A Model Validation Method Based on Convolutional Neural Network

Ke Fang; Ju Huo

doi:10.1007/978-981-99-7240-1_15

A Model Validation Method Based on Convolutional Neural Network

Ke Fang^*
, Ju Huo

^*Corresponding author for this work

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

Abstract

Conventional model validation methods analyze outputs similarity between simulation and real world with same inputs. However, it is hard to guarantee the condition in practice. In order to solve the problem, a method based on convolutional neural network (CNN) is proposed, including data preprocessing, activation function, loss function, and optimization algorithm. Meanwhile, a CNN is established for model validation training and test. Finally, a case study of model validation is presented. The result shows that, the method can obtain 98.5% validation accuracy under the condition of same inputs, and can discriminate credibility levels with different inputs as well.

Original language	English
Title of host publication	Methods and Applications for Modeling and Simulation of Complex Systems - 22nd Asia Simulation Conference, AsiaSim 2023, Proceedings
Editors	Fazilah Hassan, Noorhazirah Sunar, Mohd Ariffanan Mohd Basri, Mohd Saiful Azimi Mahmud, Mohamad Hafis Izran Ishak, Mohamed Sultan Mohamed Ali
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	194-203
Number of pages	10
ISBN (Print)	9789819972395
DOIs	https://doi.org/10.1007/978-981-99-7240-1_15
State	Published - 2024
Event	22nd Asia Simulation Conference, AsiaSim 2023 - Langkawi, Malaysia Duration: 25 Oct 2023 → 26 Oct 2023

Publication series

Name	Communications in Computer and Information Science
Volume	1911 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	22nd Asia Simulation Conference, AsiaSim 2023
Country/Territory	Malaysia
City	Langkawi
Period	25/10/23 → 26/10/23

Keywords

Convolutional Neural Network
Different Inputs
GRA
Model Validation
TIC

Access to Document

10.1007/978-981-99-7240-1_15

Cite this

Fang, K., & Huo, J. (2024). A Model Validation Method Based on Convolutional Neural Network. In F. Hassan, N. Sunar, M. A. Mohd Basri, M. S. A. Mahmud, M. H. I. Ishak, & M. S. Mohamed Ali (Eds.), Methods and Applications for Modeling and Simulation of Complex Systems - 22nd Asia Simulation Conference, AsiaSim 2023, Proceedings (pp. 194-203). (Communications in Computer and Information Science; Vol. 1911 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-7240-1_15

Fang, Ke ; Huo, Ju. / A Model Validation Method Based on Convolutional Neural Network. Methods and Applications for Modeling and Simulation of Complex Systems - 22nd Asia Simulation Conference, AsiaSim 2023, Proceedings. editor / Fazilah Hassan ; Noorhazirah Sunar ; Mohd Ariffanan Mohd Basri ; Mohd Saiful Azimi Mahmud ; Mohamad Hafis Izran Ishak ; Mohamed Sultan Mohamed Ali. Springer Science and Business Media Deutschland GmbH, 2024. pp. 194-203 (Communications in Computer and Information Science).

@inproceedings{261b13a2273b4ff7a8bcf0742be13109,

title = "A Model Validation Method Based on Convolutional Neural Network",

abstract = "Conventional model validation methods analyze outputs similarity between simulation and real world with same inputs. However, it is hard to guarantee the condition in practice. In order to solve the problem, a method based on convolutional neural network (CNN) is proposed, including data preprocessing, activation function, loss function, and optimization algorithm. Meanwhile, a CNN is established for model validation training and test. Finally, a case study of model validation is presented. The result shows that, the method can obtain 98.5\% validation accuracy under the condition of same inputs, and can discriminate credibility levels with different inputs as well.",

keywords = "Convolutional Neural Network, Different Inputs, GRA, Model Validation, TIC",

author = "Ke Fang and Ju Huo",

note = "Publisher Copyright: {\textcopyright} 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 22nd Asia Simulation Conference, AsiaSim 2023 ; Conference date: 25-10-2023 Through 26-10-2023",

year = "2024",

doi = "10.1007/978-981-99-7240-1\_15",

language = "英语",

isbn = "9789819972395",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "194--203",

editor = "Fazilah Hassan and Noorhazirah Sunar and \{Mohd Basri\}, \{Mohd Ariffanan\} and Mahmud, \{Mohd Saiful Azimi\} and Ishak, \{Mohamad Hafis Izran\} and \{Mohamed Ali\}, \{Mohamed Sultan\}",

