Hyperspectral and Ensemble Learning Method for Rapid Identification of Black Spot in Yali Pear at Gley Stage
ZHANG Fan1, WANG Wen-xiu1, ZHANG Yu-fan1, HU Ze-xuan1, ZHAO Dan-yang1, MA Qian-yun1, SHI Hai-yan2, SUN Jian-feng1*
1. College of Food Science and Technology, Hebei Agricultural University, Baoding 071000,China
2. College of Horticulture, Hebei Agricultural University, Baoding 071000,China
Abstract:It is still difficult to identify black pear spots in the early stage of infection because the changes in the appearance of the infected area are very small and difficult to be observed by the naked eye. This study combined hyperspectral imaging technology and Stacking integrated learning algorithm to realize gley identification and detection of pear black spot. Firstly, a hyperspectral imaging system was used to collect the hyperspectral images of healthy pear samples and different disease grades. The region of interest (ROI) was selected based on the images, and the average spectrum was extracted. Then, First derivative (FD), Second derivative (SD), Standard Normal Variable Transformation (SNVT), SNV-FD and SNV-SD pretreatments were performed on the extracted original spectral data. Then, the Competitive Adaptive Weight Sampling (CARS) method was used to extract the spectral information of the characteristic wavelength. Finally, the Least Square support vector machines (LS-SVM), K-nearest neighbor method (KNN), Random Forest (RF) and Linear discriminant Analysis (LDA)classification models are established respectively based on the screened feature information. Among them, the combination of SNV-FD-LSSVM, SNV-KNN and SNV-FD-RF was better, with test set accuracy of 94%, 88% and 88% respectively. In the models established by LS-SVM, KNN, RF and LDA algorithms, the number of test set accuracy not less than 85.00% are 5, 3, 2 and 0 respectively. Therefore, three classifiers, LS-SVM, KNN and RF, are selected for subsequent ensemble learning. In order to improve the model accuracy, the optimized LS-SVM, KNN and RF models were used as the base classifier to construct the Stacking learning framework, and the modeling results of a single classifier were compared and analyzed. The results showed that the overall recognition accuracy of the integrated learning model is 98.68%, which is 4.64% higher than that of the single classifier model, and the recognition rate of gley samples is 11% higher. The results confirmed the feasibility of hyperspectral imaging combined with an integrated learning method to identify pear samples with a black spot in the gley stage. The integrated model significantly improved the accuracy of the single model. Moreover, it provides a new method for early detection and disease classification of black pear spots, and lays a foundation for further study on applying integrated learning algorithms in qualitative spectral analysis.
Key words:Hyperspectral imaging technology; Black spot of pear; Stacking integrated model; Gley period; The base model
张 凡,王文秀,张宇帆,胡泽轩,赵丹阳,马倩云,石海燕,孙剑锋. 高光谱和集成学习的鸭梨黑斑病潜育期快速识别方法[J]. 光谱学与光谱分析, 2023, 43(05): 1541-1549.
ZHANG Fan, WANG Wen-xiu, ZHANG Yu-fan, HU Ze-xuan, ZHAO Dan-yang, MA Qian-yun, SHI Hai-yan, SUN Jian-feng. Hyperspectral and Ensemble Learning Method for Rapid Identification of Black Spot in Yali Pear at Gley Stage. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1541-1549.
[1] Pan T T, Chyngyz E, Sun D W, et al. Postharvest Biology and Technology, 2019, 154: 96.
[2] Li J B, Huang W Q, Tian X, et al. Computers and Electronics in Agriculture, 2016, 127: 582.
[3] JIN Xiu, QI Hai-jun, LI Shao-wen(金 秀, 齐海军, 李绍稳). Food Science(食品科学), 2018, 39(19): 233.
[4] Jarolmasjed S, Espinoza C Z, Sankaran S. Journal of Food Measurement and Characterization, 2017, 11(3): 987.
[5] Yuan R R, Liu G S, He G G, et al. Computers and Electronics in Agriculture, 2021, 182: 106043.
[6] Pan L Q, Zhang Q, Zhang W, et al. Food Chemistry, 2016, 192: 134.
[7] LIU Si-jia, TIAN You-wen, ZHANG Fang, et al(刘思伽, 田有文, 张 芳, 等). Food Science(食品科学), 2017, 38(8): 277.
[8] Ghoggali N, Douak F Z, Ghoggali W. Optik, 2022, 257: 168813.
[9] LU Wei, CAI Miao-miao, ZHANG Qiang, et al(卢 伟, 蔡苗苗, 张 强, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2021, 41(7): 2196.
[10] WU Jing-zhu, ZHANG Le, LI Jiang-bo, et al(吴静珠, 张 乐, 李江波, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2022, 53(5): 302.
[11] BAI Jian-yu, SONG Feng-hui, WU Zheng-bao, et al(白剑宇, 宋峰惠, 吴正保, 等). Xinjiang Agricultural Sciences(新疆农业科学), 2017, 54(9): 1651.
[12] Yu D M, Xu T Y, Song K. Spectroscopy Letters, 2018, 51: 191.
[13] Li J B, Huang W Q, Tian X, et al. Computers and Electronics in Agriculture, 2016, 127: 582.