基于光谱技术的Bipls算法结合CARS算法的苹果可溶性固形物含量检测
|
摘要
可溶性固形物含量是判断苹果内部品质的重要参考属性之一。利用高光谱技术获取苹果感兴趣区域的反射光谱,以S-G平滑(Savitzky-Golay smoothing)和直接正交信号校正(Direct orthogonal signal correction, DOSC)算法对光谱数据进行梯度预处理后,用后向区间偏最小二乘法(Bipls)优选出3,5,6,7,8,9,13,14,15,16,17,18,19,20,21,23等16个子区间,共计177个波长。结合竞争自适应重加权采样算法(CARS)再作进一步筛选,提取出449.6,512.9,544.8,547.2,594.3,596.8,928.2 nm等7个特征波长,利用偏最小二乘算法(PLS)建立基于特征波长的可溶性固形物含量检测模型,所得模型评价为R_c=0.906 2,RMSEC为0.482 2,R_p=0.871 6,RMSEP为0.614 0。该算法模型预测性能同Bipls和Bipls-SPA模型相比更为优异,证明了Bipls结合CARS算法在提高苹果可溶性固体物含量检测精度方面的有效性。
Soluble solid content(SSC) is one of the important reference attributes for judging the internal quality of apples. The hyperspectral technique was used to obtain the reflectance spectrum of the region of interest of the apple, and using the Savitzky-Golay smoothing and direct orthogonal signal correction algorithms(DOSC) to perform gradient preprocessing on the spectral data.Backward interval partial least squares method(Bipls) prefers selecting 16 sub-intervals of 3, 5, 6, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19, 20, 21, 23 for a total of 177 wavelengths. Combined with the competitive adaptive reweighted sampling algorithm(CARS) for further screening, 7 characteristic wavelengths such as 449.6, 512.9, 544.8, 547.2, 594.3, 596.8, 928.2 nm were extracted. Partial least squares algorithm was used to develop SSC determination model based on characteristic wavelengths. The model was evaluated as R_c=0.906 2, RMSEC of 0.482 2, R_p=0.871 6 and RMSEP of 0.614 0. The performance of the model with Bipls and Bipls-SPA is more excellent, the effectiveness of Bipls combined with CARS algorithm in improving the detection accuracy of apple soluble solids content was proved.
Soluble solid content(SSC) is one of the important reference attributes for judging the internal quality of apples. The hyperspectral technique was used to obtain the reflectance spectrum of the region of interest of the apple, and using the Savitzky-Golay smoothing and direct orthogonal signal correction algorithms(DOSC) to perform gradient preprocessing on the spectral data.Backward interval partial least squares method(Bipls) prefers selecting 16 sub-intervals of 3, 5, 6, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19, 20, 21, 23 for a total of 177 wavelengths. Combined with the competitive adaptive reweighted sampling algorithm(CARS) for further screening, 7 characteristic wavelengths such as 449.6, 512.9, 544.8, 547.2, 594.3, 596.8, 928.2 nm were extracted. Partial least squares algorithm was used to develop SSC determination model based on characteristic wavelengths. The model was evaluated as R_c=0.906 2, RMSEC of 0.482 2, R_p=0.871 6 and RMSEP of 0.614 0. The performance of the model with Bipls and Bipls-SPA is more excellent, the effectiveness of Bipls combined with CARS algorithm in improving the detection accuracy of apple soluble solids content was proved.
引文
[1] 李江波,饶秀勤,应义斌. 农产品外部品质无损检测中高光谱成像技术的应用研究进展 [J]. 光谱学与光谱分析, 2011,31(8):2021-2026. LI J B,RAO X Q,YING Y B. Advance on application of hyperspectral imaging to nondestructive detection of agricultural products external quality [J]. Spectrosc. Spectr. Anal., 2011,31(8):2021-2026. (in Chinese)
[2] 姜微,房俊龙,王树文,等. CARS-SPA算法结合高光谱检测马铃薯还原糖含量 [J]. 东北农业大学学报, 2016,47(2):88-95. JIANG W,FANG J L,WANG S W,et al.. Using cars-spa algorithm combined with hyperspectral to determine reducing sugars content in potatoes [J]. J. Northeast Agric. Univ., 2016,47(2):88-95. (in Chinese).