booktitle = "Methods and Applications for Modeling and Simulation of Complex Systems - 22nd Asia Simulation Conference, AsiaSim 2023, Proceedings",

address = "德国",

}

Fang, K & Huo, J 2024, A Model Validation Method Based on Convolutional Neural Network. in F Hassan, N Sunar, MA Mohd Basri, MSA Mahmud, MHI Ishak & MS Mohamed Ali (eds), Methods and Applications for Modeling and Simulation of Complex Systems - 22nd Asia Simulation Conference, AsiaSim 2023, Proceedings. Communications in Computer and Information Science, vol. 1911 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 194-203, 22nd Asia Simulation Conference, AsiaSim 2023, Langkawi, Malaysia, 25/10/23. https://doi.org/10.1007/978-981-99-7240-1_15

A Model Validation Method Based on Convolutional Neural Network. / Fang, Ke ; Huo, Ju.
Methods and Applications for Modeling and Simulation of Complex Systems - 22nd Asia Simulation Conference, AsiaSim 2023, Proceedings. ed. / Fazilah Hassan; Noorhazirah Sunar; Mohd Ariffanan Mohd Basri; Mohd Saiful Azimi Mahmud; Mohamad Hafis Izran Ishak; Mohamed Sultan Mohamed Ali. Springer Science and Business Media Deutschland GmbH, 2024. p. 194-203 (Communications in Computer and Information Science; Vol. 1911 CCIS).

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

TY - GEN

T1 - A Model Validation Method Based on Convolutional Neural Network

AU - Fang, Ke

AU - Huo, Ju

PY - 2024

Y1 - 2024

N2 - Conventional model validation methods analyze outputs similarity between simulation and real world with same inputs. However, it is hard to guarantee the condition in practice. In order to solve the problem, a method based on convolutional neural network (CNN) is proposed, including data preprocessing, activation function, loss function, and optimization algorithm. Meanwhile, a CNN is established for model validation training and test. Finally, a case study of model validation is presented. The result shows that, the method can obtain 98.5% validation accuracy under the condition of same inputs, and can discriminate credibility levels with different inputs as well.

AB - Conventional model validation methods analyze outputs similarity between simulation and real world with same inputs. However, it is hard to guarantee the condition in practice. In order to solve the problem, a method based on convolutional neural network (CNN) is proposed, including data preprocessing, activation function, loss function, and optimization algorithm. Meanwhile, a CNN is established for model validation training and test. Finally, a case study of model validation is presented. The result shows that, the method can obtain 98.5% validation accuracy under the condition of same inputs, and can discriminate credibility levels with different inputs as well.

KW - Convolutional Neural Network

KW - Different Inputs

KW - GRA

KW - Model Validation

KW - TIC

UR - https://www.scopus.com/pages/publications/85175996982

U2 - 10.1007/978-981-99-7240-1_15

DO - 10.1007/978-981-99-7240-1_15

M3 - 会议稿件

AN - SCOPUS:85175996982

SN - 9789819972395

T3 - Communications in Computer and Information Science

SP - 194

EP - 203

BT - Methods and Applications for Modeling and Simulation of Complex Systems - 22nd Asia Simulation Conference, AsiaSim 2023, Proceedings

A2 - Hassan, Fazilah

A2 - Sunar, Noorhazirah

A2 - Mohd Basri, Mohd Ariffanan

A2 - Mahmud, Mohd Saiful Azimi

A2 - Ishak, Mohamad Hafis Izran

A2 - Mohamed Ali, Mohamed Sultan

PB - Springer Science and Business Media Deutschland GmbH

T2 - 22nd Asia Simulation Conference, AsiaSim 2023

Y2 - 25 October 2023 through 26 October 2023

ER -

Fang K , Huo J. A Model Validation Method Based on Convolutional Neural Network. In Hassan F, Sunar N, Mohd Basri MA, Mahmud MSA, Ishak MHI, Mohamed Ali MS, editors, Methods and Applications for Modeling and Simulation of Complex Systems - 22nd Asia Simulation Conference, AsiaSim 2023, Proceedings. Springer Science and Business Media Deutschland GmbH. 2024. p. 194-203. (Communications in Computer and Information Science). doi: 10.1007/978-981-99-7240-1_15

A Model Validation Method Based on Convolutional Neural Network

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this