近红外结合线性回归算法快速预测小麦籽粒干物质和重量

陈岩; 何鸿举; 欧阳娟; 欧行奇; 郭景丽; 王玉玲; 乔红; 李新华

doi:10.13386/j.issn1002-0306.2021060159

NIR Combined with Linear Regression Algorithm for Rapid Prediction of Dry Matter and Weight in Wheat Grain

1.
School of Food Science, Henan Institute of Science and Technology, Xinxiang 453003, China
2.
Xinxiang Nongle Seed Industry Co., Ltd, Xinxiang 453003, China
3.
School of Life Science and Technology, Henan Institute of Science and Technology, Xinxiang 453003, China
4.
Henan Xinlianxin Chemical Industry Group Co., Ltd., Xinxiang 453004, China

More Information

Corresponding author:
HE Hongju: 何鸿举（1983−），男，博士，副教授，主要从事食品质量分析与快速检测方面的研究，E-mail：hongju_he007@126.com

近红外结合线性回归算法快速预测小麦籽粒干物质和重量

1.
河南科技学院食品学院，河南新乡 453003
2.
新乡市农乐种业有限责任公司，河南新乡 453003
3.
河南科技学院生命科技学院，河南新乡 453003
4.
河南心连心化学工业集团股份有限公司，河南新乡 453004

详细信息

中图分类号: TS251.7
计量
- 文章访问数: 227
- HTML全文浏览量: 50
- PDF下载量: 22
出版历程
- 收稿日期: 2021-06-17
- 网络出版日期: 2021-12-17
- 刊出日期: 2022-02-14

摘要

Abstract: In order to realize simultaneous and rapid nondestructive detection of wheat quality (dry matter, weight), 35 wheat varieties samples were subjected to near-infrared (NIR) system scanning, and the spectral information were acquired and pretreated by three methods including Gaussian filtering smoothing (GFS), normalize (N) and baseline correction (BC), respectively. Partial least squares (PLS) algorithm was adopted to build a quantitative relationship between spectra and reference value of dry matter and weight, respectively. Two methods such as regression coefficients (RC) and successive projections algorithm (SPA) were applied to select optimal wavelengths from the full 900~1700 nm range for PLS model optimization. Based on the selected optimal wavelengths, PLS and multiple linear regression (MLR) prediction models were built respectively. The results indicated that the RC-RAW-PLS models based on 20 optimal wavelengths selected from RAW spectra by RC method had better performance in dry matter prediction, with r_P of 0.93 and RMSEP of 0.03%. The SPA-RAW-MLR model built with 12 optimal wavelengths selected from RAW spectra by SPA method had better performance in weight prediction, with r_P of 0.89 and RMSEP of 0.32 g. In conclusion, NIR spectroscopy combined with PLS and MLR algorithm could be used for rapid prediction of dry matter and weight in wheat grain.
- near-infrared (NIR) /
- wheat /
- partial least square (PLS) /
- dry matter /
- weight
摘要: 为了实现小麦品质（干物质、重量）的快速无损检测，对35个小麦品种样品进行了近红外系统扫描，获取光谱信息，并进行高斯滤波平滑（GFS）、归一化（N）和基线校正（BC）预处理。采用偏最小二乘（PLS）算法分别建立光谱信息与干物质和重量参考值之间的定量关系。采用回归系数法（RC）和连续投影算法（SPA）两种方法在900~1700 nm范围内选择最优波长对全波段PLS模型进行优化。基于选择的最优波长，分别建立PLS和MLR预测模型。结果表明，基于RC法从RAW光谱中筛选出的20个最佳波长构建的RC-RAW-PLS模型对干物质有较好的预测性能，r_P为0.93，RMSEP为0.03%。基于SPA法从RAW光谱中选取的12个最优波长建立的SPA-RAW-MLR模型对重量有较好的预测性能，r_P为0.89，RMSEP为0.32 g。综上所述，近红外光谱结合PLS和MLR算法可分别用于小麦籽粒干物质和重量的快速预测。
- 近红外 /
- 小麦 /
- 偏最小二乘 /
- 干物质 /
- 重量

HTML全文

Figure 1. NIR reflectance characteristics of wheat grain samples for dry matter

Notes: (a) GFS spectra, (b) N spectra, (c) BC spectra and (d) RAW spectra. Fig.2 is the same as Fig.1.

