基于可见-近红外光谱和化学计量学的带壳香榧坏籽快速识别

doi:10.3964/j.issn.1000-0593(2024)09-2675-08

Abstract
References
Related Citation (15)

Download: PDF (6537 KB)
Export: BibTeX | EndNote (RIS)

Abstract Inedible shelled Torreya grandis bad seeds will be produced during post-ripening treatment and frying, which cannot be accurately recognized and rejected manually without destroying the shells, affecting the overall quality of shelled Torreya grandis seeds. This study used two near-infrared spectrometers to collect spectral data of shelled normal and bad Torreya grandis seeds and eight spectral pre-processing methods was studied and compared. Then, a single wavelength selection method (Uninformative Variables Elimination, Competitive Adaptive Reweighted Sampling, Successive Projections Algorithm, and Subwindow Permutation Analysis) and a joint wavelength selection method were adopted to select characteristic wavelength, and Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) methods were applied to establish the identification model of Torreya grandis bad seeds. Also, the model's performance was compared to determine the better wavelength selection method for different spectrometers. The results show that for spectrometer 1, preprocessing can not improve the model performance effectively. The Successive Projections Algorithm is the optimal wavelength selection method. The sensitivity, specificity, and accuracy of the LDA and SVM models in the prediction set are 97.10%, 95.00%, 96.00% and 97.10%, 97.50%, and 97.30%, respectively, superior to the full-wavelength model. The number of modeled wavelength variables was reduced from 661 to 9, only 1.36% of the original number of wavelength variables. For spectrometer 2, baseline correction is the optimal preprocessing method, and Subwindow Permutation Analysis is the optimal feature wavelength selection method. The sensitivity, specificity, and accuracy of the prediction sets of the developed LDA and SVM models are 100.00%, 92.50%, 96.00% and 100.00%, 95.00%, and 97.30%, which are consistent with full-band model performance. The number of modeled wavelength variables was reduced from 155 to 55, which is 35.48% of the original number of wavelength variables. It can be seen that near-infrared spectroscopy can better identify the shelled bad Torreya grandis seeds, and the appropriate wavelength selection method can effectively screen the characteristic wavelengths, simplify the model, and improve the accuracy and stability of the model. It is also found that the wavelength range of 1 000~1 300 nm is related to the starch, fat, and protein content of Torreya grandis seeds, making it more suitable for identifying bad Torreya grandis seeds. This study provides a reference for the rapid and nondestructive identification of shelled Torreya grandis bad seeds.

Key words：Shelled Torreya grandis seeds;Visible-near infrared spectroscopy;Bad seeds;Characteristic wavelength screening

Received: 2023-08-29 Accepted: 2024-03-25

ZTFLH:

TS255.6

Corresponding Authors: SUN Tong E-mail: suntong980@163.com

Cite this article:

WENG Ding-kang,FAN Zheng-xin,KONG Ling-fei, et al. Rapid Identification of Shelled Bad Torreya Grandis Seeds Based on Visible-Near Infrared Spectroscopy and Chemometrics[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(09): 2675-2682.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2024)09-2675-08 OR https://www.gpxygpfx.com/EN/Y2024/V44/I09/2675

[1] HE Ci-ying, LOU He-qiang, WU Jia-sheng(何慈颖, 娄和强, 吴家胜). Journal of Zhejiang A&F University(浙江农林大学学报), 2023, 40(4): 714.
[2] LI Zhe-bin(李哲斌). Chinese Journal of Oil Crop Sciences(中国油料作物学报), 2022, 44: 1166.
[3] WU Cheng-zhao, WANG Yi-tao, HU dong, et al(吴成招, 王一韬, 胡栋, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2023, 43(3): 685.
[4] SUN Tong, LI Han-lin, KONG Ling-fei, et al(孙通, 李翰林, 孔令飞, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2023, 39(24): 298.
[5] YU Chu-ze, WENG Ding-kang, CAO Shuo-sen, et al(俞储泽, 翁定康, 曹烁森, 等). Journal of Chinese Institute of Food Science and Technology(中国食品学报), 2024, 24(2): 292.
[6] An M, Cao C, Wang S, et al. Journal of Food Composition and Analysis, 2023, 121: 105407.
[7] Rovira G, Miaw C S W, Martins M L C, et al. Microchemical Journal, 2022, 181: 107816.
[8] Sammarco G, Dall'asta C, Suman M. Vibrational Spectroscopy, 2023, 126: 103531.
[9] Miaw C S W, Martins M L C, Sena M M, et al. Food Analytical Methods, 2022, 15(4): 1074.
[10] Guan S, Shang Y, Zhao C, Sustainability, 2023, 15(10)：7757.
[11] Xiang J, Huang Y, Guan S, et al. Sustainability, 2023, 15(16)：12423.
[12] DOU Lin-lin, ZHANG Yan, LIU Hai-bin, et al(窦琳琳, 张淹, 刘海滨, 等). Chinese Traditional and Herbal Drugs(中草药), 2023, 54(9): 2925.
[13] HU Yun-chao, WANG Hong-hong, XIONG Zhi-xin, et al(胡云超, 王红鸿, 熊智新, 等). Journal of Forestry Engineering(林业工程学报), 2023, 8(2): 101.
[14] LIU Qiang, GONG Zhong-liang，LI Da-peng, et al(刘强, 龚中良, 李大鹏, 等). China Oils and Fats(中国油脂), 2024, 49(3): 132.
[15] LUO Qi, TUO Xian-guo, ZHANG Gui-yu, et al(罗琪, 庹先国, 张贵宇, 等). Modern Food Science and Technology(现代食品科技), 2023, 39(4): 311.
[16] SUN Tong, WU Yi-qing, LI Xiao-zhen, et al(孙通, 吴宜青, 李晓珍, 等). Acta Optica Sinica(光学学报), 2015, 35(6): 1.
[17] XIONG Jian-fang, LIU Yao, QIAO Fu, et al(熊建芳, 刘瑶, 乔付, 等). Transducer and Microsystem Technologies(传感器与微系统), 2023, 42(5): 25.
[18] ZHAO Chun-lin, YIN Zhi-peng, ZHANG Wen-bin, et al(赵春林, 尹治棚, 张文斌, 等). Food Science and Technology(食品科技), 2023, 48(11): 253.
[19] CHEN Yan-li, SUN Ming, CHEN Cheng, et al(陈燕丽, 孙明, 陈诚, 等). Science Technology and Engineering(科学技术与工程), 2023, 23(34): 14682.
[20] LI Zheng, WANG Mei, HUANG He, et al(李征, 王媚, 黄河, 等). China Brewing(中国酿造), 2023, 42(3): 222.
[21] WANG Yan-na, MENG Xue-cheng, ZHAO Di, et al(王艳娜, 孟学成, 赵荻, 等). Journal of Nanjing Forestry University (Natural Sciences Edition)[南京林业大学学报(自然科学版)], 2022, 64(4): 169.