Hand-Held Visible/Near Infrared Nondestructive Detection System for Soluble Solid Content in Mandarin by 1D-CNN Model
CAI Jian-rong1, 2, HUANG Chu-jun1, MA Li-xin1, ZHAI Li-xiang1, GUO Zhi-ming1, 3*
1. School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, China
2. International Joint Research Laboratory of Intelligent Agriculture and Agri-Products Processing (Jiangsu University), Jiangsu Education Department, Zhenjiang 212013, China
3. Key Laboratory of Modern Agricultural Equipment and Technology (Jiangsu University), Ministry of Education, Zhenjiang 212013, China
Abstract：To realize the rapid, nondestructive detection of solid soluble content (SSC) in Mandarin, a hand-held nondestructive detection system was developed based on visible/near-infrared technology. Wide spectra range LED light source combined with a narrowband response micro-spectrometer was designed as a core in the handheld nondestructive detection terminal. The cloud data system of the fruit spectrometer based on Internet of Things technology was also developed, including a user database, equipment database, test database and model database. The data system was connected with the detection terminal through a communication module to realize functions, including modifying parameters of spectra collection, uploading and downloading the cloud data and invoking cloud model. Based on the spectra collected by the system, anovelone-dimensional convolutional neural network (1D-CNN) model was proposed to predictmandarin soluble solid content. The network contains 7 layers: input, convolution, pooling, full connection, and output. Mandarin spectra of the master machine were collected to build the 1D-CNN SSC prediction model, and the 1D-CNN model was compared with traditional regression methods to evaluate the model performance. The Rp and RMSEP of the 1D-CNN model were 0.812 and 0.488 respectively, better than that of partial least squares (PLS), artificial neural network (ANN) and support vector machine (SVM).Transfer learning method based on the 1D-CNN model of the master machine was adopted to transfer the model to the slave machine, the influence of the number of samples from the slave machine on model transfer was studied, and a small number of slave machine spectral samples for model training achieved good model transfer effect, modeling transferring result with root mean square error of prediction of the slave machine being 0.531.The results demonstrated that the detection system has the advantages of fast detection, low cost and simple operation. The 1D-CNN network based on the detection system could effectively extract effective features of Mandarin spectra and perform regression analysis. With the help of the transfer learning algorithm, the effective transfer of the 1D-CNN model between different devices can be realized, which could meet the demand fornon-destructive testing of solid soluble content in the mandarin industry.This research provided a reference for developing and applying handheld spectrometer non-destructive testing system of fruit internal quality.
Key words：Nondestructive detection; Mandarin; Visible/near infrared spectroscopy; Soluble solid content; One-dimensional convolutional neural network; Transfer learning; Model transfer
[1] Magwaza L S, Opara U L, Nieuwoudt H, et al. Food and Bioprocess Technology, 2012, 5(2): 425.
[2] GUO Zhi-ming, CHEN Quan-sheng, ZHANG Bin, et al(郭志明, 陈全胜, 张 彬, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2017, 33(8): 253.
[3] ZHAO Juan，QUAN Peng-kun, ZHANG Meng-sheng，et al(赵 娟, 全朋坤, 张猛胜，等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报)，2019，50(4): 326.
[4] FAN Shu-xiang, WANG Qing-yan, YANG Yu-sen, et al(樊书祥, 王庆艳, 杨雨森, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析) 2021, 41(10): 3058.
[5] Guo W, Li W, Yang B, et al. Journal of Food Engineering, 2019, 257: 1.
[6] WANG Fan, LI Yong-yu, PENG Yan-kun, et al(王 凡, 李永玉, 彭彦昆, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2017，33(19): 295.
[7] LUO Yin-bin, CAI Yan-li, LAN Han, et al(罗印斌, 蔡艳丽, 兰 菡，等). Science and Technology of Food Industry(食品工业科技), 2018, 39(15): 340.
[8] Zhang X, Chen L, Sun Y, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2018, 193(0): 133.
[9] Feng F, Wang S, Wang C, et al. Sensors, 2019, 19(23): 5276.
[10] Xu L, Zhu D, Chen X, et al. Chemometrics and Intelligent Laboratory Systems，2020, 199: 103954.
[11] Gu J, Wang Z, Kuen J, et al. Pattern Recognition, 2018, 77(1): 354.
[12] Gopal C J, Ratna S, Anupam A. Procedia Computer Science, 2020, 167: 403.
[13] Liu Y, Xu J, Tao Y, et al. The Analyst, 2020, 145(9): 3297.
[14] Yu Y, Huang J, Liu S, et al. Measurement, 2021, 177: 109340.
[15] He X, Fu X, Rao X, et al. Postharvest Biology and Technology, 2016, 121: 62.
[16] Zhu J, Sharma A S, Xu J, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2021, 246: 118994.
[17] Huang L, Guo S, Wang Y, et al. Mathematical Biosciences and Engineering, 2019, 16(4): 3003.