[3] 洪涯,洪添胜,代芬,等. 连续投影算法在砂糖橘总酸无损检测中的应用 [J]. 农业工程学报, 2010,26(S2):380-384. HONG Y,HONG T S,DAI F,et al.. Successive projections algorithm for variable selection in nondestructive measurement of citrus total acidity [J]. Trans. CSAE, 2010,26(S2):380-384. (in Chinese)
[4] DONG J L,GUO W C,WANG Z W,et al.. Nondestructive determination of soluble solids content of ‘Fuji’ apples produced in different areas and bagged with different materials during ripening [J]. Food Anal. Methods, 2016,9(5):1087-1095.
[5] LI H D,LIANG Y Z,XU Q S,et al.. Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration [J]. Anal. Chim. Acta, 2009,648(1):77-84.
[6] 詹白勺,倪君辉,李军. 高光谱技术结合CARS算法的库尔勒香梨可溶性固形物定量测定 [J]. 光谱学与光谱分析, 2014,34(10):2752-2757. ZHAN B S,NI J H,LI J. hyperspectral technology combined with CARS algorithm to quantitatively determine the SSC in Korla fragrant pear [J]. Spectrosc. Spectr. Anal., 2014,34(10):2752-2757. (in Chinese)
[7] 张华秀,李晓宁,范伟,等. 近红外光谱结合CARS变量筛选方法用于液态奶中蛋白质与脂肪含量的测定 [J]. 分析测试学报, 2010,29(5):430-434. ZHANG H X,LI X N,FAN W,et al.. Determination of protein and fat in liquid milk by NIR combined with CARS variables screening method [J]. J. Instrum. Anal., 2010,29(5):430-434. (in Chinese)
[8] YUN Y H,LI H D,WOOD L R E,et al.. An efficient method of wavelength interval selection based on random frog for multivariate spectral calibration [J]. Spectrochim. Acta Part A, 2013,111:31-36.
[9] LI X L,SUN C J,LUO L B,et al.. Determination of tea polyphenols content by infrared spectroscopy coupled with iPLS and random frog techniques [J]. Comput. Electron. Agric., 2015,112:28-35.
[10] 张怡卓,涂文俊,李超,等. 基于BiPLS-SPA优选近红外光谱的木材基本密度预测——以柞木为例 [J]. 东北林业大学学报, 2016,44(10):79-83. ZHANG Y Z,TU W J,LI C,et al.. Xylosma racemosum basic density prediction with BiPLS-SPA and near infrared wavelength optimization [J]. J. Northeast Forestry Univ., 2016,44(10):79-83. (in Chinese)
[11] 褚小立. 化学计量学方法与分子光谱分析技术 [M]. 北京:化学工业出版社, 2011. CHU X L. Molecular Spectroscopy Analytical Technology Combined with Chemometrics and Its Applications [M]. Beijing:Chemical Industry Press, 2011. (in Chinese)
[12] 刘桂松,郭昊淞,潘涛,等. Vis-NIR光谱模式识别结合SG平滑用于转基因甘蔗育种筛查 [J]. 光谱学与光谱分析, 2014,34(10):2701-2706. LIU G S,GUO H S,PAN T,et al.. Vis-NIR spectroscopic pattern recognition combined with SG smoothing applied to breed screening of transgenic sugarcane [J]. Spectrosc. Spectr. Anal., 2014,34(10):2701-2706. (in Chinese)
[13] 褚小立,袁洪福,陆婉珍. 近红外分析中光谱预处理及波长选择方法进展与应用 [J]. 化学进展, 2004,16(4):528-542. CHU X L,YUAN H F,LU W Z. Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique [J]. Prog. Chem., 2004,16(4):528-542. (in Chinese)
[14] 史波林,庆兆珅,籍保平,等. 应用GA-DOSC算法消除果皮影响近红外漫反射光谱分析苹果硬度的研究 [J]. 光谱学与光谱分析, 2009,29(3):665-670. SHI B L,QING Z S,JI B P,et al.. Using GA-DOSC method to eliminate interference of peel with prediction of apple firmness based on near infrared diffuse reflection spectra [J]. Spectrosc. Spectr. Anal., 2009,29(3):665-670. (in Chinese)
[15] WESTERHUIS J A,DE JONG S,SMILDE A K. Direct orthogonal signal correction [J]. Chemom. Intell. Lab. Syst., 2001,56(1):13-25.
[2] 姜微,房俊龙,王树文,等. CARS-SPA算法结合高光谱检测马铃薯还原糖含量 [J]. 东北农业大学学报, 2016,47(2):88-95. JIANG W,FANG J L,WANG S W,et al.. Using cars-spa algorithm combined with hyperspectral to determine reducing sugars content in potatoes [J]. J. Northeast Agric. Univ., 2016,47(2):88-95. (in Chinese).