下载: 全尺寸图片幻灯片

Figure 2. NIR reflectance characteristics of wheat grain samples for weight

下载: 全尺寸图片幻灯片

Table 1 Reference values of dry matter and weight in wheat grain

Index	Sample set	Number of sample	Minimum	Maximum	Mean	Standard deviation
Dry matter	Calibration	97	98.61%	99.00%	98.89%	0.08
Dry matter	Prediction	48	98.66%	98.99%	98.89%	0.07
Weight	Calibration	87	17.91 g	21.50 g	19.37 g	0.70
Weight	Prediction	43	18.03 g	20.84 g	19.34 g	0.67

下载: 导出CSV

Table 2 Dry matter and weight prediction by PLS models based on full NIR wavelength

Index	Spectra	Model	Number of wavelengths	Latent variables	Calibration		Cross-validation		Prediction			∆E
Index	Spectra	Model	Number of wavelengths	Latent variables	r_C	RMSEC	r_CV	RMSECV	r_P	RMSEP	RPD	∆E
Dry matter	GFS	GFS-PLS	400	9	0.96	0.02%	0.92	0.03%	0.92	0.03%	2.33	0.01
	N	N-PLS	400	8	0.96	0.02%	0.93	0.03%	0.91	0.03%	2.33	0.01
	BC	BC-PLS	400	9	0.96	0.02%	0.92	0.03%	0.91	0.03%	2.33	0.01
	RAW	RAW-PLS	400	9	0.96	0.02%	0.93	0.03%	0.91	0.03%	2.33	0.01
Weight	GFS	GFS-PLS	400	5	0.82	0.46 g	0.76	0.52 g	0.72	0.51 g	1.49	0.05
	N	N-PLS	400	4	0.82	0.45 g	0.75	0.54 g	0.74	0.49 g	1.63	0.04
	BC	BC-PLS	400	5	0.82	0.45 g	0.75	0.53 g	0.74	0.50 g	1.43	0.05
	RAW	RAW-PLS	400	5	0.82	0.45 g	0.75	0.53 g	0.73	0.50 g	1.60	0.05

下载: 导出CSV

Table 3 Results of optimal wavelengths selected by RC and SPA methods for dry matter prediction

Spectra	Wavelength selection method	Number of full wavelength	The specific optimal wavelengths	Number of optimal wavelengths	Wavelength reduction（%）
Raw	RC	400	920.03, 971.72, 1056.56, 1065.30, 1135.56, 1209.00, 1217.31, 1324.34, 1438.18, 1461.00, 1520.78, 1596.41, 1645.73, 1661.58, 1673.39, 1677.30, 1682.19, 1685.12, 1692.91 and 1697.76 nm	20	95
Raw	SPA	400	901.76, 1107.40, 1203.05, 1682.19 and 1690.96 nm	5	99
GFS	RC	400	912.21, 922.64, 926.54, 935.62, 967.87, 1009.98, 1108.63, 1122.12, 1127.01, 1130.68, 1205.43, 1326.62, 1327.76, 1381.89, 1401.91, 1631.76, 1647.72, 1650.7, 1663.55, 1678.28, 1684.15, 1692.91, 1693.88 and 1699.69 nm	24	94
GFS	SPA	400	958.87, 1680.24, 1697.76, 1699.69, and 1700.66 nm	5	99
N	RC	400	938.21, 956.30, 974.29, 1015.05, 1023.90, 1091.37, 1175.51, 1213.75, 1324.34, 1405.23, 1610.62, 1634.76, 1673.39 and 1692.91 nm	14	97
N	SPA	400	910.91, 1192.30, 1205.43, 1324.34, 1395.25, 1682.19, 1685.12, 1692.91 and 1697.76 nm	9	98
BC	RC	400	908.30, 910.91, 912.21, 960.16, 967.87, 971.72, 1007.44, 1021.37, 1085.18, 1091.37, 1107.40, 1119.67, 1124.57, 1213.75, 1324.34, 1326.62, 1610.62, 1619.71, 1629.75, 1673.39, 1677.30, 1690.96, 1692.91, 1693.88, and 1697.76 nm	25	94
BC	SPA	400	1203.05, 1461.00, 1690.96, 1692.91 and 1695.82 nm	5	99

下载: 导出CSV

Table 4 Results of optimal wavelengths selected by RC and SPA methods for weight prediction

