Identification of mould varieties infecting maize kernels based on Raman hyperspectral imaging technique combined with multi-channel residual module convolutional neural network
文献类型: 外文期刊
作者: Long, Yuan 1 ; Tang, Xiuying 1 ; Fan, Shuxiang 2 ; Zhang, Chi 2 ; Zhang, Bin 1 ; Huang, Wenqian 2 ;
作者机构: 1.China Agr Univ, Coll Engn, Beijing 100083, Peoples R China
2.Beijing Acad Agr & Forestry Sci, Intelligent Equipment Res Ctr, Beijing 100097, Peoples R China
3.Natl Res Ctr Intelligent Equipment Agr, Beijing 100097, Peoples R China
关键词: Raman hyperspectral imaging; Maize kernels; Mould varieties; Residual unit; Nondestructive detection
期刊名称:JOURNAL OF FOOD COMPOSITION AND ANALYSIS ( 影响因子:4.3; 五年影响因子:4.6 )
ISSN: 0889-1575
年卷期: 2024 年 125 卷
页码:
收录情况: SCI
摘要: Maize kernels are easily infected with different kinds of moulds in nature which has terrible negative effects on kernels. In this research, a series of multi-channel residual modules (MCRMs) were introduced to convolutional neural network (CNN) to identify the mould varieties combined with Raman hyperspectral imaging technique. Specifically, Raman hyperspectral images of maize kernels infected with different moulds were acquired and their characteristics were summarized and prepared for further analysis. Traditional machine learning (TML) models and deep learning (DL) models were both established and compared. For TML, three kinds of modeling methods combined with four kinds of variables selection methods were applied to establish the mould varieties identification model. For DL, five different residual units were explored to obtain the optimal MCRM-CNN architecture. The results showed that MCRM-CNN was more capable of mining hidden information compared with TML methods. Finally, MCRM-CNN-SVM provided the optimal model to identify the moulds varieties with accuracy in the testing set of 100% by taking the variables extracted by MCRM-CNN as the inputs of SVM. The residual unit was composed of three stacking residual blocks with different kernels of 3, 5, 7 without the shortcut connection (MNR) and the recall rates of A. niger, A. flavus, A. glaucus, A. parasiticus and control set were all 100%, respectively. Consequently, the proposed method expanded the nondestructive online detection for identifying mould varieties infecting maize kernels by combining RHSI and DL.
- 相关文献
作者其他论文 更多>>
-
Fusion of spectra and texture data of hyperspectral imaging for prediction of myoglobin content in nitrite-cured mutton
作者:Wan, Guoling;Liu, Guishan;He, Jianguo;Li, Yan;Guo, Mei;Wan, Guoling;Fan, Shuxiang;Fan, Shuxiang;Wang, Wei;Ma, Chao;Cheng, Lijuan
关键词:Hyperspectral imaging; Texture data; Myoglobin; Spectral dimensionality reduction; Information fusion
-
Non-destructive detection of single-seed viability in maize using hyperspectral imaging technology and multi-scale 3D convolutional neural network
作者:Fan, Yaoyao;Zhao, Chunjiang;Fan, Yaoyao;An, Ting;Wang, Qingyan;Yang, Guang;Huang, Wenqian;Wang, Zheli;Zhao, Chunjiang;Tian, Xi
关键词:viability detection; maize seeds; hyperspectral imaging; YOLOv7 model; 3D convolution neural network
-
Assessment of protein content and insect infestation of maize seeds based on on-line near-infrared spectroscopy and machine learning
作者:Wang, Zheli;Wang, Zheli;Huang, Wenqian;Li, Jiangbo;Liu, Sanqing;Fan, Shuxiang
关键词:Maize seeds; Near-infrared spectra; On-line detection; Machine learning
-
Monitoring the major taste components during black tea fermentation using multielement fusion information in decision level
作者:An, Ting;Li, Guanglin;Zhao, Chunjiang;An, Ting;Dong, Chunwang;An, Ting;Wang, Zheli;Fan, Shuxiang;Huang, Wenqian;Tian, Xi;Duan, Dandan;Zhao, Chunjiang
关键词:Black tea; Hyperspectral imaging; Electrical properties; Data fusion; Stacking combination strategy
-
Physiological Alterations and Nondestructive Test Methods of Crop Seed Vigor: A Comprehensive Review
作者:Xing, Muye;Xing, Muye;Long, Yuan;Wang, Qingyan;Tian, Xi;Fan, Shuxiang;Zhang, Chi;Huang, Wenqian;Xing, Muye;Long, Yuan;Wang, Qingyan;Tian, Xi;Fan, Shuxiang;Zhang, Chi;Huang, Wenqian;Xing, Muye;Long, Yuan;Wang, Qingyan;Tian, Xi;Fan, Shuxiang;Zhang, Chi;Huang, Wenqian;Xing, Muye;Long, Yuan;Wang, Qingyan;Tian, Xi;Fan, Shuxiang;Zhang, Chi;Huang, Wenqian
关键词:physiological factors; novel test; mechanism
-
Development of a General Prediction Model of Moisture Content in Maize Seeds Based on LW-NIR Hyperspectral Imaging
作者:Wang, Zheli;Wang, Zheli;Li, Jiangbo;Zhang, Chi;Fan, Shuxiang
关键词:general prediction model; hyperspectral imaging; maize seed; moisture content
-
Detection of early bruises on apples using hyperspectral reflectance imaging coupled with optimal wavelengths selection and improved watershed segmentation algorithm
作者:Tian, Xi;He, Xin;Zhang, Chi;Li, Jiangbo;Huang, Wenqian;Liu, Xuefeng;Liu, Xuefeng;Huang, Wenqian
关键词:hyperspectral imaging; bruise detection; band ratio image; apple; improved watershed segmentation algorithm