Nondestructive Determination of TSS Content in Postharvest Mulberry Fruits Using Hyperspectral Imaging and Deep Learning
WANG Zi-xuan1, YANG Liang2, 3, 4*, HUANG Ling-xia2, HE Yong4, ZHAO Li-hua3, ZHAN Peng-fei3
1. Business School, Hohai University, Nanjing 210024, China
2. Key Laboratory of Silkworm and Bee Resource Utilization and Innovation of Zhejiang Province，Hangzhou 310058, China
3. Institute of Sericulture, Huzhou Academy of Agricultural Sciences, Huzhou 313002, China
4. Key Laboratory of Spectroscopy Sensing, Ministry of Agriculture and Rural Affairs, Hangzhou 310058, China
Abstract：Originating in China, mulberry is one of the fruits of the homology of medicine and food and has a long history. However, the industrialization of mulberry fruit has been limited by its characteristics of short maturity period and the tendency for thin skin to decay. Total soluble solid (TSS) is an important component of determining the mulberry flavor and qualityandis one of the most basic quality characteristics for its postharvest-commercialization. This study aims to optimize a prediction model for monitoring the TSS content in postharvest mulberry fruits using near-infrared hyperspectral imaging and deep learning methods and to evaluate the impact of common postharvest storage temperature on the quantitative models, thus providing support for rapid quality assessment of mulberry fruits. Mulberry fruits with consistent commercial maturity were selected for storage at room temperature (25 ℃) and low temperature (4 ℃). Samples from different storage stages were selected for spectral data collection and TSS content determination until mulberry fruits became unfit for consumption. Based on the spatial information provided by the corrected hyperspectral images, regions of interest were extracted to obtain representative spectra without background accurately. Then, standard normal variate (SNV), multiplicative scatter correction (MSC), and Savizkg-Golag (SG) smoothing were used for spectra preprocessing to improve the spectral signal-to-noise ratio. Prediction models for TSS content measurement in postharvest mulberry fruits were established using deep learning. For mulberry samples stored at room temperature and low temperature, the optimal CNN models obtained the residual prediction deviation values of 5.828 and 5.429, with the root mean square error of prediction (RMSEP) values of 1.082 and 1.099°Brix, respectively, indicating that the prediction performance of the CNN model was degraded due to the low-temperature storage. The classical machine learning methods of partial least squares (PLS) and least square support vector machine (LS-SVM) were used to establish models for TSS prediction further to verify the effectiveness of the constructed CNN models. Results showed that the nonlinear LS-SVM model was more suitable for predicting TSS content in mulberry fruits than the linear PLS model. For mulberry fruits stored at two different temperatures, the optimal LS-SVM models achieved RPD values of 4.221 and 4.423 for TSS prediction, respectively, indicating that the CNN performed better than the classical machine learning methods. In conclusion, hyperspectral imaging combined with deep learning CNN has excellent potential in predicting TSS content inpostharvest mulberry fruits, which provides technical support for rapid assessment of mulberry quality.
Key words：Mulberry fruit; Postharvest; Total soluble solid; Hyperspectral imaging; Deep learning; Convolutional neural network
王子轩，杨 良，黄凌霞，何 勇，赵丽华，占鹏飞. 高光谱结合深度学习的桑椹采后TSS含量无损检测[J]. 光谱学与光谱分析, 2024, 44(06): 1724-1730.
WANG Zi-xuan, YANG Liang, HUANG Ling-xia, HE Yong, ZHAO Li-hua, ZHAN Peng-fei. Nondestructive Determination of TSS Content in Postharvest Mulberry Fruits Using Hyperspectral Imaging and Deep Learning. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(06): 1724-1730.
[1] Yuan Q X, Zhao L Y. Journal of Agricultural and Food Chemistry, 2017, 65(48): 10383.
[2] He X R, Fang J C, Ruan Y L, et al. Food Chemistry, 2018, 245: 899.
[3] Wen P, Hu T G, Linhardt R J, et al. Trends in Food Science & Technology, 2019, 83: 138.
[4] YAN Hui, GUO Cheng, DI Dan-dan, et al(颜 辉, 郭 成, 第丹丹, 等). Acta Sericologica Sinica(蚕业科学), 2016, 42(6): 1077.
[5] Huang L X, Wu D, Jin H F, et al. Biosystems Engineering, 2011, 109(4): 377.
[6] Soltanikazemi M, Mehdizadeh S A, Heydari M. International Journal of Food Properties, 2017, 20(11): 2437.
[7] Huang L X, Zhou Y B, Meng L W, et al. Food Chemistry, 2017, 224: 1.
[8] Yang L, Gao H Q, Meng L W, et al. Food Chemistry, 2021, 2021, 334: 127614.
[9] Kattenborn T, Leitloff J, Schiefer F, et al. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 173: 24.
[10] Kirienko M, Biroli M, Gelardi F, et al. Clinical and Translational Imaging, 2021, 9(1): 37.
[11] KAN Xiang-cheng, XIE Guang-qiang, LI Yao-xiang, et al(阚相成, 解光强, 李耀翔, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2022, 42(11): 3387.
[12] Guo Z M, Wang M M, Shujat A, et al. Food Science & Nutrition, 2020, 8(7): 3793.
[13] Huang J D, He H Y, Lv R L, et al. Analytica Chimica Acta, 2022, 1224: 340238.
[14] Zhu N, Huang W N, Wu D, et al. Scientific Reports, 2017, 7: https://doi.org/10.1038/S41598-017-09817-7.
[15] Nicolaï B M, Beullens K, Bobelyn E, et al. Postharvest Biology and Technology, 2007, 46(2): 99.
[16] Pathmanaban P, Gnanavel B K, Anandan S S. Trends in Food Science & Technology, 2019, 94: 32.
[17] Wang B, Sun J F, Xia L M, et al. Food Reviews International, 2023, 39(2): 1043.
[18] Zhao Y R, Yu K Q, He Y. Journal of Analytical Methods in Chemistry, 2015, 2015: 343782.
