Quantitative Regression Modeling of Cocoa Bean Content Based on Gated Dilated Convolution Network

Yayu Chen; Wenju Zhou; Minrui Fei; Haikuan Wang; Xiaofei Han; Huiyu Zhou

doi:10.1007/978-981-33-6378-6_34

Quantitative Regression Modeling of Cocoa Bean Content Based on Gated Dilated Convolution Network

Yayu Chen, Wenju Zhou, Minrui Fei^*, Haikuan Wang, Xiaofei Han, Huiyu Zhou

^*Corresponding author for this work

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

Abstract

By analyzing the near-infrared spectrum, we can determine the quantitative relationship model between the spectral data of different cocoa beans and the target components. This paper proposes a predictive regression model based on 1D-CNN. Based on the traditional convolutional neural network, gating mechanisms and dilated convolutions are combined. The particle swarm optimization method is used to optimize the hyper-parameters of one-dimensional convolution. The end-to-end near-infrared predictive regression model does not require wavelength selection. It is convenient to use and has a strong promotional value. Taking the public cocoa beans near-infrared data set as an example, the method can predict the water and fat content in cocoa beans, and the effectiveness of the method is verified. Comparing the improved one-dimensional convolution with traditional one-dimensional convolution results and partial least squares regression, it shows better prediction accuracy and robustness.

Original language	English
Title of host publication	Recent Featured Applications of Artificial Intelligence Methods. LSMS 2020 and ICSEE 2020 Workshops - Workshops of the 6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020, Proceedings
Editors	Minrui Fei, Kang Li, Zhile Yang, Qun Niu, Xin Li
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	456-468
Number of pages	13
ISBN (Print)	9789813363779
DOIs	https://doi.org/10.1007/978-981-33-6378-6_34
Publication status	Published - 12 Jan 2020
Externally published	Yes
Event	6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020 - Shanghai, China Duration: 25 Oct 2020 → 25 Oct 2020

Publication series

Name	Communications in Computer and Information Science
Volume	1303
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020
Country/Territory	China
City	Shanghai
Period	25/10/2020 → 25/10/2020

Bibliographical note

Funding Information:
This research is financially supported by Natural Science Foundation of China (61877065), the National Key Research and Development Program of China (No. 2019YFB1405500) and Key Project of Science and Technology Commission of Shanghai Municipality under Grant (No. 16010500300).

Publisher Copyright:
© 2020, Springer Nature Singapore Pte Ltd.

Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.

Keywords

Convolutional neural network
Dilated convolution
Gating mechanisms
Infrared spectroscopic data

ASJC Scopus subject areas

General Computer Science
General Mathematics

Access to Document

10.1007/978-981-33-6378-6_34Licence: Unspecified

Cite this

Chen, Y., Zhou, W., Fei, M., Wang, H., Han, X., & Zhou, H. (2020). Quantitative Regression Modeling of Cocoa Bean Content Based on Gated Dilated Convolution Network. In M. Fei, K. Li, Z. Yang, Q. Niu, & X. Li (Eds.), Recent Featured Applications of Artificial Intelligence Methods. LSMS 2020 and ICSEE 2020 Workshops - Workshops of the 6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020, Proceedings (pp. 456-468). (Communications in Computer and Information Science; Vol. 1303). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-33-6378-6_34

Chen, Yayu ; Zhou, Wenju ; Fei, Minrui et al. / Quantitative Regression Modeling of Cocoa Bean Content Based on Gated Dilated Convolution Network. Recent Featured Applications of Artificial Intelligence Methods. LSMS 2020 and ICSEE 2020 Workshops - Workshops of the 6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020, Proceedings. editor / Minrui Fei ; Kang Li ; Zhile Yang ; Qun Niu ; Xin Li. Springer Science and Business Media Deutschland GmbH, 2020. pp. 456-468 (Communications in Computer and Information Science).

@inproceedings{f6eb0b68a477429aaea6d02c55008450,

title = "Quantitative Regression Modeling of Cocoa Bean Content Based on Gated Dilated Convolution Network",

abstract = "By analyzing the near-infrared spectrum, we can determine the quantitative relationship model between the spectral data of different cocoa beans and the target components. This paper proposes a predictive regression model based on 1D-CNN. Based on the traditional convolutional neural network, gating mechanisms and dilated convolutions are combined. The particle swarm optimization method is used to optimize the hyper-parameters of one-dimensional convolution. The end-to-end near-infrared predictive regression model does not require wavelength selection. It is convenient to use and has a strong promotional value. Taking the public cocoa beans near-infrared data set as an example, the method can predict the water and fat content in cocoa beans, and the effectiveness of the method is verified. Comparing the improved one-dimensional convolution with traditional one-dimensional convolution results and partial least squares regression, it shows better prediction accuracy and robustness.",

keywords = "Convolutional neural network, Dilated convolution, Gating mechanisms, Infrared spectroscopic data",

author = "Yayu Chen and Wenju Zhou and Minrui Fei and Haikuan Wang and Xiaofei Han and Huiyu Zhou",

note = "Funding Information: This research is financially supported by Natural Science Foundation of China (61877065), the National Key Research and Development Program of China (No. 2019YFB1405500) and Key Project of Science and Technology Commission of Shanghai Municipality under Grant (No. 16010500300). Publisher Copyright: {\textcopyright} 2020, Springer Nature Singapore Pte Ltd. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020 ; Conference date: 25-10-2020 Through 25-10-2020",

