanced Engineering Informatics
A hybrid intelligent genetic algorithm
Advanced Engineering Informatics
An image evaluation approach for parameter-based product form and color design
Computer-Aided Design
A Kansei mining system for affective design
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
Product aesthetics plays an important role in new product design and development. Product form can deliver product images and affect customer's impression to a product. However, it is usually difficult to apply conventional approaches to represent the product form precisely and effectively for modeling the relationship between product image and customer perception. The objective of this work is to develop a computational technique for product aesthetics design so that customer perception can be taken into product form design in a more systematic and intelligent manner. To achieve this aim, a novel parametric approach is proposed to introduce design parameters such as line, size, and ratio into product design model and the technique of generalized superellipse fitting is adopted to describe the outline pattern of a product. Since customer perception on a product is highly non-linear and very difficult to be described by any traditional mathematical approaches, an artificial neural network (ANN) model is therefore established to relate the design parameters and the perceptual values for the design of a new product. A case study of mobile phone design, in which twelve numerical parameters are defined for the conceptual model, has been conducted to explain the implementation of the proposed approach. A three-layered perceptron ANN model is developed to predict the perceptual values of stylishness based on a survey using 32 mobile phone samples. The results of the case study illustrate that the proposed approach can successfully generate an optimum design of a mobile phone by applying a genetic algorithm (GA) on the trained ANN model.