基于可见/近红外光谱技术的板栗产地识别

doi:10.13733/j.jcam.issn.20955553.2021.12.28

摘要/Abstract

摘要： 采用可见/近红外光谱分析技术对河北和安徽两个产地的板栗进行检测分级，获得板栗样品在600~1 100 nm波长区间的可见/近红外光谱，采用偏最小二乘判别分析（PLSDA）进行建模，比较不同预处理方法和波长范围对PLSDA模型精度的影响。结果显示，不同预处理方法对模型性能影响较大，一阶导数预处理在全波长范围所建PLSDA模型性能最优，校正集和验证集的决定系数分别为0.884和0.863，均方根误差分别为0.170和0.191。不同波长范围也会影响模型的预测和识别性能，在波长区间为750~1 000 nm的光谱所建立的PLSDA模型性能要高于全波长光谱所建立的模型性能，其中经过SavitzkyGolay平滑预处理后，模型性能的提高最为明显，且其与原始光谱在校正集和验证集的敏感性和特异性均达到最优，即识别率均可达到100%。因此，可见/近红外光谱分析技术能够对板栗产地进行鉴别。

关键词: 板栗, 产地, 可见/近红外光谱技术, 光谱预处理方法, 波长范围

Abstract: This paper focused on identifying the geographic origin of chestnut by using visible and nearinfrared (VIS/NIR) spectroscopy. The VIS/NIR spectra were obtained at the spectral range of 600-1 100 nm for chestnut samples. Partial least square discriminant analysis models were developed, and different spectral preprocessing methods were used and compared to evaluate the effect on mathematical models. Besides, different spectral ranges were also compared to determine the influence on the accuracy of the PLSDA model. The results showed that different spectral preprocessing methods could influence the PLSDA models. PLSDA model for the spectra based on 1st derivative test could provide optimal performance with the determination coefficients for calibration and validation sets of 0.884 and 0.863, RMSEC and RMSEP of 0.170 and 0.191, respectively. The spectral range also affected mathematical models. The performance for the PLSDA models over the spectral range of 750-1 000 nm overall was better, especially for the spectra based on SavitzkyGolay smoothing preprocessing method, which could provide noticeable improvement for model performance. The models for the original spectra and the spectra based on SavitzkyGolay smoothing preprocessing method in calibration and validation sets had optimal sensitivity and specificity, which suggested that the recognition rate for calibration and validation sets could reach 100%. Thus, visible and nearinfrared spectroscopy can recognize the geographic origin of chestnut.

Key words: geographic origin, visible and nearinfrared spectroscopy, spectral preprocessing methods, spectral range

中图分类号:

S24： TP391.4

杨雨图, 熊杰, 司万, 方会敏, 黄玉萍. 基于可见/近红外光谱技术的板栗产地识别[J]. 中国农机化学报, 2021, 42(12): 189-194.

Yang Yutu, Xiong Jie, Si Wan, Fang Huimin, Huang Yuping.. Detection of chestnut production place based on visible and nearinfrared spectroscopy[J]. Journal of Chinese Agricultural Mechanization, 2021, 42(12): 189-194.

