|
|
|
|
|
|
Determination of Huanghua Pear’s Harvest Time Based on Convolutional Neural Networks by Visible-Near Infrared Spectroscopy |
LIU Hui-jun, WEI Chao-yu, HAN Wen, YAO Yan |
College of Metrological Technology and Engineering, China Jiliang University, Hangzhou 310018, China |
|
|
Abstract The maturity of fruit at harvest time determines its final eating quality. Choosing the optimal harvest time of fruit is one of the key issues to improve fruit quality. Visible/near-infrared spectroscopy technology is suitable for fruit maturity and harvest time determination because of its rapid and non-destructive detection characteristics. Due to the large difference in fruit quality on the tree, traditional chemometric methods require complex spectral pretreatment, and the model is not suitable for different seasons, orchards, etc. In this paper, the discrimination model of Huanghua pear’s harvest time by full convolutional neural networks (CNNs) based on visible/near infrared spectroscopy (Vis/NIR) was proposed. The CNNs was used for spectral feature extraction, and the error backpropagation algorithm combined with the random gradient descent method was used to adjust the connection weights between layers, and output the Logistic regression of harvest time determination, which implemented the end-to-end discrimination of Huanghua pear’s harvest time, and the result was compared with the PLSDA method. The one-dimensional convolutional neural networks included one input layer, two convolution layers, a pooling layer and one Softmax output layer, using cross-entropy as the loss function, and the L2 regularization was used as the regular term to avoid overfitting, without preprocessing. A total of 450 samples were collected for two years. Three hundred samples in the first year constituted training set, 90 samples constituted test set one, and 60 samples in the second year constituted test set two. The results have shown that when the test set and the training set were collected from the same year, correct discrimination rate of PLSDA and CNNs models was 100%, when the test was from different years, correct discrimination rate reduced to 41.67% and 88.33%, respectively. The correlation coefficient and the mutual information of the modes indicated that the CNN model could take advantage of full-spectrum information. Therefore, the CNNs method optimizes convolution kernels through iteration to achieve more flexible preprocessing, which can reduce the difficulty of model training. The established model has good ability of explanation and generalization. The proposed method could be applied in discrimination of fruit’s harvest time.
|
Received: 2019-06-05
Accepted: 2019-10-28
|
|
|
[1] Sharpe P, Barber H. Applied Optics, 1972, 11(12): 2902.
[2] Peirs A, Lammertyn J, Ooms K, et al. Postharvest Biology and Technology, 2001, 21(2): 189.
[3] Peirs A, Schenk A, Nicolaï B M. Postharvest Biology and Technology, 2005, 35(1): 1.
[4] Zude M, Herold B, Roger J M, et al. Journal of Food Engineering, 2006, 77(2): 254.
[5] Liew C Y, Lau C Y. Int. Food Res. J, 2012, 19(2): 751.
[6] ZHAO Juan, QUAN Peng-kun,MA Min-juan, et al(赵 娟, 全朋坤, 马敏娟, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2018, 49(12): 354.
[7] McCormick R, Biegert K. NIR News, 2019, 30(1): 12.
[8] Malek S, Melgani F, Bazi Y. Journal of Chemometrics, 2018,32(5):e2977.
[9] Bjerrum E, Glahder M, Skov T. arXiv preprint arXiv: 1710.01927, 2017.
[10] LU Meng-yao, YANG Kai, SONG Peng-fei, et al(鲁梦瑶, 杨 凯, 宋鹏飞, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2018, 38(12): 3724.
[11] Acquarelli J, Van Laarhoven T, Gerretzen J, et al. Analytica Chimica Acta, 2017, 954: 22.
