|
|
|
|
|
|
Development of Multi-Cultivar Universal Model for Soluble Solid Content of Apple Online Using Near Infrared Spectroscopy |
LIU Yan-de, XU Hai, SUN Xu-dong, JIANG Xiao-gang, RAO Yu, ZHANG Yu |
School of Mechatronics & Vehicle Engineering, East China Jiaotong University, National and Local Joint Engineering Research Center of Fruit Intelligent Photoelectric Detection Technology and Equipment, Nanchang 330013, China |
|
|
Abstract Cultivar variability influences the near-infrared modeling and analysis of the internal quality of the fruit due to the different cell structure, composition and optical transmission characteristics of the fruit so that the original model can not predict the fruit quality parameters with high precision. The feasibility of a multi-cultivar model’s development for the online determination of the internal quality of apple including “Candy Heart”, “Red Fuji” and “Crystal Fuji” was investigated. Near infrared diffuse transmittance spectra of each cultivar were collected by the fruit sorting equipment under the condition of the interval time of 100 ms and motion speed of 5 s-1. The spectral curves of all the cultivars were similar where the prominent absorption peaks were near 650, 709 and 810 nm, and troughs were near 670, 750 and 830 nm, and their variations were mainly reflected in the spectral absorption intensity. The spectral pre-process methods including multiplicative scatter correction, Savitzky-Golay smoothing and normalization were employed to filter out the variations in signals caused by the cultivars. Partial least squares regression method was used to establish the common model for the soluble solid content where the calibration sets of the total samples were combined. Uninformative variable elimination was used to select the modeling variables whose number of effective variables selected was 155, and the performance of the UVE-PLS model resulted in greater coefficient of determination for prediction of 0.80, lower root mean square error of 0.61% and higher residual prediction deviation of 2.21. Successive projections algorithm was employed to select the variables in the wavelengths selected by UVE and the number of variables selected was 22. Multivariable linear regression was used to establish the simplified model, which resulted in coefficient of determination for prediction of 0.78 and root mean square error of prediction of 0.64%. The test sets of all the cultivars were used to access the performance of best universal model, which resulted in latent variables of 6~10, coefficient of determination for prediction of 0.77~0.79 and root mean square error of 0.45%~0.75%. The results highlighted the potential of dynamic on-line sorting instruments for the testing of internal qualities of apples. The prediction range of the single cultivar model was expanded, and the robustness of prediction model among different cultivars were improved by establishing the common model. Appropriate variable selection methods can decrease the number of model variables, reduce the complexity of the model and ultimately increase the model rate. The development of the universal model of different cultivars for predicting internal quality has a good potential application in wavelength-limited near infrared spectroscopy equipment.
|
Received: 2019-03-07
Accepted: 2019-06-26
|
|
|
[1] NIE Ji-yun,LI Zhi-xia,LI Hai-fei,et al(聂继云,李志霞,李海飞,等). Scientia Agricultura Sinica(中国农业科学),2012,45(14):2895.
[2] Yuan L,Cai J,Sun L,et al. Food Analytical Methods,2016,9(3):785.
[3] Daniela E,Alessia P,Peter R,et al. Molecules,2015,20(8):13603.
[4] Fan S,Guo Z,Zhang B,et al. Food Analytical Methods,2016,9(5):1333.
[5] Arendse E,Fawole O A,Magwaza L S,et al. Biosystems Engineering,2017,159:22.
[6] Escribano S,Biasi W V,Lerud R,et al. Postharvest Biology and Technology,2017,128:112.
[7] Jun S,Yating L,Xiaohong W,et al. Journal of Food Process Engineering,2018,41(8):e12884.
[8] Liu R,Qi S,Han D. Journal of Near Infrared Spectroscopy,2015,23(5):301.
[9] Wang J,Wang J,Chen Z,et al. Postharvest Biology and Technology,2017,129:143.
[10] GAO Zi-yi,FAN Xian-guang,YANG Hui-juan,et al(高滋艺,范献光,杨惠娟,等). Food Science(食品科学),2016,37(19):70.
[11] Chang C W,Laird D A,Mausbach M J,et al. Soil Science Society of America Journal,2001,65(2):480.
[12] Zude-Sasse M,Truppel I,Herold B. Postharvest Biology and Technology,2002,25(2):123.
[13] YAN Yan-lu(严衍禄). Basic and Application of Near Infrared Spectroscopy(近红外光谱分析基础与应用). Beijing:China Light Industry Press(北京:中国轻工业出版社),2005. 8.
[14] Yun Y H,Li H D,Deng B C,et al. TrAC Trends in Analytical Chemistry,2019,113:102.
