Recognition of maize seed varieties based on hyperspectral imaging technology and integrated learning algorithms
文献类型: 外文期刊
作者: Yang, Huan 1 ; Wang, Cheng 1 ; Zhang, Han 1 ; Zhou, Ya'nan 1 ; Luo, Bin 1 ;
作者机构: 1.Beijing Acad Agr & Forestry Sci, Res Ctr Intelligent Equipment, Beijing, Peoples R China
2.Natl Agr Intelligent Equipment Engn Technol Res Ct, Beijing, Peoples R China
3.Jiangsu Univ, Sch Agr Engn, Zhenjiang, Peoples R China
关键词: Hyperspectral; Random subspace ensemble learning; Maize seed; Variety recognition
期刊名称:PEERJ COMPUTER SCIENCE ( 影响因子:3.8; 五年影响因子:4.1 )
ISSN:
年卷期: 2023 年 9 卷
页码:
收录情况: SCI
摘要: Purity is an important factor of maize seed quality that affects yield, and traditional seed purity identification methods are costly or time-consuming. To achieve rapid and accurate detection of the purity of maize seeds, a method for identifying maize seed varieties, using random subspace integrated learning and hyperspectral imaging technology, was proposed. A hyperspectral image of the maize seed endosperm was collected to obtain a spectral image cube with a wavelength range of 400 similar to 1,000 nm. Methods, including Standard Normal Variate (SNV), multiplicative Scatter Correction (MSC), and Savitzky-Golay First Derivative (SG1) were used to preprocess raw spectral data. Iteratively retains informative variables (IRIV) and competitive adaptive reweighted sampling (CARS) were used to reduce the dimensions of the spectral data. A recognition model of maize seed varieties was established using k-nearest neighbor (KNN), support vector machine (SVM), line discrimination analysis (LDA) and decision tree (DT). Among the preprocessing methods, MSC has the best effect. Among the dimensionality reduction methods, IRIV has the best performance. Among the base classifiers, LDA had the highest precision. To improve the precision in identifying maize seed varieties, LDA was used as the base classifier to establish a random subspace ensemble learning (RSEL) model. Using MSC-IRIV-RSEL, precision increased from 0.9333 to 0.9556, and the Kappa coefficient increased from 0.9174 to 0.9457. This study shows that the method based on hyperspectral imaging technology combined with subspace ensemble learning algorithm is a new method for maize seed purity recognition.
- 相关文献
作者其他论文 更多>>
-
Ultrasensitive molecular imprinted electrochemical sensor for in vivo determination of glycine betaine in plants
作者:Ai, Geng;Zhou, Yanan;Zhang, Heng;Wei, Qian;Luo, Bin;Wang, Cheng;Xue, Xuzhang;Li, Aixue;Ai, Geng;Xie, Yingge
关键词:Molecularly imprinted polymer; Glycine betaine; In vivo measurement; Electrochemical sensor
-
An ultrasensitive probe-free electrochemical immunosensor for gibberellins employing polydopamine-antibody nanoparticles modified electrode
作者:You, Yang;Luo, Bin;Wang, Cheng;Dong, Hongtu;Wang, Xiaodong;Hou, Peichen;Li, Aixue;You, Yang;Sun, Lijun
关键词:Gibberellins; Immunosensor; Carboxylated graphene oxide; Carboxylated multi -walled carbon nanotubes; Polydopamine nanoparticles
-
Emergence of Antifungal Resistant Subclades in the Global Predominant Phylogenetic Population of Candida albicans
作者:Gong, Jie;Xu, Juan;Zhang, Shu;Geng, Yuan-Yuan;Zhao, Fei;Lu, Xin;He, Li-Hua;Zhang, Jian-Zhong;Chen, Xin-Fei;Zhang, Han;Xu, Ying-Chun;Xiao, Meng;Chen, Xin-Fei;Zhang, Han;Xu, Ying-Chun;Xiao, Meng;Fan, Xin;Fan, Xin;Li, Ruo-Yu;Wan, Zhe;Li, Ruo-Yu;Wan, Zhe;Li, Ruo-Yu;Chen, Sharon C-A;Kong, Fanrong;Sun, Zi-Yong;Kang, Mei;Liao, Kang;Guo, Da-Wen;Hu, Zhi-Dong;Chu, Yun-Zhuo;Zhao, Hong-Mei;Zou, Gui-Ling;Shen, Chong;Shen, Chong;Wu, Wei-Wei;Wang, He;Liu, Gui-Ming
关键词:Candida albicans; phylogenetic population; azole-resistance; Erg11p; Tac1p; azole-nonsusceptibility
-
Recombinant hemagglutinin displaying on yeast reshapes congenital lymphocyte subsets to prompt optimized systemic immune protection against avian influenza infection
作者:Zhang, Han;Li, Zexing;Zhang, Huixia;Guo, Yanyu;Zhang, Xinyi;Zhang, Lilin;Yang, Liu;Li, Shujun;Li, Changyan;Cui, Daqing;Xie, Ruyu;Huang, Jinhai;Li, Yongqing
关键词:avian influenza virus; Saccharomyces cerevisiae; innate immunity; vaccine; chicken
-
Study on the spatio-temporal evolution and influencing factors of farmland abandonment on a county scale
作者:Wang, Cheng;Su, Yue;Xie, Yan;Xia, Panpan;He, Shan;Cui, Yanglin;Cui, Yanglin
关键词:Farmland abandonment; Spatiotemporal evolution; Influencing factors; Yangtze River Delta; Pingyang County
-
Research on artificial neural networks to accurately predict element concentrations in nutrient solutions
作者:Zhai, Jiawei;Dong, Hongtu;Liu, Tianyang;Jin, Xiaotong;Luo, Bin;Li, Aixue;Wang, Cheng;Wang, Xiaodong;Zhai, Jiawei;Wang, Xiaodong;Wang, Xiaodong
关键词:nutrient solution measurement; multi-ion sensing; back propagation (BP); radial basis function (RBF); particle swarm optimization (PSO); genetic algorithm (GA); gravitational search algorithm (GSA)
-
Identification of wheat seed endosperm texture using hyperspectral imaging combined with an ensemble learning model
作者:Zhao, Wei;Luo, Bin;Bai, Weiwei;Kang, Kai;Zhang, Han;Zhao, Wei;Zhao, Xueni;Bai, Weiwei;Hou, Peichen;Zhang, Han
关键词:Wheat classification; Feature fusion; Endosperm texture; Vitreosity; Hyperspectral imaging; Ensemble learning