[12] Cui C, Fearn T. Chemometrics and Intelligent Laboratory Systems, 2018, 182: 9. |
[1] |
LI Xin-ting, ZHANG Feng, FENG Jie*. Convolutional Neural Network Combined With Improved Spectral
Processing Method for Potato Disease Detection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 215-224. |
[2] |
LAN Yan1,WANG Wu1,XU Wen2,CHAI Qin-qin1*,LI Yu-rong1,ZHANG Xun2. Discrimination of Planting and Tissue-Cultured Anoectochilus Roxburghii Based on SMOTE and Inception-CNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 158-163. |
[3] |
WANG Qi-biao1, HE Yu-kai1, LUO Yu-shi1, WANG Shu-jun1, XIE Bo2, DENG Chao2*, LIU Yong3, TUO Xian-guo3. Study on Analysis Method of Distiller's Grains Acidity Based on
Convolutional Neural Network and Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3726-3731. |
[4] |
YANG Qun1, 2, LING Qi-han1, WEI Yong1, NING Qiang1, 2, KONG Fa-ming1, ZHOU Yi-fan1, 2, ZHANG Hai-lin1, WANG Jie1, 2*. Non-Destructive Monitoring Model of Functional Nitrogen Content in
Citrus Leaves Based on Visible-Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3396-3403. |
[5] |
HUANG Meng-qiang1, KUANG Wen-jian2, 3*, LIU Xiang1, HE Liang4. Quantitative Analysis of Cotton/Polyester/Wool Blended Fiber Content by Near-Infrared Spectroscopy Based on 1D-CNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3565-3570. |
[6] |
CAI Jian-rong1, 2, HUANG Chu-jun1, MA Li-xin1, ZHAI Li-xiang1, GUO Zhi-ming1, 3*. Hand-Held Visible/Near Infrared Nondestructive Detection System for Soluble Solid Content in Mandarin by 1D-CNN Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2792-2798. |
[7] |
TANG Ruo-han1, 2, LI Xiu-hua1, 2*, LÜ Xue-gang1, 2, ZHANG Mu-qing2, 3, YAO Wei2, 3. Transmittance Vis-NIR Spectroscopy for Detecting Fibre Content of
Living Sugarcane[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2419-2425. |
[8] |
PU Shan-shan, ZHENG En-rang*, CHEN Bei. Research on A Classification Algorithm of Near-Infrared Spectroscopy Based on 1D-CNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2446-2451. |
[9] |
TANG Ting, PAN Xin*, LUO Xiao-ling, GAO Xiao-jing. Fusion of ConvLSTM and Multi-Attention Mechanism Network for
Hyperspectral Image Classification[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2608-2616. |
[10] |
LI Wen-xia1, DU Yu-jun2, WANG Yue1, LIU Zheng-dong3*, ZHENG Jia-hui1, DU Wen-qian1, WANG Hua-ping4. Research on On-Line Efficient Near-Infrared Spectral Recognition and Automatic Sorting Technology of Waste Textiles Based on Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2139-2145. |
[11] |
LIANG Wan-jie1, FENG Hui2, JIANG Dong3, ZHANG Wen-yu1, 4, CAO Jing1, CAO Hong-xin1*. Early Recognition of Sclerotinia Stem Rot on Oilseed Rape by Hyperspectral Imaging Combined With Deep Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2220-2225. |
[12] |
JIANG Xia*, QIU Bo, WANG Lin-qian, GUO Xiao-yu. Automatic Classification Method of Star Spectra Based on
Semi-Supervised Mode[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1875-1880. |
[13] |
ZHENG Zhi-jie1, LIN Zhen-heng1, 2*, XIE Hai-he2, NIE Yong-zhong3. The Method of Terahertz Spectral Classification and Identification for Engineering Plastics Based on Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1387-1393. |
[14] |
CHEN Dong-ying1, 2, ZHANG Hao1, 2*, ZHANG Zi-long1, YU Mu-xin1, CHEN Lu3. Research on the Origin Traceability of Honeysuckle Based on Improved 1D-VD-CNN and Near-Infrared Spectral Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1471-1477. |
[15] |
LIN Jing-tao, XIN Chen-xing, LI Yan*. Spectral Characteristics of “Trapiche-Like Sapphire” From ChangLe, Shandong Province[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(04): 1199-1204. |
|
|
|
|