太赫兹光谱结合机器学习算法快速测定冻干胡萝卜的水分含量

doi:10.3964/j.issn.1000-0593(2025)07-1924-08

Abstract
References
Related Citation (15)

Download: PDF (10761 KB)
Export: BibTeX | EndNote (RIS)

Abstract Moisture content (MC) is vital to freeze-dried carrots' quality and shelf life. However, traditional moisture measurement methods are time-consuming and inefficient. Therefore, this study aimed to develop a rapid, nondestructive detection method utilizing terahertz time-domain spectroscopy (THz-TDS) and machine learning (ML) technology to determine the moisture content of freeze-dried carrots. The time-domain spectral data for 140 samples with varying moisture content were collected. Based on the optical parameter extraction model, the' absorption coefficient spectrum and refractive index spectrum of these samples within the terahertz frequency band were obtained. To enhance the quality of the spectral data, the acquired spectra underwent preprocessing through moving average (MA) smoothing and Savitzky-Golay (SG) smoothing. Subsequently, three feature extraction algorithms: competitive adaptive reweighting sampling (CARS), successive projection algorithm (SPA), and uninformative variable elimination (UVE), were employed to filter out the spectral variables most closely related to water content from the original spectral data. Finally, three machine learning algorithms: partial least squares regression (PLSR), back propagation artificial neural networks (BPANN), and extreme gradient boosting (XGBoost) were utilized to construct quantitative prediction models. These models were then comprehensively evaluated using model evaluation indices to determine the optimal optical parameters and the most effective algorithm combination for detecting the moisture content of freeze-dried carrots. The results indicated that the absorption coefficient spectrum accurately and effectively captured the moisture information. Pretreatment effectively reduced spectral noise, and feature extraction identified the key variables related to moisture. BPANN exhibited the best quantitative prediction performance among the machine learning algorithms tested. Specifically, the SG-CARS-BPANN model, which was based on the absorption coefficient spectrum, demonstrated the strongest predictive capability (R²_C=0.971 2，RMSEC=0.007 3，R²_P=0.936 6，RMSEP=0.010 7). These findings demonstrated that the combination of THz-TDS and machine learning algorithms can realize rapid and nondestructive moisture detection in freeze-dried carrots, and the established method has the potential to monitor moisture content in freeze-dried fruits and vegetables in real time during drying and storage.

Key words：Terahertz time-domain spectroscopy; Freeze-dried fruits and vegetables; Chemometrics; Absorption coefficient; Nondestructive quantitative analysis

Received: 2024-12-17 Accepted: 2025-03-01

ZTFLH:

O657.3

Corresponding Authors: XIE Yun-fei E-mail: xieyunfei@jiangnan.edu.cn

Cite this article:

SUN Meng,CHENG Jun,DIAO Shu, et al. Rapid Determination of Moisture Content of Freeze-Dried Carrots by Terahertz Spectroscopy Combined With Machine Learning Algorithms[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(07): 1924-1931.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2025)07-1924-08 OR https://www.gpxygpfx.com/EN/Y2025/V45/I07/1924

[1] Keser D, Guclu G, Kelebek H, et al. Food and Bioproducts Processing, 2020, 119: 350.
[2] Crichton S, Shrestha L, Hurlbert A, et al. Drying Technology, 2018, 36(7): 804.
[3] Zhang Lihui, Zhang Min, Mujumdar A S. Food Reviews International, 2023, 39(3): 1733.
[4] Zambrano M V, Dutta B, Mercer D G, et al. Trends in Food Science & Technology, 2019, 88: 484.
[5] Gezimati M, Singh G. Optical and Quantum Electronics, 2023, 55(2): 151.
[6] Shen Yin, Zhao Chunjiang, Li Bin, et al. Analytical Methods, 2021, 13(36): 4120.
[7] Gong Zhiyuan, Deng Di, Sun Xudong, et al. Infrared Physics & Technology, 2022, 120: 103997.
[8] Helal S, Sarieddeen H, Dahrouj H, et al. IEEE Signal Processing Magazine, 2022, 39(5): 42.
[9] Sun Xudong, Xu Chao, Luo Chagen, et al. Food Quality and Safety, 2023, 7(2): 2399.
[10] Dorney T D, Baraniuk R G, Mittleman D M. Journal of the Optical Society of America A-Optics Image Science and Vision, 2001, 18(7): 1562.
[11] Duvillaret L, Garet F, Coutaz J L. IEEE Journal of Selected Topics in Quantum Electronics, 1996, 2(3): 739.
[12] Wang Junyi, Fu Dandan, Hu Zhigang, et al. Foods, 2024, 13(5): 783.
[13] Wang Haipeng, Chen Pu, Dai Jiawei, et al. Trends in Analytical Chemistry, 2022, 153: 116648.
[14] HU Jun, LÜ Hao-hao, QIAO Peng, et al(胡军, 吕豪豪, 乔鹏, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2024, 44(7): 1896.
[15] Hu Jun, Chen Rui, Xu Zhen, et al. Sensors, 2021, 21(9): 3238.
[16] Chen Yuanzhe, Chen Zhuoting, Yan Qian, et al. International Journal of Biological Macromolecules, 2024, 262: 130002.
[17] Hu Jun, Zhan Chaohui, Shi Hongyang, et al. Infrared Physics & Technology, 2023, 131: 104448.
[18] Tang Zhengmin, Miao Jianbo, Liu Quancheng, et al. Microchemical Journal, 2021, 169: 106635.
[19] Ouyang Qin, Rong Yanna, Wu Jiaqi, et al. Food Chemistry, 2023, 420: 136078.
[20] Wei Yunpeng, Yuan Minghua, Hu Huiqiang, et al. Journal of Food Composition and Analysis, 2024, 128: 106079.
[21] Chen Tao, Ma Lingjie, Tang Zongqing, et al. Journal of Food Science, 2022, 87(3): 1108.
[22] Jin Peilin, Fu Yifan, Niu Renzhong, et al. Foods, 2023, 12(14): 2756.
[23] Mao Yilin, Li He, Wang Yu, et al. Foods, 2022, 11(16): 2537.
[24] Zhao Songguang, Adade S Y S S, Wang Zhen, et al. Foof Chemistry, 2023, 423: 136208.