Deep Neural Networks for new product form design

Chun-Chun Wei; Chung-Hsing Yeh; Ian Wong; Bernie Walsh; Yang-Cheng Lin

Deep Neural Networks for new product form design

Chun-Chun Wei, Chung-Hsing Yeh, Ian Wong, Bernie Walsh, Yang-Cheng Lin

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

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.

Original language	English
Title of host publication	Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics
Editors	Oleg Gusikhin, Kurosh Madani, Janan Zaytoon
Place of Publication	Portugal
Publisher	Scitepress
Pages	653-657
Number of pages	5
Volume	2
ISBN (Electronic)	9789897583803
ISBN (Print)	9789897583803
Publication status	Published - 2019
Event	International Conference on Informatics in Control, Automation and Robotics 2019 - Prague, Czechia Duration: 29 Jul 2019 → 31 Jul 2019 Conference number: 16th http://www.icinco.org/?y=2019

Conference

Conference	International Conference on Informatics in Control, Automation and Robotics 2019
Abbreviated title	ICINCO 2019
Country/Territory	Czechia
City	Prague
Period	29/07/19 → 31/07/19
Internet address	http://www.icinco.org/?y=2019

Keywords

Artificial Intelligence
Consumer-oriented Expert System
Deep Learning
Neural Networks
Product Form Design

Cite this

@inproceedings{8d3019564e5b4b808eb22ca66ab3de3d,

title = "Deep Neural Networks for new product form design",

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{\textquoteright} 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 hiddenneurons has the highest predicting accuracy rate (80%) and is used to help product designers determine the optimal form combination for new fragrance bottle design.",

keywords = "Artificial Intelligence, Consumer-oriented Expert System, Deep Learning, Neural Networks, Product Form Design",

author = "Chun-Chun Wei and Chung-Hsing Yeh and Ian Wong and Bernie Walsh and Yang-Cheng Lin",

year = "2019",

language = "English",

isbn = "9789897583803",

volume = "2",

pages = "653--657",

editor = "Gusikhin, {Oleg } and Madani, {Kurosh } and Zaytoon, {Janan }",

booktitle = "Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics",

publisher = "Scitepress",

address = "Portugal",

note = "International Conference on Informatics in Control, Automation and Robotics 2019, ICINCO 2019 ; Conference date: 29-07-2019 Through 31-07-2019",

url = "http://www.icinco.org/?y=2019",

}

Wei, C-C, Yeh, C-H , Wong, I, Walsh, B & Lin, Y-C 2019, Deep Neural Networks for new product form design. in O Gusikhin, K Madani & J Zaytoon (eds), Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics. vol. 2, Scitepress, Portugal , pp. 653-657, International Conference on Informatics in Control, Automation and Robotics 2019, Prague, Czechia, 29/07/19.

Deep Neural Networks for new product form design. / Wei, Chun-Chun; Yeh, Chung-Hsing ; Wong, Ian et al.
Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics. ed. / Oleg Gusikhin; Kurosh Madani; Janan Zaytoon. Vol. 2 Portugal : Scitepress, 2019. p. 653-657.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Deep Neural Networks for new product form design

AU - Wei, Chun-Chun

AU - Yeh, Chung-Hsing

AU - Wong, Ian

AU - Walsh, Bernie

AU - Lin, Yang-Cheng

N1 - Conference code: 16th

PY - 2019

Y1 - 2019

N2 - 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 hiddenneurons has the highest predicting accuracy rate (80%) and is used to help product designers determine the optimal form combination for new fragrance bottle design.

AB - 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 hiddenneurons has the highest predicting accuracy rate (80%) and is used to help product designers determine the optimal form combination for new fragrance bottle design.

KW - Artificial Intelligence

KW - Consumer-oriented Expert System

KW - Deep Learning

KW - Neural Networks

KW - Product Form Design

M3 - Conference Paper

SN - 9789897583803

VL - 2

SP - 653

EP - 657

BT - Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics

A2 - Gusikhin, Oleg

A2 - Madani, Kurosh

A2 - Zaytoon, Janan

PB - Scitepress

CY - Portugal

T2 - International Conference on Informatics in Control, Automation and Robotics 2019

Y2 - 29 July 2019 through 31 July 2019

ER -