耦合平均影响值-连续投影算法优化种子活力近红外检测模型

doi:10.3964/j.issn.1000-0593(2022)10-3135-08

Abstract
References
Related Citation (15)

Download: PDF (3129 KB)
Export: BibTeX | EndNote (RIS)

Abstract At present, near-infrared spectroscopy (NIRS) technology, can realize the rapid and non-destructive detection of seed vigor, but the vigor grade is generally less than 3, and the accuracy is not high.The contradiction between the increase of vigor level and model precision urgently needs to be solved in the near-infrared spectrum detection of seed vigor. Five kinds of seed samples were obtained by the artificial aging method, and the corresponding spectral data were collected to establish the BP prediction model. In order to improve the accuracy and robustness of the model, an algorithm of coupled Mean Impact Value-Successive Projection Algorithm (MIV_opt-SPA_sa) is presented. Aiming at the problem of determining the number of feature variables extracted by the Successive Projection Algorithm(SPA), the algorithm sets the number range of feature wavelengths and selects the best in this range to realize adaptive SPA(SPA_sa). Aiming at the problem that SPA algorithm takes a too long time, MIV algorithm is used to reduce the dimension of SPA algorithm. Although the MIV method can sort the wavelength influence values, it lacks the threshold value for selecting wavelength influence. Therefore, the relative distance ratio is introduced to optimize the MIV algorithm to effectively segment the characteristic wavelength range. The full spectrum with 1 845 wavelengths is extracted by the MIV_opt-SPA_sa algorithm, and 37 characteristic wavelengths are extracted, which are mainly distributed near the 7 main absorption peaks of near-infrared spectrum of maize seeds. The results show that the algorithm can effectively extract the characteristic wavelength, which is consistent with the NIR absorption characteristics of maize seed biochemical substances. In order to verify the effect of the algorithm on the performance of the model, the full spectrum BP model, SPA_sa-BP model, MIV-BP model, MIV_opt-SPA_sa-BP model and competitive adaptive reweighting CARS-BP model were established to classify the five grades of maize seed vigor. The average prediction accuracy of the MIV_opt-SPA_sa-BP model is 99.1%, which is higher than other models; the average prediction time is 14.382 s, which is lower than that of the MIV-BP model (24.523),CAR-BP (97.226) and SPA_sa-BP model (101.224 s), but higher than that of full-spectrum model (0.253 1); The best performance cross-entropy is 0.007 892, which is far lower than other 4 models. The experimental results show that the MIV_opt-SPA_sa algorithm can effectively improve the accuracy of the near-infrared detection model of maize seed vigor, realize multi-level, accurate and nondestructive detection of seed vigor, and provide a reference for optimizing the optimisation seed vigor detection model.

Key words：Near infrared spectroscopy; Seed vigor; Maize; Mean impact value; Successive projection algorithm

Received: 2021-07-29 Accepted: 2021-10-25

ZTFLH:

O657.33

Corresponding Authors: HU Jun E-mail: hj_1977@sohu.com

Cite this article:

YANG Dong-feng,LI Ai-chuan,LIU Jin-ming, et al. Optimization of Seed Vigor Near-Infrared Detection by Coupling Mean Impact Value With Successive Projection Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3135-3142.

URL:

http://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2022)10-3135-08 OR http://www.gpxygpfx.com/EN/Y2022/V42/I10/3135

[1] HU Jin, LI Yong-ping, HU Wei-min(胡晋, 李永平, 胡伟民). Principle and Method of Seed Viability Determination(种子生活力测定原理和方法). Beijing: China Agricultural Publishing House(北京: 中国农业出版社), 2009, 5.
[2] Maythem A A, Robert L G, Mauricio F S, et al. Seed Science Research, 2018, 28(3): 245.
[3] He X T, Feng X P, Sun D W, et al. Molecules, 2019, 24(12): 2227.
[4] LI Wu, LI Yan, LI Gao-ke, et al(李武, 李妍, 李高科, 等). Journal of Nuclear Agricultural Sciences(核农学报), 2018, 32(8): 1611.
[5] JIN Wen-ling, CAO Nai-liang, ZHU Ming-dong, et al(金文玲, 曹乃亮, 朱明东, 等). Chinese Optics(中国光学), 2020, 13(5): 1032.
[6] Rato Tiago J, Reis Marco S. Chemometrics and Intelligent Laboratory Systems, 2019, 186(6): 41.
[7] Zareef M, Chen Q S, Ouyang Q, et al. Analytical Methods, 2018, 10(25): 3023.
[8] ZHOU Hua-mao, CHEN Tian-bing, LIU Mu-hua, et al(周华茂, 陈添兵, 刘木华, 等). Chin. J. Anal. Chem. (分析化学), 2020, 48(6): 811.
[9] Dong Chunwang, Liu Zhongyuan, Yang Chongshan, et al. Infrared Physics & Technology, 2021, 119(11): 103934.
[10] Liu Jinming, Jin Shuo, Bao Changhao, et al. Bioresource Technology, 2021, 321(2): 124449.
[11] Yun Y H, Bin J, Liu D L, et al. Analytica Chimica Acta, 2019, 1058(2): 58.
[12] CHENG Jie-hong, CHEN Zheng-guang(程介虹, 陈争光). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(11): 3451.
[13] Jiang H, Xu W, Chen Q. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2019, 214(10): 366.
[14] Yang M, Xu D, Chen S, et al. Sensors, 2019, 19(2): 263.
[15] Nie Pengcheng, Zhang Jinnuo, Feng Xuping, et al. Sensors and Actualtors B: Chemical, 2019, 296(8): 126630.
[16] Wakholi C, Kandpal L M, Lee H, et al. Sensors and Actualtors B: Chemical, 2018, 255(3): 498.
[17] Song J, Li G, Yang X. Journal of the Science of Food and Agriculture, 2019, 99(11): 4898.
[18] Araùjo M U, Saldanha T, Galvão R K. Chemometrics and Intelligent Laboratory Systems, 2001, 57(2): 65.
[19] Dombi G W, Nandi P, Saxe J M. The Journal of Trauma: Injury, Infection, and Critical Care, 1995, 39(5): 915.
[20] Tan X, Ji Z, Zhang Y. Technology & Health Care, 2018, 26(6): 1.
[21] Zhang Z, Yang J. International Journal of Oil, Gas and Coal Technology, 2016, 11(3): 279.
[22] LI Da-hu, LI Qiu-ke, WANG Wen-cai, et al(李大虎, 李秋科, 王文才, 等). Coal Engineering(煤炭工程), 2020, 52(11): 154.
[23] YAN Yan-lu, CHEN Bin, ZHU Da-zhou(严衍禄, 陈斌, 朱大洲). Principle, Technology and Application of Near Infrared Spectroscopy(近红外光谱分析的原理、技术与应用). Beijing: China Light Industry Press(北京: 中国轻工业出版社), 2013. 2.
[24] PAN Qing-xian, DONG Hong-bin, HAN Qi-long, et al(潘庆先, 董红斌, 韩启龙, 等). Journal of University of Science and Technology of China(中国科学技术大学学报), 2017, 47(1): 18.