|
|
|
|
|
|
Fast Classification Method of Black Goji Berry (Lycium Ruthenicum Murr.) Based on Hyperspectral and Ensemble Learning |
LU Wei1, CAI Miao-miao1, ZHANG Qiang2, LI Shan3 |
1. Jiangsu Provincial Laboratory of Modern Facility Agriculture Technology and Equipment Engineering, College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210031, China
2. School of Water Resources and Hydropower, Qinghai University, Xining 810016, China
3. School of Life Science and Technology, Tongji University, Shanghai 200092, China |
|
|
Abstract Black goji berry has high nutrition and medical value. Different grades of black goji berry have different quality, and prices are also significantly different. However, due to the lack of effective detection and grading methods, the black goji berry market is chaotic, and the bad become mixed with the good, which affects the black goji berry market’s quality supervision. To achieve fast, non-destructive and high-precision classification of black goji berry, this paper proposes a fast non-destructive classification method of black goji berry based on hyperspectral and ensemble learning. First of all, for Nomhong 1st grade (NMH-grade1), Nomhong 2nd grade (NMH-grade2), Nomhong 3rd grade (NMH-grade3), Nomhong 4th grade (NMH-grade4), select 200 for each grade. Then, in two placement modes (carpopodium up and overall horizontal after removing the carpopodium), the spectral image cube with a spectral range of 391.6~2 528.1 nm is acquired using a GaiaSorter-Dual wide-band hyperspectral sorter. Through the mask processing, automatically extract single black goji berry ROI hyperspectral information with cell counting algorithm. The spectral information of black goji berry in the range of 500~2 400 nm is extracted. After FD(First Derivative), FFT(Fast Fourier Transform), HT(Hilbert Transform), SG(Savitzky Golay), Normalize, SNV(Standard Normal Variate) preprocessing, the spectral information of the characteristic wavelength is extracted by PCA(Principal Components Analysis), SPA(Successive Projection Algorithm), CARS(Competitive Adaptive Reweighted Sampling). Then build LIBSVM, LDA(Latent Dirichlet Allocation), KNN(k-Nearest Neighbor), RF(Random Forest), NB(Naive Bayes) detection models. The combination of sarcocarp-Normalize-SPA-LDA, sarcocarp-FD-CARS-RF and sarcocarp-SNV-CARS-LIBSVM is the best, with accuracy rates of 0.941 7, 0.941 7 and 0.937 5, respectively. At the same time, it can be found that in the pretreatment, FD, HT, Normalize, and SNV have better effects. In the dimensionality reduction method, the models of SPA and CARS have better effects. And in the models established by LIBSVM, LDA, KNN, RF, and NB, the number of test set accuracy rates of not less than 0.9 are 2, 7, 0, 4, and 1, respectively, so the three classifiers LDA, RF, and LIBSVM work best. To further improve the classification accuracy of black goji berry, LDA, RF and LIBSVM are used as meta-models to build a fast and non-destructive classification model of black goji berry Stacking ensemble learning. When the sarcocarp-FD-SPA-Stacking is combined, the accuracy can be improved from 0.941 7 to 0.983 3. A total of 17 characteristic wavelengths is extracted, respectively (in nm): 591.6, 609.1, 721.6, 989.1, 1 083.3, 1 111.3, 1 296.1, 1 564.9, 1 844.9, 1 934.5, 1 996.1, 2 046.5, 2 130.5, 2 292.9, 2 315.3, 2 320.9, 2 348.9. Among them, there are C-H frequency doubling peaks and absorption peaks near 721.6, 1 083.3, 1 111.3, 2 130.5, 2 292.9, 2 315.3, 2 320.9, 2 348.9, O—H frequency doubling peaks and absorption peaks near 721.6, 989.1, 1 934.5, 1 996.1, 2 292.9, and C—O absorption peaks near 2 130.5 and 2 292.9. Research has shown that fast and non-destructive classification of black goji berry based on hyperspectral combined with ensemble learning is feasible.
|
Received: 2020-05-16
Accepted: 2020-09-21
|
|
|
[1] ZHANG Ying, CHEN Hao(张 莹, 陈 浩). The Food Industry(食品工业), 2018, 39(3): 312.
[2] He J, Chen L, Chu B, et al. Molecules, 2018, 23(9): 2395.
[3] WANG Lei, QIN Hong, LI Jing, et al(王 磊, 覃 鸿, 李 静,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(4): 1270.
[4] YU Hui-chun, WANG Run-bo, YIN Yong, et al(于慧春, 王润博, 殷 勇, 等). Journal of Nuclear Agricultural Sciences(核农学报), 2018, 32(3): 523.
[5] Zhu S, Chao M, Zhang J, et al. Sensors, 2019, 19(23): 5225.
[6] Xu Y, Zhang H, Zhang C, et al. Infrared Physics & Technology, 2019, 102: 103034.
[7] Zhang J, Huang Y, Reddy K N, et al. Pest Management Science, 2019, 75(12): 3260.
[8] Ahn D H, Choi J Y, Kim H C, et al. Sensors, 2019, 19(7): 1560.
[9] YUAN Pei-sen, YANG Cheng-lin, SONG Yu-hong, et al(袁培森, 杨承林, 宋玉红, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2019, 50(11): 144.