[3] 洪涯,洪添胜,代芬,等. 连续投影算法在砂糖橘总酸无损检测中的应用 [J]. 农业工程学报, 2010,26(S2):380-384. HONG Y,HONG T S,DAI F,et al.. Successive projections algorithm for variable selection in nondestructive measurement of citrus total acidity [J]. Trans. CSAE, 2010,26(S2):380-384. (in Chinese)
[4] DONG J L,GUO W C,WANG Z W,et al.. Nondestructive determination of soluble solids content of ‘Fuji’ apples produced in different areas and bagged with different materials during ripening [J]. Food Anal. Methods, 2016,9(5):1087-1095.
[5] LI H D,LIANG Y Z,XU Q S,et al.. Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration [J]. Anal. Chim. Acta, 2009,648(1):77-84.
[6] 詹白勺,倪君辉,李军. 高光谱技术结合CARS算法的库尔勒香梨可溶性固形物定量测定 [J]. 光谱学与光谱分析, 2014,34(10):2752-2757. ZHAN B S,NI J H,LI J. hyperspectral technology combined with CARS algorithm to quantitatively determine the SSC in Korla fragrant pear [J]. Spectrosc. Spectr. Anal., 2014,34(10):2752-2757. (in Chinese)
[7] 张华秀,李晓宁,范伟,等. 近红外光谱结合CARS变量筛选方法用于液态奶中蛋白质与脂肪含量的测定 [J]. 分析测试学报, 2010,29(5):430-434. ZHANG H X,LI X N,FAN W,et al.. Determination of protein and fat in liquid milk by NIR combined with CARS variables screening method [J]. J. Instrum. Anal., 2010,29(5):430-434. (in Chinese)
[8] YUN Y H,LI H D,WOOD L R E,et al.. An efficient method of wavelength interval selection based on random frog for multivariate spectral calibration [J]. Spectrochim. Acta Part A, 2013,111:31-36.
[9] LI X L,SUN C J,LUO L B,et al.. Determination of tea polyphenols content by infrared spectroscopy coupled with iPLS and random frog techniques [J]. Comput. Electron. Agric., 2015,112:28-35.
[10] 张怡卓,涂文俊,李超,等. 基于BiPLS-SPA优选近红外光谱的木材基本密度预测——以柞木为例 [J]. 东北林业大学学报, 2016,44(10):79-83. ZHANG Y Z,TU W J,LI C,et al.. Xylosma racemosum basic density prediction with BiPLS-SPA and near infrared wavelength optimization [J]. J. Northeast Forestry Univ., 2016,44(10):79-83. (in Chinese)
[11] 褚小立. 化学计量学方法与分子光谱分析技术 [M]. 北京:化学工业出版社, 2011. CHU X L. Molecular Spectroscopy Analytical Technology Combined with Chemometrics and Its Applications [M]. Beijing:Chemical Industry Press, 2011. (in Chinese)
[12] 刘桂松,郭昊淞,潘涛,等. Vis-NIR光谱模式识别结合SG平滑用于转基因甘蔗育种筛查 [J]. 光谱学与光谱分析, 2014,34(10):2701-2706. LIU G S,GUO H S,PAN T,et al.. Vis-NIR spectroscopic pattern recognition combined with SG smoothing applied to breed screening of transgenic sugarcane [J]. Spectrosc. Spectr. Anal., 2014,34(10):2701-2706. (in Chinese)
[13] 褚小立,袁洪福,陆婉珍. 近红外分析中光谱预处理及波长选择方法进展与应用 [J]. 化学进展, 2004,16(4):528-542. CHU X L,YUAN H F,LU W Z. Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique [J]. Prog. Chem., 2004,16(4):528-542. (in Chinese)
[14] 史波林,庆兆珅,籍保平,等. 应用GA-DOSC算法消除果皮影响近红外漫反射光谱分析苹果硬度的研究 [J]. 光谱学与光谱分析, 2009,29(3):665-670. SHI B L,QING Z S,JI B P,et al.. Using GA-DOSC method to eliminate interference of peel with prediction of apple firmness based on near infrared diffuse reflection spectra [J]. Spectrosc. Spectr. Anal., 2009,29(3):665-670. (in Chinese)
[15] WESTERHUIS J A,DE JONG S,SMILDE A K. Direct orthogonal signal correction [J]. Chemom. Intell. Lab. Syst., 2001,56(1):13-25.