Abstract
In this study, near infrared spectroscopy combined with chemometrics building models to was used to detect the soluble solid contents from watermelon,through four methods, K nearest neighbors regression, Random forest regression, convolution neural network, convolution neural network added residual-block. Some deep learning modules with image processing, coding modules in 1-d ways and apply in Visible/Near-infrared spectroscopy for modeling exploration was used. As a result, deep learning modules showed great potential in Visible/Near-infrared spectroscopy data processing, and CNN model got 0.855 9 correlation coefficient and 0.778 1 °Brix RMSEP in prediction-set. The Res-CNN model achieved 0.893 2 correlation coefficient and 0.710 4 °Brix RMSEP in prediction-set. The results of this study could provide a reference for the rapid and non-destructive model development of watermelon quality.
Publication Date
2-18-2023
First Page
132
Last Page
135
DOI
10.13652/j.issn.1003-5788.2020.12.028
Recommended Citation
WU, Shuang; LI, Guo-jian; and JIE, Deng-fei
(2023)
"Prediction model research of SSC in watermelon based on deep learning and visible/near infrared spectroscopy,"
Food and Machinery: Vol. 36:
Iss.
12, Article 28.
DOI: 10.13652/j.issn.1003-5788.2020.12.028
Available at:
https://www.ifoodmm.cn/journal/vol36/iss12/28
References
[1] 杨念,文长存,吴敬学.世界西瓜产业发展现状与展望[J].农业展望,2016,12(1):45-48.
[2] 赵洪卫,宋曙辉,常冬,等.小型西瓜果实生长过程中无损检测基础信息的研究[J].食品安全质量检测学报,2011,2(6):273-282.
[3] 王硕,袁洪福,宋春风,等.小西瓜糖度表征与漫反射近红外检测方法的研究[J].光谱学与光谱分析,2012,32(8):2 122-2 127.
[4] ARENDSE E,FAWOLE O A,MAGWAZA L S,et al.Non-destructive prediction of internal and external quality attributes of fruit with thick rind:A review[J].Journal of Food Engineering,2018,217:11-23.
[5] 陈辰,鲁晓翔,张鹏,等.红提葡萄VC含量的可见/近红外检测模型[J].食品与机械,2015,31(5):70-74.
[6] XU Lu,LI Jiang-bo,ZHANG Dong-yan.Near-infrared light penetration depth analysis inside melon with thick peel by a novel strategy of slicing combining with least square fitting method[J].Journal of Food Process Engineering,2018,41(7):e12886.1-e12886.6.
[7] ABASI S,MINAEE S,JAMSHIDI B,et al.Rapid measurement of apple quality parameters using wavelet de-noising transform with Vis/NIR analysis[J].Scientia Horticulturae,2019,252:7-13.
[8] 韩东海,常冬,宋曙辉,等.小型西瓜品质近红外无损检测的光谱信息采集[J].农业机械学报,2013,44(7):174-182.
[9] 何洪巨,胡丽萍,李武,等.基于可见/近红外高光谱成像技术的西甜瓜糖度检测[J].中国食物与营养,2016,22(10):53-57.
[10] ZHANG Bao-hua,GU Bao-xing,TIAN Guang-zhao,et al.Challenges and solutions of optical-based nondestructive quality inspection for robotic fruit and vegetable grading systems:A technical review[J].Trends in Food Science & Technology,2018,81:213-244.
[11] 钱曼,黄文倩,王庆艳,等.西瓜检测部位差异对近红外光谱可溶性固形物预测模型的影响[J].光谱学与光谱分析,2016,36(6):1 700-1 705.
[12] 周飞燕,金林鹏,董军.卷积神经网络研究综述[J].计算机学报,2017,40(6):1 229-1 251.
[13] 杨志锐,郑宏,郭中原,等.基于网中网卷积神经网络的红枣缺陷检测[J].食品与机械,2020,36(2):140-145.
[14] ZHOU Xin,SUN Jun,TIAN Yan,et al.Development of deep learning method for lead content prediction of lettuce leaf using hyperspectral images[J].Taylor & Tamp:Francis,2020,41(6):2 263-2 276.
[15] YU Xin-jie,LU Huan-da,WU Di.Development of deep learning method for predicting firmness and soluble solid content of postharvest Korla fragrant pear using Vis/NIR hyperspectral reflectance imaging[J].Postharvest Biology and Technology,2018,141:39-49.
[16] 介邓飞,陈猛,谢丽娟,等.适宜西瓜检测部位提高近红外光谱糖度预测模型精度[J].农业工程学报,2014,30(9):229-234.
[17] HE Kai-ming,ZHANG Xiang-yu,REN Shao-qing,et al.Deep residual learning for image recognition[J].IEEE Computer Society,2016,1:770-778.
[18] WU Zi-feng,SHEN Chun-hua,HENGEL Anton van den.Wider or deeper:Revisiting the resnet model for visual recognition[J].Pattern Recognition,2019,90:119-133.
[19] HU Li-da,GE Qi.Automatic facial expression recognition based on MobileNetV2 in Real-time[J].Journal of Physics Conference Series,2020,1 549:022136.
[20] 于攀,叶俊勇.基于谱回归和核空间最近邻的基因表达数据分类[J].电子学报,2011,39(8):1 955-1 960.
[21] 王鹏新,齐璇,李俐,等.基于随机森林回归的玉米单产估测[J].农业机械学报,2019,50(7):237-245.