Spectra	Wavelength selection method	Number of full wavelength	The specific optimal wavelengths	Number of optimal wavelengths	Wavelength reduction （%）
RAW	RC	400	908.30, 922.64, 931.73, 947.27, 1061.56, 1217.31, 1257.34, 1260.85, 1358.35, 1397.47, 1445.81, 1498.54, 1620.71, 1626.74, 1645.73, 1673.39, 1680.24, 1682.19, 1689.02, 1697.76 and 1699.69 nm	21	95
RAW	SPA	400	901.76, 1093.84, 1319.77, 1450.16, 1613.65, 1678.28, 1680.24, 1682.19, 1685.12, 1687.07, 1689.02 and 1699.69 nm	12	97
GFS	RC	400	903.07, 1152.57, 1156.21, 1158.63, 1161.05, 1162.25, 1180.32, 1225.6, 1230.32, 1258.51, 1269.01, 1293.35, 1322.06, 1624.74, 1638.76, 1675.35, 1680.24 and 1682.19 nm	18	96
GFS	SPA	400	901.76, 1096.31, 1198.28, 1458.83, 1615.67, 1680.24, 1682.19, 1684.15, 1685.12, 1687.07, 1690.96 and 1700.66 nm	12	97
N	RC	400	905.68, 908.3, 910.91, 914.82, 917.43, 922.64, 931.73, 940.8, 947.27, 997.28, 1003.63, 1009.98, 1021.37, 1036.5, 1050.30, 1061.56, 1082.7, 1090.13, 1096.31, 1098.78, 1102.47, 1108.63, 1397.47, 1626.74, 1689.02, 1697.76 and 1699.69 nm	27	93
N	SPA	400	901.76, 1236.22, 1463.16, 1678.28, 1685.12, 1689.02, 1692.91 and 1699.69 nm	8	98
BC	RC	400	922.64, 929.13, 940.8, 1023.9, 1061.56, 1211.38, 1327.76, 1376.31, 1445.81, 1498.54, 1624.74, 1626.74, 1645.73, 1654.66, 1673.39, 1678.28, 1684.15, 1689.02, 1693.88, 1695.82, 1697.76 and 1699.69 nm	22	95
BC	SPA	400	901.76, 1061.56, 1399.69, 1481.45, 1636.76, 1675.35, 1678.28, 1682.19, 1685.12, 1689.02, 1690.96 and 1697.76 nm	12	97

下载: 导出CSV

Table 5 Dry matter and weight prediction by PLS models based on optimal wavelengths

Index	Wavelengths selection method	Model	Number of optimal wavelengths	Calibration		Cross validation		Prediction			∆E
Index	Wavelengths selection method	Model	Number of optimal wavelengths	r_C	RMSEC	r_CV	RMSECV	r_P	RMSEP	RPD	∆E
Dry matter	RC	RC-GFS-PLS	24	0.93	0.03%	0.83	0.04%	0.93	0.03%	2.33	0.00
		RC-N-PLS	14	0.93	0.03%	0.91	0.03%	0.88	0.04%	1.75	0.01
		RC-BC-PLS	25	0.73	0.05%	0.55	0.06%	0.71	0.05%	1.40	0.00
		RC-RAW-PLS	20	0.94	0.02%	0.89	0.03%	0.93	0.03%	2.33	0.01
	SPA	SPA-GFS-PLS	5	−	−	−	−	−	−	−	−
		SPA-N-PLS	9	0.91	0.03%	0.89	0.03%	0.87	0.04%	1.75	0.01
		SPA-BC-PLS	5	0.49	0.07%	0.39	0.07%	0.54	0.06%	1.17	0.01
		SPA-RAW-PLS	5	0.55	0.06%	0.46	0.07 %	0.47	0.07%	1.13	0.01
Weight	RC	RC-GFS-PLS	18	0.88	0.33 g	0.75	0.46 g	0.50	0.57 g	1.18	0.24
		RC-N-PLS	27	0.90	0.31 g	0.85	0.37 g	0.74	0.45 g	1.49	0.14
		RC-BC-PLS	22	0.87	0.34 g	0.79	0.43 g	0.74	0.44 g	1.52	0.10
		RC-RAW-PLS	21	0.91	0.28 g	0.87	0.34 g	0.69	0.48 g	1.40	0.20
	SPA	SPA-GFS-PLS	12	0.90	0.31 g	0.85	0.37 g	0.81	0.38 g	1.76	0.07
		SPA-N-PLS	8	0.85	0.36 g	0.82	0.41 g	0.84	0.36 g	1.86	0.00
		SPA-BC-PLS	12	0.88	0.33 g	0.84	0.38 g	0.78	0.42 g	1.60	0.09
		SPA-RAW-PLS	12	0.89	0.32 g	0.85	0.37 g	0.81	0.39 g	1.72	0.07