year = "2020",

month = jan,

day = "12",

doi = "10.1007/978-981-33-6378-6_34",

language = "English",

isbn = "9789813363779",

series = "Communications in Computer and Information Science",

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

pages = "456--468",

editor = "Minrui Fei and Kang Li and Zhile Yang and Qun Niu and Xin Li",

booktitle = "Recent Featured Applications of Artificial Intelligence Methods. LSMS 2020 and ICSEE 2020 Workshops - Workshops of the 6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020, Proceedings",

address = "Germany",

}

Chen, Y, Zhou, W, Fei, M, Wang, H, Han, X & Zhou, H 2020, Quantitative Regression Modeling of Cocoa Bean Content Based on Gated Dilated Convolution Network. in M Fei, K Li, Z Yang, Q Niu & X Li (eds), Recent Featured Applications of Artificial Intelligence Methods. LSMS 2020 and ICSEE 2020 Workshops - Workshops of the 6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020, Proceedings. Communications in Computer and Information Science, vol. 1303, Springer Science and Business Media Deutschland GmbH, pp. 456-468, 6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020, Shanghai, China, 25/10/2020. https://doi.org/10.1007/978-981-33-6378-6_34

Quantitative Regression Modeling of Cocoa Bean Content Based on Gated Dilated Convolution Network. / Chen, Yayu; Zhou, Wenju; Fei, Minrui et al.
Recent Featured Applications of Artificial Intelligence Methods. LSMS 2020 and ICSEE 2020 Workshops - Workshops of the 6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020, Proceedings. ed. / Minrui Fei; Kang Li; Zhile Yang; Qun Niu; Xin Li. Springer Science and Business Media Deutschland GmbH, 2020. p. 456-468 (Communications in Computer and Information Science; Vol. 1303).

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

TY - GEN

T1 - Quantitative Regression Modeling of Cocoa Bean Content Based on Gated Dilated Convolution Network

AU - Chen, Yayu

AU - Zhou, Wenju

AU - Fei, Minrui

AU - Wang, Haikuan

AU - Han, Xiaofei

AU - Zhou, Huiyu

N1 - Funding Information: This research is financially supported by Natural Science Foundation of China (61877065), the National Key Research and Development Program of China (No. 2019YFB1405500) and Key Project of Science and Technology Commission of Shanghai Municipality under Grant (No. 16010500300). Publisher Copyright: © 2020, Springer Nature Singapore Pte Ltd. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

PY - 2020/1/12

Y1 - 2020/1/12

N2 - By analyzing the near-infrared spectrum, we can determine the quantitative relationship model between the spectral data of different cocoa beans and the target components. This paper proposes a predictive regression model based on 1D-CNN. Based on the traditional convolutional neural network, gating mechanisms and dilated convolutions are combined. The particle swarm optimization method is used to optimize the hyper-parameters of one-dimensional convolution. The end-to-end near-infrared predictive regression model does not require wavelength selection. It is convenient to use and has a strong promotional value. Taking the public cocoa beans near-infrared data set as an example, the method can predict the water and fat content in cocoa beans, and the effectiveness of the method is verified. Comparing the improved one-dimensional convolution with traditional one-dimensional convolution results and partial least squares regression, it shows better prediction accuracy and robustness.

AB - By analyzing the near-infrared spectrum, we can determine the quantitative relationship model between the spectral data of different cocoa beans and the target components. This paper proposes a predictive regression model based on 1D-CNN. Based on the traditional convolutional neural network, gating mechanisms and dilated convolutions are combined. The particle swarm optimization method is used to optimize the hyper-parameters of one-dimensional convolution. The end-to-end near-infrared predictive regression model does not require wavelength selection. It is convenient to use and has a strong promotional value. Taking the public cocoa beans near-infrared data set as an example, the method can predict the water and fat content in cocoa beans, and the effectiveness of the method is verified. Comparing the improved one-dimensional convolution with traditional one-dimensional convolution results and partial least squares regression, it shows better prediction accuracy and robustness.

KW - Convolutional neural network

KW - Dilated convolution

KW - Gating mechanisms

KW - Infrared spectroscopic data

UR - http://www.scopus.com/inward/record.url?scp=85101386337&partnerID=8YFLogxK

U2 - 10.1007/978-981-33-6378-6_34

DO - 10.1007/978-981-33-6378-6_34

M3 - Conference contribution

AN - SCOPUS:85101386337

SN - 9789813363779

T3 - Communications in Computer and Information Science

SP - 456

EP - 468

BT - Recent Featured Applications of Artificial Intelligence Methods. LSMS 2020 and ICSEE 2020 Workshops - Workshops of the 6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020, Proceedings

A2 - Fei, Minrui

A2 - Li, Kang

A2 - Yang, Zhile

A2 - Niu, Qun

A2 - Li, Xin

PB - Springer Science and Business Media Deutschland GmbH

T2 - 6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020

Y2 - 25 October 2020 through 25 October 2020

ER -

Chen Y, Zhou W, Fei M, Wang H, Han X, Zhou H. Quantitative Regression Modeling of Cocoa Bean Content Based on Gated Dilated Convolution Network. In Fei M, Li K, Yang Z, Niu Q, Li X, editors, Recent Featured Applications of Artificial Intelligence Methods. LSMS 2020 and ICSEE 2020 Workshops - Workshops of the 6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020, Proceedings. Springer Science and Business Media Deutschland GmbH. 2020. p. 456-468. (Communications in Computer and Information Science). doi: 10.1007/978-981-33-6378-6_34

Quantitative Regression Modeling of Cocoa Bean Content Based on Gated Dilated Convolution Network

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this