Deep Neural Networks for New Product Form Design

被引：2

作者：

Wei, Chun-Chun ^{[1
]}

Yeh, Chung-Hsing ^{[2
]}

Wang, Ian ^{[3
]}

Walsh, Bernie ^{[3
]}

Lin, Yang-Cheng ^{[4
]}

机构：

[1] Natl Taipei Univ Business, Dept Digital Media Design, Taoyuan 324, Taiwan

[2] Monash Univ, Fac Informat Technol, Clayton, Vic 3800, Australia

[3] Monash Univ, Dept Design, Monash Art Design & Architecture, Caulfield, Vic 3145, Australia

[4] Natl Cheng Kung Univ, Dept Ind Design, Tainan 701, Taiwan

来源：

ICINCO: PROCEEDINGS OF THE 16TH INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS, VOL 2 | 2019年

关键词：

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

D O I：

10.5220/0007933506530657

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

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.

引用

页码：653 / 657

页数：5

共 50 条

[41] Product Categorization by Title Using Deep Neural Networks as Feature Extractor
Paulucio, Leonardo S.
Paixao, Thiago M.
Berriel, Rodrigo F.
De Souza, Alberto F.
Badue, Claudine
Oliveira-Santos, Thiago
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
[42] Impulsive Control Discrete Fractional Neural Networks in Product Form Design: Practical Mittag-Leffler Stability Criteria
Stamov, Trayan
APPLIED SCIENCES-BASEL, 2024, 14 (09):
[43] NETWORKS OF QUEUES WITH PRODUCT FORM
PUJOLLE, G
RAIRO-RECHERCHE OPERATIONNELLE-OPERATIONS RESEARCH, 1980, 14 (04): : 317 - 330
[44] Product form queueing networks
Balsamo, S
PERFORMANCE EVALUATION: ORIGINS AND DIRECTIONS, 2000, 1769 : 377 - 401
[45] New design strategies of deep heterogenous convolutional neural networks ensembles for breast cancer diagnosis
Zerouaoui, Hasnae
El Alaoui, Omar
Idri, Ali
MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (24) : 65189 - 65220
[46] New Deep Neural Networks for Protein Model Evaluation
Wang, Junlin
Li, Zhaoyu
Shang, Yi
2017 IEEE 29TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2017), 2017, : 309 - 313
[47] A New Pruning Method to Train Deep Neural Networks
Guo, Haonan
Ren, Xudie
Li, Shenghong
COMMUNICATIONS, SIGNAL PROCESSING, AND SYSTEMS, 2018, 423 : 767 - 775
[48] GradAug: A New Regularization Method for Deep Neural Networks
Yang, Taojiannan
Zhu, Sijie
Chen, Chen
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
[49] ESTIMATING AND EXPLORING THE PRODUCT FORM DESIGN SPACE USING DEEP GENERATIVE MODELS
Burnap, Alexander
Liu, Ye
Pan, Yanxin
Lee, Honglak
Gonzalez, Richard
Papalambros, Panos Y.
PROCEEDINGS OF THE ASME INTERNATIONAL DESIGN ENGINEERING TECHNICAL CONFERENCES AND COMPUTERS AND INFORMATION IN ENGINEERING CONFERENCE, 2016, VOL 2A, 2016,
[50] Incorporating the Multiple Linear Regression with the Neural Network to the Form Design of Product Image
Chen, Hung-Yuan
Chang, Yu-Ming
2014 10TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION (ICNC), 2014, : 174 - 180

← 1 2 3 4 5 →