下载: 导出CSV

Table 6 Dry matter and weight prediction by MLR models based on optimal wavelengths

Index	wavelengths selection method	Model	Number of optimal wavelengths	Calibration		Cross validation		Prediction			∆E
Index	wavelengths selection method	Model	Number of optimal wavelengths	r_C	RMSEC	r_CV	RMSECV	r_P	RMSEP	RPD	∆E
Dry matter	RC	RC-GFS-MLR	24	0.94	0.03%	0.82	0.04%	0.84	0.04%	1.75	0.01
		RC-N-MLR	14	0.94	0.03%	0.88	0.04%	0.88	0.04%	1.75	0.01
		RC-BC-MLR	25	0.95	0.02%	0.89%	0.04%	0.86	0.04%	1.75	0.02
		RC-RAW-MLR	20	0.94	0.03%	0.87	0.04%	0.91	0.03%	2.33	0.00
	SPA	SPA-GFS-MLR	5	̶	̶	̶	̶	̶	̶	̶	̶
		SPA-N-MLR	9	0.91	0.03%	0.89	0.03%	0.87	0.04%	1.75	0.01
		SPA-BC-MLR	5	0.50	0.07%	0.33	0.07%	0.53	0.06%	1.17	0.01
		SPA-RAW-MLR	5	0.57	0.06%	0.46	0.07%	0.47	0.07%	1.13	0.01
Weight	RC	RC-GFS-MLR	18	0.88	0.33 g	0.74	0.47 g	0.46	0.58 g	1.16	0.25
		RC-N-MLR	27	0.92	0.27 g	0.77	0.44 g	0.60	0.53 g	1.26	0.26
		RC-BC-MLR	22	0.90	0.31 g	0.71	0.49 g	0.67	0.45 g	1.49	0.14
		RC-RAW-MLR	21	0.92	0.27 g	0.84	0.38 g	0.68	0.48 g	1.40	0.21
	SPA	SPA-GFS-MLR	12	0.90	0.31 g	0.85	0.37 g	0.87	0.33 g	2.03	0.02
		SPA-N-MLR	8	0.85	0.36 g	0.80	0.41 g	0.84	0.36 g	1.86	0.00
		SPA-BC-MLR	12	0.89	0.32 g	0.84	0.38 g	0.77	0.42 g	1.60	0.10
		SPA-RAW-MLR	12	0.89	0.32 g	0.84	0.37 g	0.89	0.32 g	2.09	0.00

下载: 导出CSV

Table 7 Comparison of optimal prediction results of dry matter and weight value of wheat grain by PLS and MLR mode

Index	wavelengths selection method	Model	Number of optimal wavelengths	Calibration		Cross validation		Prediction			∆E
Index	wavelengths selection method	Model	Number of optimal wavelengths	r_C	RMSEC	r_CV	RMSECV	r_P	RMSEP	RPD	∆E
Dry matter	RC	RC-RAW-PLS	20	0.94	0.02%	0.89	0.03%	0.93	0.03%	2.33	0.01
Dry matter	RC	RC-RAW-MLR	20	0.94	0.03%	0.87	0.04%	0.91	0.03%	2.33	0.00
weight	SPA SPA	SPA-N-PLS	8	0.85	0.36 g	0.82	0.41 g	0.84	0.36 g	1.86	0.00
weight	SPA SPA	SPA-RAW-MLR	12	0.89	0.32 g	0.84	0.37 g	0.89	0.32 g	2.09	0.00

下载: 导出CSV

参考文献(35)

