基于多模型决策融合的苹果产地判别及糖度含量预测

doi:10.3964/j.issn.1000-0593(2024)10-2812-07

Abstract
References
Related Citation (15)

Download: PDF (7328 KB)
Export: BibTeX | EndNote (RIS)

Abstract Traceability of apple origin and prediction of apple SSC is of great practical significance, and the purpose of origin discrimination and SSC prediction is achieved by modeling. To overcome the limitations of a single model, the overall prediction performance is improved by combining the prediction results of multiple models. Near-infrared spectroscopy (NIRS) detection technology combined with a multi-model decision fusion strategy is utilized for traceability identification of apple origin and prediction of apple SSC to verify the feasibility of the theoretical method.The spectra of apple samples were collected using a handheld near-infrared detector, and apple origin discrimination models were established using the sample spectra in combination with the random forest (RF) method, the partial least squares discriminant analysis (PLS-DA) method, and the support vector machine (SVM) method. The predictions from the three discrimination models are then used in a voting system decision fusion method to generate new discriminant results. Actual values of SSC were collected for all apple samples, and SSC prediction models were developed using the sample spectra and actual values of SSC combined with the random forest (RF) method, the partial least squares regression (PLSR) method, and the support vector regression (SVR) method. Using the outputs of the three regression models, the new SSC prediction is output through the weighting method decision fusion strategy. When the voting decision-making method was not used, the discrimination modeling using the RF method was the most effective among the three qualitative modeling methods, with a prediction accuracy of 88.71%. The worst prediction was made using the SVM method, with a prediction accuracy of 77.43%. After using the voting decision method, the accuracy of apple origin identification reached 93.42%, and its prediction precision and recall also reached a double high, both above 85%. All three quantitative modeling methods gave good results in predicting apple SSC without using the weighted decision fusion method. All three methods predicted coefficients of determination around 0.87 and root mean square errors of prediction (RMSEP) around 0.78. The prediction of the SSC level was improved after using the weighted decision fusion method. The prediction coefficient of determination was 0.91, and the RMSEP was 0.66. The feasibility of the proposed method was confirmed by using the multi-model decision fusion method in the identification of apple origin and the prediction of apple SSC to improve the accuracy of apple origin discrimination and the precision of the prediction of apple SSC. Meanwhile, the handheld NIR detector combined with the multi-model decision fusion method provides a new high-precision prediction approach for on-site non-destructive testing analysis.

Key words：Near-infrared spectroscopy; Multi-model; Decision fusion; Origin discrimination; Soluble solids content prediction

Received: 2023-07-16 Accepted: 2023-10-11

ZTFLH:

O657.3

Corresponding Authors: LIU Yan-de E-mail: jxliuyd@163.com

Cite this article:

JIANG Xiao-gang,HE Cong,JIANG Nan, et al. Discrimination of Apple Origin and Prediction of SSC Based on Multi-Model Decision Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(10): 2812-2818.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2024)10-2812-07 OR https://www.gpxygpfx.com/EN/Y2024/V44/I10/2812

[1] Pissard A, Marques E, Dardenne P, et al. Postharvest Biology and Technology, 2021, 172: 111375.
[2] Ma Te, Xia Yu, Inagaki Tetsuya, et al. Postharvest Biology and Technology, 2021, 173: 111417.
[3] LEI Ying, LIU Cui-ling, ZHOU Zi-yan(雷鹰, 刘翠玲, 周子彦). Journal of Food Science and Technology(食品科学技术学报), 2018, 36(6): 95.
[4] ZHANG Pei, WANG Yin-hong, JIANG Jing, et al(张珮, 王银红, 江靖，等). Food Science and Technology(食品科技), 2020, 45(5): 287.
[5] MA Yong-jie, GUO Jun-xian, GUO Zhi-ming, et al(马永杰, 郭俊先, 郭志明，等). Modern Food Science and Technology(现代食品科技), 2020, 36(6): 303.
[6] Caihong L, Lingling L, Yuan W, et al. Journal of Spectroscopy, 2018, 1: 6935179.
[7] ZHANG Li-xin, YANG Cui-fang, CHEN Jie, et al(张立欣, 杨翠芳, 陈杰，等). Journal of Tarim University(塔里木大学学报), 2021, 33(4): 78.
[8] MENG Qing-long, SHANG Jing, HUANG Ren-shuai, et al(孟庆龙, 尚静, 黄人帅，等). Food and Fermentation Industry(食品与发酵工业), 2020, 46(19): 205.
[9] Bian X, Diwu P, Liu Y, et al. Journal of Chemometrics, 2018, 32(11): e2940.
[10] JIA Li-hong, ZHANG Guo-hong, WANG Yi, et al(贾利红, 张国宏, 王毅，等). Analytical Instrument(分析仪器), 2022，(5): 13.
[11] ZHANG Chen, ZHU Yu-jie, FENG Guo-hong(张晨, 朱玉杰, 冯国红). Food and Fermentation Industry(食品与发酵工业), 2023, 49(18): 306.
[12] HUANG Hua, NAN Meng-di, LI Zheng-hao, et al(黄华, 南梦迪, 李政浩，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2022, 42(10): 3249.
[13] Cong Liu, Yang Simon X, Deng Lie. Journal of Food Engineering, 2015, 161: 16.
[14] Gilles Rabatel, Federico Marini, Beata Walczak, et al. Journal of Chemometrics, 2020, 34(2): 3164-1.
[15] Roberto Kawakami Harrop Galvão, Araujo Mario Cesar Ugulino, Gledson Emídio José, et al. Talanta, 2005, 67(4): 736.