[10] GONG Fang-fang, LIAO Bi-fang, DONG Jia-jia(巩芳芳, 廖碧芳, 董佳佳, 等). Journal of Zhengzhou University·Medical Sciences(郑州大学学报·医学版), 2019,54(4): 531.
[11] FAN Xiao-yi, QU Jun-hao, QU Bao-an, et al(范晓易, 曲均浩, 曲保安, 等). Journal of Geodesy and Geodynamics(大地测量与地球动力学), 2019, 39(9): 916.
[12] MA Rong, SHAN Jing, CHEN Bing-bing, et al(马 蓉, 单 璟, 陈兵兵, 等). Guangzhou Chemical Industry(广州化工),2020,48(3):17,51. |
[1] |
LIU Shu-hong1, 2, WANG Lu-si3*, WANG Li-sheng3, KANG Zhi-juan1, 2,WANG Lei1, 2,XU Lin1, 2,LIU Ai-qin1, 2. A Spectroscopic Study of Secondary Minerals on the Epidermis of Hetian Jade Pebbles From Xinjiang, China[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 169-175. |
[2] |
GAO Hong-sheng1, GUO Zhi-qiang1*, ZENG Yun-liu2, DING Gang2, WANG Xiao-yao2, LI Li3. Early Classification and Detection of Kiwifruit Soft Rot Based on
Hyperspectral Image Band Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 241-249. |
[3] |
LIANG Shou-zhen1, SUI Xue-yan1, WANG Meng1, WANG Fei1, HAN Dong-rui1, WANG Guo-liang1, LI Hong-zhong2, MA Wan-dong3. The Influence of Anthocyanin on Plant Optical Properties and Remote Sensing Estimation at the Scale of Leaf[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 275-282. |
[4] |
MU Da1, 2, WANG Qi-shu1, 2*, CUI Zong-yu1, 2, REN Jiao-jiao1, 2, ZHANG Dan-dan1, 2, LI Li-juan1, 2, XIN Yin-jie1, 2, ZHOU Tong-yu3. Study on Interference Phenomenon in Terahertz Time Domain
Spectroscopy Nondestructive Testing of Glass Fiber Composites[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3031-3040. |
[5] |
CAI Jian-rong1, 2, HUANG Chu-jun1, MA Li-xin1, ZHAI Li-xiang1, GUO Zhi-ming1, 3*. Hand-Held Visible/Near Infrared Nondestructive Detection System for Soluble Solid Content in Mandarin by 1D-CNN Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2792-2798. |
[6] |
TANG Ruo-han1, 2, LI Xiu-hua1, 2*, LÜ Xue-gang1, 2, ZHANG Mu-qing2, 3, YAO Wei2, 3. Transmittance Vis-NIR Spectroscopy for Detecting Fibre Content of
Living Sugarcane[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2419-2425. |
[7] |
LUO Zheng-fei1, GONG Zheng-li1, 2, YANG Jian1, 2*, YANG Chong-shan2, 3, DONG Chun-wang3*. Rapid Non-Destructive Detection Method for Black Tea With Exogenous Sucrose Based on Near-Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2649-2656. |
[8] |
ZHANG Yue1, 2, LI Yang1, 2, SONG Yue-peng1, 2*. Nondestructive Detection of Slight Mechanical Damage of Apple by Hyperspectral Spectroscopy Based on Stacking Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2272-2277. |
[9] |
LI Quan-lun1, CHEN Zheng-guang1*, JIAO Feng2. Prediction of Oil Content in Oil Shale by Near-Infrared Spectroscopy Based on Stacking Ensemble Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(04): 1030-1036. |
[10] |
SHENG Qiang1, 2, ZHENG Jian-ming1*, LIU Jiang-shan2, SHI Wei-chao1, LI Hai-tao2. Advances and Prospects in Inner Surface Defect Detection Based on Cite Space[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 9-15. |
[11] |
ZHANG Zhi-wei1, 2, QIU Rong1, 2*, YAO Yin-xu1, 2, WAN Qing3, PAN Gao-wei1, SHI Jin-fang1. Measurement and Analysis of Uranium Using Laser-Induced
Breakdown Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 57-61. |
[12] |
JU Wei1, LU Chang-hua2, 3, ZHANG Yu-jun3, CHEN Xiao-jing1, JIANG Wei-wei2*. Research on Quantitative Regression Method of IR Spectra of Organic Compounds Based on Ensemble Learning With Wavelength Selection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 239-247. |
[13] |
ZHU Jin-yan, ZHU Yu-jie*, FENG Guo-hong*, ZENG Ming-fei, LIU Si-qi. Optimization of Near-Infrared Detection Model of Blueberry Sugar Content Based on Deep Belief Network and Hybrid Wavelength Selection Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(12): 3775-3782. |
[14] |
WANG Wei, LI Yong-yu*, PENG Yan-kun, YANG Yan-ming, YAN Shuai, MA Shao-jin. Design and Experiment of a Handheld Multi-Channel Discrete Spectrum Detection Device for Potato Processing Quality[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(12): 3889-3895. |
[15] |
LI Ming1*, HAN Dong-hai2*, LU Ding-qiang1, LU Xiao-xiang1, CHAI Chun-xiang1, LIU Wen3, SUN Ke-xuan1. Research Progress of Universal Model of Near-Infrared Spectroscopy in Agricultural Products and Foods Detection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(11): 3355-3360. |
|
|
|
|