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 proceedingConference 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 languageEnglish
Title of host publicationRecent 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
EditorsMinrui Fei, Kang Li, Zhile Yang, Qun Niu, Xin Li
PublisherSpringer Science and Business Media Deutschland GmbH
Pages456-468
Number of pages13
ISBN (Print)9789813363779
DOIs
Publication statusPublished - 12 Jan 2020
Externally publishedYes
Event6th 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 202025 Oct 2020

Publication series

NameCommunications in Computer and Information Science
Volume1303
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference6th International Conference on Life System Modeling and Simulation, LSMS 2020, and 6th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2020
CountryChina
CityShanghai
Period25/10/202025/10/2020

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

  • Computer Science(all)
  • Mathematics(all)

Fingerprint Dive into the research topics of 'Quantitative Regression Modeling of Cocoa Bean Content Based on Gated Dilated Convolution Network'. Together they form a unique fingerprint.

Cite this