Comparative analysis of spectra and modeling of different cross-diameter orah mandarin based on spectral transformation algorithm

Authors

HU Feng, School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha, Hunan 410004, China
GONG Zhongliang, School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha, Hunan 410004, ChinaFollow
WEN Tao, School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha, Hunan 410004, China
DAI Xingyong, School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha, Hunan 410004, China
TANG Ziye, School of Mechanical and Electrical Engineering, Central South University of Forestry and Technology, Changsha, Hunan 410004, China

Corresponding Author(s)

龚中良（1965—），男，中南林业科技大学教授，博士。E-mail: gzlaa@163.com

Abstract

Objective: To reduce the influence of transverse diameter of Mandarin orange on the prediction of sugar content. Methods: 132 citrus were divided into three groups according to transverse diameter: small （65～70 mm）, medium （70～75 mm） and large （75～80 mm）. After collecting the transverse diameter spectrum of all citrus, the spectrum information and transverse diameter information of citrus were synthesized by spectral transformation algorithm, and the spectrum of different sizes of citrus was converted to the same transverse diameter datum. The pre-correction and post-correction spectra were respectively preprocessed, divided by target symbiotic distance algorithm （SPXY）, screened by competitive adaptive weight sampling （CARS） and selected by partial least squares regression （PLS） to establish the sugar degree model before and after correction. Results: The prediction set determination coefficient （R²_P） was increased from 0.790 to 0.821, and the prediction set root mean square error （RMSEP） was decreased from 0.489 to 0.443. The middle fruit spectrum was modified, R²_P increased from 0.801 to 0.845, RMSEP decreased from 0.460 to 0.422. R²_P increased from 0.820 to 0.863 and RMSEP decreased from 0.431 to 0.393. Conclusion: The spectral correction algorithm can reduce the spectral difference caused by the transverse diameter and improve the prediction accuracy of the model.

Publication Date

7-22-2024

First Page

113

Last Page

121,218

DOI

10.13652/j.spjx.1003.5788.2023.80688

Recommended Citation

Feng, HU; Zhongliang, GONG; Tao, WEN; Xingyong, DAI; and Ziye, TANG (2024) "Comparative analysis of spectra and modeling of different cross-diameter orah mandarin based on spectral transformation algorithm," Food and Machinery: Vol. 40: Iss. 5, Article 17.
DOI: 10.13652/j.spjx.1003.5788.2023.80688
Available at: https://www.ifoodmm.cn/journal/vol40/iss5/17

References

[1] 余怀鑫. 基于可见—近红外光谱技术的柑橘品质无损检测研究[D]. 武汉: 华中农业大学, 2021: 9. YU H X. Research on non-destructive testing of citrus quality based on visible-near-infrared spectroscopy[D]. Wuhan: Huazhong Agricultural University, 2021: 9.
[2] MILLER W M, ZUDE M. NIR-based sensing to identify soluble solids content of Florida citrus[J]. Applied Engineering in Agriculture, 2004, 20: 321-327.
[3] HERREMANS E, VERBOVEN P, DEFRAEYE T, et al. X-ray CT for quantitative food microstructure engineering: The apple case[J]. Nuclear Instruments and Methods in Physics Research Section B-Beam Interactions with Materials and Atoms, 2014, 324: 88-94.
[4] MC CLARK V A, FRASER D G, JORDAN R B, et al. Internal quality assessment of mandarin fruit by vis/NIR spectroscopy[J]. Journal of Near Infrared Spectroscopy, 2003, 11: 323-332.
[5] 杜冉. 基于近红外透射光谱技术的苹果内部品质在线检测的研究[D]. 淄博: 山东理工大学, 2008: 10. DU R. Research on on-line detection of internal quality of apple based on near-infrared transmission spectroscopy[D]. Zibo: Shandong University of Technology, 2008: 10.
[6] 曹松涛. 样品相关因素对梨糖度可见/近红外光谱检测影响的研究[D]. 杭州: 浙江大学, 2017: 12. CAO S T. Study on the influence of sample correlation factors on visible/near-infrared spectroscopy detection of pear sugar content[D]. Hangzhou: Zhejiang University, 2017: 12.
[7] 田世杰. 基于透射光谱的苹果霉心病判别影响因素及其修正方法研究[D]. 咸阳: 西北农林科技大学, 2020: 42. TIAN S J. Study on the identification factors and correction method of apple mold heart disease based on transmission spectrum[D]. Xianyang: Northwest A & F University, 2020: 42.
[8] 雷雨, 何东健, 周兆永, 等. 苹果霉心病可见/近红外透射能量光谱识别方法[J]. 农业机械学报, 2016, 47（4）: 193-200. LEI Y, HE D J, ZHOU Z Y, et al. Identification method of visible/near-infrared transmission energy spectroscopy for apple mold heart disease[J]. Transactions of the Chinese Society for Agricultural Machinery, 2016, 47（4）: 193-200.
[9] 马敏娟, 李磊, 赵娟, 等. 融合不同成熟度的苹果可溶性固形物预测模型研究[J]. 食品安全质量检测学报, 2018, 9（11）: 290-296. MA M J, LI L, ZHAO J, et al. Study on soluble solids prediction model of apple with different maturity levels[J]. Journal of Food Safety and Quality Inspection, 2018, 9（11）: 290-296.
[10] 吴辰星. 融合多源信息的苹果霉心病在线检测方法研究[D]. 咸阳: 西北农林科技大学, 2017: 15. WU C X. Research on online detection method of apple mold heart disease with multi-source information[D]. Xianyang: Northwest A & F University, 2017: 15.
[11] 河野澄夫. 近赤外分光法による果実糖度の測定[J]. 食粮その科学と技術, 2005, 43（3）: 69-86. HEYE C F. Determination of fruit sugar content by near-infrared spectroscopy[J]. Food and Science and Technology, 2005, 43（3）: 69-86.
[12] 常汉. 水心病苹果水心程度与可溶性固形物含量在线无损检测方法与分级装备研究[D]. 杭州: 浙江大学, 2021: 22. CHANG H. Research on online nondestructive testing method and grading equipment for water-centered degree and soluble solids content of apple with water heart disease[D]. Hangzhou: Zhejiang University, 2021: 22.
[13] WORKMAN J R J, WEYER L. Practical guide to interpretive near-infrared spectroscopy[M]. Boca Raton: CRC Press, 2007: 27.