Authors:
Chun-Chun Wei
1
;
Chung-Hsing Yeh
2
;
Ian Wang
3
;
Bernie Walsh
3
and
Yang-Cheng Lin
4
Affiliations:
1
Department of Digital Media Design, National Taipei University of Business, Taoyuan, 324 and Taiwan
;
2
Faculty of Information Technology, Monash University, Clayton, Victoria 3800 and Australia
;
3
Department of Design, Monash Art Design and Architecture, Monash University, Caulfield East, Victoria 3145 and Australia
;
4
Department of Industrial Design, National Cheng Kung University, Tainan, 701 and Taiwan
Keyword(s):
Artificial Intelligence, Consumer-oriented Expert System, Deep Learning, Neural Networks, Product Form Design.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Business Analytics
;
Cardiovascular Technologies
;
Computing and Telecommunications in Cardiology
;
Data Engineering
;
Decision Support Systems
;
Decision Support Systems, Remote Data Analysis
;
Health Engineering and Technology Applications
;
Human Factors & Human-System Interface
;
Industrial Engineering
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Intelligent Design and Manufacturing
;
Knowledge-Based Systems
;
Neural Networks Based Control Systems
;
Production Planning, Scheduling and Control
;
Symbolic Systems
Abstract:
Neural Networks (NNs) are non-linear models and are widely used to model complex relationships, thus being well suited to formulate the product design process for matching design form elements to consumers’ affective preferences. In this paper, we construct 36 deep NN models, using one to four hidden layers with three different dropout ratios and three widely used rules for determining the number of neurons in the hidden layer(s). As a result of extensive experiments, the NN model using one hidden layer with 140 hidden neurons has the highest predicting accuracy rate (80%) and is used to help product designers determine the optimal form combination for new fragrance bottle design.