[1]	HE Z H, ZHUANG Q S, CHENG S H, et al. Wheat industry development and scientific and technological progress in China[J]. Journal of Agronomy,2018,8(1):99−106.
[2]	WEI Z Y, SI Z F, WANG Y. Detection of wheat protein content based on near-infrared diffuse reflectance spectroscopy[J]. Science and Technology of Light Industry,2018,34(5):41−42,57.
[3]	PANDEY P, SRIVASTAVA S, HARI N M. Comparison of FT-NIR and NIR for evaluation of phyisco-chemical properties of stored wheat grains[J]. Food Quality and Safety,2018,2(3):165−172. doi: 10.1093/fqsafe/fyy015
[4]	PASHA I, ANJUM F M, MORRIS C F. Grain hardness: a major determinant of wheat quality[J]. Food Science & Technology International,2010,16(6):511−522.
[5]	YANG L, SUN M, LIN W, et al. Effects of population structure on soil water consumption and biomass production in dryland wheat[J]. Chinese Journal of Ecology,2021,40(5):1356−1365.
[6]	KLEIJER G, LEVY L, SCHWAERZEI R, et al. Relationship between test weight and several quality parameters in wheat[J]. Revue Suisse Dagriculture,2007,39(6):305−309.
[7]	HELGERUD T, SEGTNAN V H, WOLD J P, et al. Near-infrared spectroscopy for rapid estimation of dry matter content in whole unpeeled potato tubers[J]. Journal of Food Research,2012,1(4):55−65. doi: 10.5539/jfr.v1n4p55
[8]	HAO L I, CAO X Y, SONG J M, et al. Effects of spikelet and grain positions on grain weight and protein content of different wheat varieties[J]. Acta Agronomica Sinica,2017,43(2):238−252. doi: 10.3724/SP.J.1006.2017.00238
[9]	ZHU M T, LONG Y, CHEN Y, et al. Fast determination of lipid and protein content in green coffee beans from different origins using NIR spectroscopy and chemometrics[J]. Journal of Food Composition and Analysis,2021(2):104055.
[10]	WOLD J P, O'FARRELL M, ANDERSEN P V, et al. Optimization of instrument design for in-line monitoring of dry matter content in single potatoes by NIR interaction spectroscopy[J]. Foods,2021,10(4):828. doi: 10.3390/foods10040828
[11]	HEMAN A, HSIEH C L. Measurement of moisture content for rough rice by visible and Near-Infrared (NIR) spectroscopy[J]. Engineering in Agriculture Environment & Food,2016,9(3):280−290.
[12]	FERREIRA D S, PALLONE J A, Poppi R J. Fourier transform near-infrared spectroscopy (FT-NIRS) application to estimate Brazilian soybean [Glycine max (L. ) Merril] composition[J]. Food Research International,2013,51(1):53−58. doi: 10.1016/j.foodres.2012.09.015
[13]	QIU G, ENLI L, LU H, et al. Single-Kernel FT-NIR spectroscopy for detecting supersweet corn (Zea mays L. Saccharata Sturt) seed viability with multivariate data analysis[J]. Sensors,2018,18(4):1010. doi: 10.3390/s18041010
[14]	KAMARANGA H S, SCOTT R, BEAN S R, et al. Moisture effects on robustness of sorghum grain protein near-infrared spectroscopy calibration[J]. Cereal Chemistry,2019,96(4):678−688. doi: 10.1002/cche.10164
[15]	ZHAO H, GUO B, WEI Y, et al. Near infrared reflectance spectroscopy for determination of the geographical origin of wheat[J]. Food Chemistry,2013,138(2-3):1902−1907. doi: 10.1016/j.foodchem.2012.11.037
[16]	LI X. Study on the influence of water content and grain size on the accuracy of fourier NIR prediction model for maize and wheat[D]. Sichuan Agricultural University, 2006.
[17]	SHI H, YU P. Comparison of grating-based near-infrared (NIR) and fourier transform mid-infrared (ATR-FT/MIR) spectroscopy based on spectral preprocessing and wavelength selection for the determination of crude protein and moisture content in wheat[J]. Food Control,2017,82(5):57−58.
[18]	ANDRÁS S, SZILVESZTER G. Analysis of wheat grain development using NIR spectroscopy[J]. Journal of Cereal Science,2012,56(1):31−38. doi: 10.1016/j.jcs.2012.04.011
[19]	JI Y M, SUN H. Establishment of Near-infrared spectrum analysis model for main quality indexes of wheat[J]. Food Research and Development,2017,38(21):142−145.