参考文献

［１］　Massantini R, Moscetti R, Frangipane M T. Evaluating progress of chestnut quality: A review of recent developments ［J］. Trends in Food Science & Technology, 2021, 113: 1062.
［2］　李勇, 周文化. 板栗全粉对鲜湿面品质影响及主成分分析［J］. 食品科技, 2019, 44(8): 152-157.
Li Yong, Zhou Wenhua. Effect of chestnut powder on fresh noodles quality and principal component analysis ［J］. Food Science and Technology, 2019, 44(8): 152-157.
［3］　Gao H, Shi P. Progress of Chinese chestnut process technology and production model ［C］. Academic Conference on Horticulture Science and Technology, 2009.
［4］　曹小艳, 李志, 张卿, 等. 不同板栗品种(系)抗性淀粉综合评价［J］. 中国粮油学报, 2019, 34(7): 39-46.
Cao Xiaoyan, Li Zhi, Zhang Qing, et al. Comprehensive evaluation of resistant starch in different Chinese chestnut varieties ［J］. Journal of the Chinese Cereals and Oils Association, 2019, 34(7): 39-46.
［5］　徐阳, 龚榜初, 江锡兵, 等. 不同栗药模式中板栗产量与品质分析［J］. 江苏农业科学, 2019, 47(9): 189-193.
［6］　何勇, 李晓丽. 用近红外光谱鉴别杨梅品种的研究［J］. 红外与毫米波学报, 2006, 25(3): 192-194, 212.
He Yong, Li Xiaoli. Discriminating varieties of waxberry using near infrared spectra ［J］. Journal of Infrared and Millimeter Waves, 2006, 25(3): 192-194, 212.
［7］　李晓丽, 唐月明, 何勇, 等. 基于可见/近红外光谱的水稻品种快速鉴别研究［J］. 光谱学与光谱分析, 2008, 28(3): 578-581.
Li Xiaoli, Tang Yueming, He Yong,et al. Discrimination of varieties of paddy based on Vis/NIR spectroscopy combined with chemometrics ［J］. Spectroscopy and Spectral Analysis, 2008, 28(3): 578-581.
［8］　陈建, 陈晓, 李伟, 等. 基于近红外光谱技术和人工神经网络的玉米品种鉴别方法研究［J］. 光谱学与光谱分析, 2008, 28(8): 1806-1809.
Chen Jian, Chen Xiao, Li Wei,et al. Study on discrimination of corn seed based on nearinfrared spectra and artificial neural network model ［J］. Spectroscopy and Spectral Analysis, 2008, 28(8): 1806-1809.
［9］　孙旭东, 郝勇, 张光伟. 近红外光谱结合最小二乘支持向量机的脐橙叶片含水率无损检测［J］. 中国农机化学报, 2015, 36(2): 150-153, 168.
Sun Xudong, Hao Yong, Zhang Guangwei. Nondestructive detection of water content for navel oranges leaves using nearinfrared spectroscopy combined with least squares support vector machine ［J］. Journal of Chinese Agricultural Mechanization, 2015, 36(2): 150-153, 168.
［10］　孙旭东, 龚志远, 蔡丽君, 等. 水果糖度近红外光谱在线检测装置［J］. 中国农机化, 2012(2): 116-120.
Sun Xudong, Gong Zhiwei, Cai Lijun, et al. Equipment of online detection for sugar content in fruit based on near infrared spectroscopy ［J］. Chinese Agricultural Mechanization, 2012(2): 116-120.
［11］　王晓明, 章海亮, 罗微, 等. 近红外光谱检测梨果硬度研究［J］. 中国农机化学报, 2015, 36(6): 120-123, 142.
Wang Xiaoming, Zhang Hailiang, Luo Wei, et al. Study on pear firmness detection by using near infrared reflectance spectroscopy based on CARS ［J］. Journal of Chinese Agricultural Mechanization, 2015, 36(6): 120-123, 142.
［12］　Cassani Lucia, Santos Mauricio, Gerbino Esteban, et al. A combined approach of infrared spectroscopy and multivariate analysis for the simultaneous determination of sugars and fructans in strawberry juices during storage ［J］. Journal of Food Science, 2018, 83(2): 631-638.
［13］　李兴鹏, 姜洪喆, 蒋雪松, 等. 木本粮油林果品质的近红外光谱及成像无损检测研究进展［J/OL］. 食品与发酵工业: 1-8［2021-12-10］. https://doi.org/10.13995/j.cnki.11-1802/ts.027746.
［14］　Jiang Hongzhe, Ru Yu, Chen Qin, et al. Nearinfrared hyperspectral imaging for detection and visualization of offal adulteration in ground pork ［J］. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2021, 249: 119307.
