Optical Instruments, Volume. 45, Issue 4, 71(2023)
Spectral reflectivity based tea concentration prediction for tea dyeing of rice paper
Figures & Tables(11)
Fig. 1. Images of two kinds of tea dyed rice papers using distilled water and tap water
Fig. 2. The average spectral reflectance of two kinds of tea dyed rice papers using distilled water and tap water
Fig. 4. Spectral curves of 300 samples of each of the four brands of ricepaper
Fig. 5. Results of PLS model estimation for four brands of rice paper
Fig. 6. Results of BP neural network model for four brands of rice paper
Fig. 7. The characteristic spectral wavelengths of four brands of rice paper were screened by SPA
Table 1. Chromatism of two kinds of tea dyed rice papers using distilled water and tap water
View tableView in ArticleTable 1. Chromatism of two kinds of tea dyed rice papers using distilled water and tap water
茶叶使用量 Paper1 Paper2 25 g 35 g 25 g 35 g 蒸馏水500 mL L*=72.207 a*=3.172 b*=19.341 L*=66.760 a*=4.547 b*=20.257 L*=71.186 a*=4.775 b*=22.072 L*=66.597 a*=5.490 b*=22.957 自来水500 mL L*=72.732 a*=3.171 b*=19.328 L*=67.067 a*=4.611 b*=20.656 L*=71.890 a*=4.764 b*=22.052 L*=66.763 a*=4.919 b*=21.937 色差 0.3232 0.3946 0.6664 0.5350
Table 2. PLS model results of four brands of rice paper
View tableView in ArticleTable 2. PLS model results of four brands of rice paper
样本 训练集 测试集 预测正确率/% R2 RMSE 预测正确率/% R2 RMSE Paper1 90.29 0.9026 2.5250 88.13 0.8726 2.7988 Paper2 93.61 0.9178 2.1123 91.73 0.9066 2.3162 Paper3 95.55 0.9506 1.7010 93.35 0.9319 1.8980 Paper4 96.33 0.9724 0.9212 95.69 0.9521 1.0121 平均 93.95 0.9359 1.8149 92.23 0.9158 2.0063
Table 3. BP neural network model results of four brands of rice paper
View tableView in ArticleTable 3. BP neural network model results of four brands of rice paper
样本 训练集 测试集 预测正确率/% R2 RMSE 预测正确率/% R2 RMSE Paper1 95.64 0.9294 1.0028 95.02 0.9211 0.9626 Paper2 97.54 0.9531 0.9206 96.61 0.9488 0.9937 Paper3 96.98 0.9864 0.8048 96.92 0.9577 0.8657 Paper4 98.27 0.9919 0.7079 98.06 0.9886 0.7156 平均 97.11 0.9652 0.8590 96.65 0.9541 0.8844
Table 4. Results of SPA-PLS and SPA-BP neural network estimation models for four brands of rice paper
View tableView in ArticleTable 4. Results of SPA-PLS and SPA-BP neural network estimation models for four brands of rice paper
模型 样本 训练集 测试集 预测正确率/% R2 RMSE 预测正确率/% R2 RMSE SPA-PLS Paper1 90.87 0.8689 2.2241 91.69 0.8994 2.0906 Paper2 94.47 0.9346 2.1832 94.47 0.9346 2.1834 Paper3 96.74 0.9837 1.0817 96.70 0.9822 1.1391 Paper4 97.75 0.9895 0.7636 98.47 0.9931 0.5170 平均 94.96 0.9442 1.5632 95.33 0.9523 1.4826 SPA-BP Paper1 97.60 0.9817 1.1780 98.22 0.9819 1.1618 Paper2 98.32 0.9945 0.6420 98.16 0.9935 1.0628 Paper3 98.77 0.9905 0.6040 98.36 0.9921 0.6122 Paper4 98.49 0.9938 0.6753 98.84 0.9965 0.5363 平均 98.30 0.9901 0.7743 98.40 0.9910 0.8433
Tools
Get Citation
Copy Citation Text
Shaobo WANG, Jiangkun ZHANG, Qingbiao CHENG, Ning SHEN, Jie LIU, Jie FENG. Spectral reflectivity based tea concentration prediction for tea dyeing of rice paper[J]. Optical Instruments, 2023, 45(4): 71
Paper Information
Category: DESIGN AND RESEARCH
Received: Nov. 28, 2022
Accepted: --
Published Online: Sep. 26, 2023
The Author Email: FENG Jie (fengjie_ynnu@126.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20