[20]	HE H J, WANG Y L, QIAO H, et al. Rapid and non-contact evaluation of water content in wheat by long-wave near-infrared spectra[J]. Journal of Hainan Normal University (Natural Science),2019,32(1):26−32. doi: 10.1080/01431161.2010.519003
[21]	ZHAI Y, CUI L, ZHOU X, et al. Estimation of nitrogen, phosphorus, and potassium contents in the leaves of different plants using laboratory-based visible and near-infrared reflectance spectroscopy: comparison of partial least-square regression and support vector machine regression methods[J]. International Journal for Remote Sensing,2013,34(7):2502−2518. doi: 10.1080/01431161.2012.746484
[22]	KOTILAINEN J K, FALOMO R. Near-infrared imaging of the host galaxies of intermediate redshift steep spectrum radio quasars[J]. Astronomy & Astrophysics,2000,364(1):70−82.
[23]	QI L U, CHEN C, PENG Z Q. Application of adaptive filter to noninvasive biochemical examination by near infrared spectroscopy[J]. Optics & Precision Engineering,2012,20(4):873−879.
[24]	CAO B, LI H, FAN M, et al. Determination of pesticides in a flour substrate by chemometric methods using terahertz spectroscopy[J]. Analytical Methods,2018,10(42):5097−5104. doi: 10.1039/C8AY01728J
[25]	WANG J, SMITS E, BOOM R M, et al. Arabinoxylans concentrates from wheat bran by electrostatic separation[J]. Journal of Food Engineering,2015,155(6):29−36.
[26]	SU P F, ZHANG P F, ZHANG W G, et al. Establishment of near infrared rapid analysis model for moisture of barley, wheat and pea[J]. Brewery Science and Technology,2021(3):31−34.
[27]	TIAN X, WANG Q, LI J, et al. Non-destructive prediction of soluble solids content of pear based on fruit surface feature classification and multivariate regression analysis[J]. Infrared Physics & Technology,2018,92(6):336−344.
[28]	BUONDONNO A, AMENTA P, VISCARRA-ROSSEL R A, et al. Prediction of soil properties with PLSR and vis-NIR spectroscopy: Application to mediterranean soils from southern italy[J]. Current Analytical Chemistry,2012,8(2):283−299. doi: 10.2174/157341112800392571
[29]	QIN T J, LIU D, CONG Y L, et al. Determination of moisture, fat, carbohydrate and protein content of flour by near infrared spectroscopy[J]. Science and Technology of Food Industry,2020,41(12):256−263.
[30]	DAI X, HANG S, WEN L, et al. On-line UV-NIR spectroscopy as a process analytical technology (PAT) tool for on-line and real-time monitoring of the extraction process of coptis rhizome[J]. Rsc Advances,2016,6(12):10078−10085. doi: 10.1039/C5RA23688F
[31]	CHENG J H, JIN H, LIU Z. Developing a NIR multispectral imaging for prediction and visualization of peanut protein content using variable selection algorithms[J]. Infrared Physics & Technology,2018,88:92−96.
[32]	BAO Y, KONG W, YONG H, et al. Quantitative analysis of total amino acid in barley leaves under herbicide stress using spectroscopic technology and chemometrics[J]. Sensors,2012,12(10):13393−13401. doi: 10.3390/s121013393
[33]	WANG H, HE H, MA H, et al. LW-NIR hyperspectral imaging for rapid prediction of TVC in chicken flesh[J]. International Journal of Agricultural and Biological Engineering,2019,12(3):180−186. doi: 10.25165/j.ijabe.20191203.4444
[34]	LESTANDER T A, LEARDI R, GELADI P. Selection of Near infrared wavelengths using genetic algorithms for the determination of seed moisture content[J]. Journal of Near Infrared Spectroscopy,2003,11(6):433−446. doi: 10.1255/jnirs.394
[35]	HE H J, WANG Y L, QIAO H, et al. NIR spectra method for rapid prediction of dry matter content in wheat grain[J]. Journal of Hainan Normal University (Natural Science),2019,32(1):33−38.

施引文献(8)

期刊类型引用(4)

1.	XUE Hang，XU Xiping，MENG Xiang. Variety classification and identification of maize seeds based on hyperspectral imaging method. Optoelectronics Letters. 2025(04): 234-241 . 必应学术
2.	贾文珅，吕浩林，张上，秦英栋，周巍. 利用便捷式可见-近红外光谱仪和机器学习分辨霉变小麦及霉变程度. 智慧农业(中英文). 2024(01): 89-100 . 百度学术
3.	杨龙涛，尚玮瑶，万子龙，杨海兴，张国斌. 化肥减量配施生物有机肥对露地西葫芦产量、品质和养分分配的影响. 甘肃农业大学学报. 2024(02): 64-73 . 百度学术
4.	周昊宇，朱倩莹，钟玉鸣，刘袆帆，谢曦，肖更生，马路凯，刘东杰，王琴. 基于线性回归分析法预测李果实干制后果干糖酸比. 食品安全质量检测学报. 2023(20): 200-208 . 百度学术