［15］　Jiang Hongzhe, Jiang Xuesong, Ru Yu, et al. Sweetness detection and grading of peaches and nectarines by combining shortand longwave fouriertransform nearinfrared spectroscopy ［J］. Analytical Letters, 2020(4): 1-20.
［16］　刘雪梅. 近红外漫反射光谱检测土壤有机质和速效N的研究［J］. 中国农机化学报, 2013, 34(2): 202-206.
Liu Xuemei. Near infrared diffuse reflectance spectra detection of soil organic matter and available N ［J］. Journal of Chinese Agricultural Mechanization, 2013, 34(2): 202-206.
［17］　刘燕德, 姜小刚, 熊松盛, 等. 基于CARS算法的脐橙果园土壤有机质近红外检测［J］. 中国农机化学报, 2016, 37(2): 240-244.
Liu Yande, Jiang Xiaogang, Xiong Songsheng, et al. Using CARS to predict the content of soil organic matter based on VisNIR spectra ［J］. Journal of Chinese Agricultural Mechanization, 2016, 37(2): 240-244.
［18］　刘燕德, 熊松盛, 刘德力, 等. 基于VisNIR光谱的果园土壤有机质便携式检测仪研究［J］. 中国农机化学报, 2015, 36(4): 263-267.
Liu Yande, Xiong Songsheng, Liu Deli, et al. Research on portable detecting instrument of soil organic matter based on VisNIR spectra ［J］. Journal of Chinese Agricultural Mechanization, 2015, 36(4): 263-267.
［19］　Chang C W, Laird, David A, et al. Nearinfrared reflectance spectroscopyprincipal components regression analyses of soil properties ［J］. Soil Science Society of America Journal, 2001, 65(2): 480-490.
［20］　Dunn B W, Batten G D, Beecher H G, et al. The potential of nearinfrared reflectance spectroscopy for soil analysis—A case study from the Riverine Plain of southeastern Australia ［J］. Australian Journal of Experimental Agriculture, 2002, 42(5): 607-614.
［21］　汤彦丰, 张卓勇, 范国强, 等. 基于大黄的红外光谱的人工神经网络鉴别研究［J］. 光谱学与光谱分析, 2005, 25(5): 715-718.
Tang Yanfeng, Zhang Zhuoyong, Fan Guoqiang, et al. Identification of official rhubarb samples based on IR spectra and neural networks ［J］. Spectroscopy and Spectral Analysis, 2005, 25(5): 715-718.
［22］　徐永群, 孙素琴, 冯学峰, 等. 黄芩产区红外指纹图谱和聚类分析法的快速鉴别研究［J］. 光谱学与光谱分析, 2003, 23(3): 502-505.
Xu Yongqun, Sun Suqin, Feng Xuefeng, et al. Quick indentification of scullcaps in different geographical origins using clustering analysis method and infrared fingerprint spectra ［J］. Spectroscopy and Spectral Analysis, 2003, 23(3): 502-505.
［23］　徐永群, 黄昊, 周群, 等. 红外指纹图谱和聚类分析法在赤芍产域分类鉴别中的应用［J］. 分析化学, 2003, 31(1): 5-9.
Xu Yongqun, Huang Hao, Zhou Qun, et al. The application of fingerprint infrared spectra and clustering analysis in the discrimination of geographical origin of paeonia lactiflora pall ［J］. Chinese Journal of Analytical Chemistry, 2003, 31(1): 5-9.
［24］　丁念亚, 黎薇, 冯昕韡, 等. 近红外漫反射光谱在中药分类及真伪鉴别中的应用［J］. 计算机与应用化学, 2008, 25(4): 499-502.
Ding Nianya, Li Wei, Feng Xinwei, et al. Classification and identification of Chinese traditional medicines with NIR diffuse reflection ［J］. Computers and Applied Chemistry, 2008, 25(4): 499-502.
［25］　赵龙莲, 张录达, 李军会, 等. 小波包熵和Fisher判别在近红外光谱法鉴别中药大黄真伪中的应用［J］. 光谱学与光谱分析, 2008, 28(4): 817-820.
Zhao Longlian, Zhang Luda, Li Junhui, et al. Application of wavelet packet entropy and fisher classifier to the identification of medicinal rhubarbs with nearinfrared spectrum ［J］. Spectroscopy and Spectral Analysis, 2008, 28(4): 817-820.