Deep Neural Network-Based Sorghum Adulteration Detection in Baijiu Brewing

In Baijiu brewing process, suppliers may adulterate glutinous sorghum with commercially inferior japonica sorghum, which can affect the yield and quality of the final Baijiu production. Currently, sorghum adulteration detection in Baijiu brewing process in China is carried out manually by sampling a...

Full description

Saved in:
Bibliographic Details
Main Authors: Shanglin Yang, Yang Lin, Yong Li, Defu Xu, Suyi Zhang, Lihui Peng
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Open Journal of Instrumentation and Measurement
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9826840/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849304173661650944
author Shanglin Yang
Yang Lin
Yong Li
Defu Xu
Suyi Zhang
Lihui Peng
author_facet Shanglin Yang
Yang Lin
Yong Li
Defu Xu
Suyi Zhang
Lihui Peng
author_sort Shanglin Yang
collection DOAJ
description In Baijiu brewing process, suppliers may adulterate glutinous sorghum with commercially inferior japonica sorghum, which can affect the yield and quality of the final Baijiu production. Currently, sorghum adulteration detection in Baijiu brewing process in China is carried out manually by sampling and observation, which strongly depends on the experiences of workers. In this paper, we proposed a method that uses sorghum images as input and combines image processing and deep neural networks to identify grain varieties and calculate the adulteration ratio. Two derivative networks of CNN, i.e., ResNet and SqueezeNet are used to implement the deep neural networks for sorghum grain identification and adulteration ratio calculation. The classification accuracy of the ResNet and SqueezeNet based models reached 93.34% and 87.98% on test set, respectively. The root mean squared error (RSME) for adulteration ratio estimation is 4.95% and 7.73%, respectively. The mean absolute error (MAE) is 4.20% and 6.29% accordingly. The proposed pipeline is capable of realizing rapid and non-destructive adulteration detection of raw materials in industrial production, thus conducing to the industrial digital transformation and efficiency improvement.
format Article
id doaj-art-516730df582642c8be0c0fbd5691c4fa
institution Kabale University
issn 2768-7236
language English
publishDate 2022-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of Instrumentation and Measurement
spelling doaj-art-516730df582642c8be0c0fbd5691c4fa2025-08-20T03:55:48ZengIEEEIEEE Open Journal of Instrumentation and Measurement2768-72362022-01-0111810.1109/OJIM.2022.31900249826840Deep Neural Network-Based Sorghum Adulteration Detection in Baijiu BrewingShanglin Yang0https://orcid.org/0000-0002-1591-0846Yang Lin1https://orcid.org/0000-0002-5124-8650Yong Li2https://orcid.org/0000-0002-8304-4089Defu Xu3https://orcid.org/0000-0002-3948-0692Suyi Zhang4https://orcid.org/0000-0002-1898-3805Lihui Peng5https://orcid.org/0000-0001-7363-6374Department of Automation, Tsinghua University, Beijing, ChinaLuzhou Laojiao Company Ltd., Luzhou, ChinaLuzhou Laojiao Company Ltd., Luzhou, ChinaLuzhou Laojiao Company Ltd., Luzhou, ChinaLuzhou Laojiao Company Ltd., Luzhou, ChinaDepartment of Automation, Tsinghua University, Beijing, ChinaIn Baijiu brewing process, suppliers may adulterate glutinous sorghum with commercially inferior japonica sorghum, which can affect the yield and quality of the final Baijiu production. Currently, sorghum adulteration detection in Baijiu brewing process in China is carried out manually by sampling and observation, which strongly depends on the experiences of workers. In this paper, we proposed a method that uses sorghum images as input and combines image processing and deep neural networks to identify grain varieties and calculate the adulteration ratio. Two derivative networks of CNN, i.e., ResNet and SqueezeNet are used to implement the deep neural networks for sorghum grain identification and adulteration ratio calculation. The classification accuracy of the ResNet and SqueezeNet based models reached 93.34% and 87.98% on test set, respectively. The root mean squared error (RSME) for adulteration ratio estimation is 4.95% and 7.73%, respectively. The mean absolute error (MAE) is 4.20% and 6.29% accordingly. The proposed pipeline is capable of realizing rapid and non-destructive adulteration detection of raw materials in industrial production, thus conducing to the industrial digital transformation and efficiency improvement.https://ieeexplore.ieee.org/document/9826840/Adulteration detectionbrewing processdeep learningimage processingmachine vision
spellingShingle Shanglin Yang
Yang Lin
Yong Li
Defu Xu
Suyi Zhang
Lihui Peng
Deep Neural Network-Based Sorghum Adulteration Detection in Baijiu Brewing
IEEE Open Journal of Instrumentation and Measurement
Adulteration detection
brewing process
deep learning
image processing
machine vision
title Deep Neural Network-Based Sorghum Adulteration Detection in Baijiu Brewing
title_full Deep Neural Network-Based Sorghum Adulteration Detection in Baijiu Brewing
title_fullStr Deep Neural Network-Based Sorghum Adulteration Detection in Baijiu Brewing
title_full_unstemmed Deep Neural Network-Based Sorghum Adulteration Detection in Baijiu Brewing
title_short Deep Neural Network-Based Sorghum Adulteration Detection in Baijiu Brewing
title_sort deep neural network based sorghum adulteration detection in baijiu brewing
topic Adulteration detection
brewing process
deep learning
image processing
machine vision
url https://ieeexplore.ieee.org/document/9826840/
work_keys_str_mv AT shanglinyang deepneuralnetworkbasedsorghumadulterationdetectioninbaijiubrewing
AT yanglin deepneuralnetworkbasedsorghumadulterationdetectioninbaijiubrewing
AT yongli deepneuralnetworkbasedsorghumadulterationdetectioninbaijiubrewing
AT defuxu deepneuralnetworkbasedsorghumadulterationdetectioninbaijiubrewing
AT suyizhang deepneuralnetworkbasedsorghumadulterationdetectioninbaijiubrewing
AT lihuipeng deepneuralnetworkbasedsorghumadulterationdetectioninbaijiubrewing