[15] de Araújo Gomes A,Galvão R K H,de Araújo M C U,et al. Microchemical Journal,2013,110:202. |
[1] |
GAO Feng1, 2, XING Ya-ge3, 4, LUO Hua-ping1, 2, ZHANG Yuan-hua3, 4, GUO Ling3, 4*. Nondestructive Identification of Apricot Varieties Based on Visible/Near Infrared Spectroscopy and Chemometrics Methods[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 44-51. |
[2] |
LI Yu1, ZHANG Ke-can1, PENG Li-juan2*, ZHU Zheng-liang1, HE Liang1*. Simultaneous Detection of Glucose and Xylose in Tobacco by Using Partial Least Squares Assisted UV-Vis Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 103-110. |
[3] |
BAO Hao1, 2,ZHANG Yan1, 2*. Research on Spectral Feature Band Selection Model Based on Improved Harris Hawk Optimization Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 148-157. |
[4] |
HU Cai-ping1, HE Cheng-yu2, KONG Li-wei3, ZHU You-you3*, WU Bin4, ZHOU Hao-xiang3, SUN Jun2. Identification of Tea Based on Near-Infrared Spectra and Fuzzy Linear Discriminant QR Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3802-3805. |
[5] |
LIU Xin-peng1, SUN Xiang-hong2, QIN Yu-hua1*, ZHANG Min1, GONG Hui-li3. Research on t-SNE Similarity Measurement Method Based on Wasserstein Divergence[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3806-3812. |
[6] |
BAI Xue-bing1, 2, SONG Chang-ze1, ZHANG Qian-wei1, DAI Bin-xiu1, JIN Guo-jie1, 2, LIU Wen-zheng1, TAO Yong-sheng1, 2*. Rapid and Nndestructive Dagnosis Mthod for Posphate Dficiency in “Cabernet Sauvignon” Gape Laves by Vis/NIR Sectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3719-3725. |
[7] |
WANG Qi-biao1, HE Yu-kai1, LUO Yu-shi1, WANG Shu-jun1, XIE Bo2, DENG Chao2*, LIU Yong3, TUO Xian-guo3. Study on Analysis Method of Distiller's Grains Acidity Based on
Convolutional Neural Network and Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3726-3731. |
[8] |
LUO Li, WANG Jing-yi, XU Zhao-jun, NA Bin*. Geographic Origin Discrimination of Wood Using NIR Spectroscopy
Combined With Machine Learning Techniques[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3372-3379. |
[9] |
ZHANG Shu-fang1, LEI Lei2, LEI Shun-xin2, TAN Xue-cai1, LIU Shao-gang1, YAN Jun1*. Traceability of Geographical Origin of Jasmine Based on Near
Infrared Diffuse Reflectance Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3389-3395. |
[10] |
YANG Qun1, 2, LING Qi-han1, WEI Yong1, NING Qiang1, 2, KONG Fa-ming1, ZHOU Yi-fan1, 2, ZHANG Hai-lin1, WANG Jie1, 2*. Non-Destructive Monitoring Model of Functional Nitrogen Content in
Citrus Leaves Based on Visible-Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3396-3403. |
[11] |
HUANG Meng-qiang1, KUANG Wen-jian2, 3*, LIU Xiang1, HE Liang4. Quantitative Analysis of Cotton/Polyester/Wool Blended Fiber Content by Near-Infrared Spectroscopy Based on 1D-CNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3565-3570. |
[12] |
HUANG Zhao-di1, CHEN Zai-liang2, WANG Chen3, TIAN Peng2, ZHANG Hai-liang2, XIE Chao-yong2*, LIU Xue-mei4*. Comparing Different Multivariate Calibration Methods Analyses for Measurement of Soil Properties Using Visible and Short Wave-Near
Infrared Spectroscopy Combined With Machine Learning Algorithms[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3535-3540. |
[13] |
KANG Ming-yue1, 3, WANG Cheng1, SUN Hong-yan3, LI Zuo-lin2, LUO Bin1*. Research on Internal Quality Detection Method of Cherry Tomatoes Based on Improved WOA-LSSVM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3541-3550. |
[14] |
HUANG Hua1, LIU Ya2, KUERBANGULI·Dulikun1, ZENG Fan-lin1, MAYIRAN·Maimaiti1, AWAGULI·Maimaiti1, MAIDINUERHAN·Aizezi1, GUO Jun-xian3*. Ensemble Learning Model Incorporating Fractional Differential and
PIMP-RF Algorithm to Predict Soluble Solids Content of Apples
During Maturing Period[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3059-3066. |
[15] |
CHEN Jia-wei1, 2, ZHOU De-qiang1, 2*, CUI Chen-hao3, REN Zhi-jun1, ZUO Wen-juan1. Prediction Model of Farinograph Characteristics of Wheat Flour Based on Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3089-3097. |
|
|
|
|