摘要
ObjectiveTo realize the automatic recognition of the slicing angles of Fritillariae Thunbergii Bulbus （FTB） based on the improved YOLOv7-tiny algorithm. MethodFirstly， a diverse dataset of FTB images， totaling 16 000 pictures， with various angles was constructed. Furthermore， improvements were made to YOLOv7-tiny by replacing standard convolutions with ghost convolution （GhostConv）， incorporating the coordinate attention （CA） mechanism as a preferred addition， substituting some activation functions with HardSwish function for decreasing the floating point operations. Additionally， a penalty term for angle recognition error was integrated into the loss function， and modifications were made to the non-maximum suppression （NMS） strategy to address cases where multiple detection results were associated with the same target. In order to verify the effectiveness of different improvement points on the optimization of the algorithm model， ablation experiments were carried out on all the improvement points， and the effectiveness of the improvement points was proved by comparing the prediction results before and after the addition of a certain improvement point on the basis of the original model or the model with the addition of an improvement point that has been verified to be effective， in order to evaluate the improvement of the indexes. ResultThe number of parameters required for the improved slicing angle recognition algorithm of FTB was about 55.4% of the original algorithm， and the amount of computation was about 59.4% of the original algorithm. The mAP@0.5［mean average precision at an intersection over union（IoU） of 0.5］ increased by 12.2%， the mean absolute error（MAE） of the recognized angle was 5.02°， representing a reduction of 4.58° compared to the original algorithm. In the experimental environment of this paper， the average recognition time per image was as low as 8.7 ms， significantly faster than the average human reaction time. ConclusionThis study， by utilizing the improved YOLOv7-tiny algorithm， achieves effective slicing angle recognition of FTB with high accuracy and more lightweight， which provides a novel approach for stable and precise automated slicing of FTB， thereby providing valuable insights into the automation of processing other traditional Chinese medicines.
摘要
Objective: To established a near-infrared spectroscopy quantitative model for the rapid determination of volatile oils from Rhizoma wenyujin concisum. Methods:Firstly, the volatile oils from Rhizoma wenyujin was determined by the distillation method described in Chinese Pharmacopoeia. The quantitative calibration model was established and optimized by fourier transformation near-infrared spectroscopy ( FT-NIR) combined with partial least square ( PLS) regression. The calibration model was evaluated by the coef-ficient (r), root-mean-square error of calibration (RMSEC) and root mean square of cross-validation (RMSECV) of the calibration model as well as the root mean square of prediction ( RMSEP) of prediction model. Results: In the combination of FT-NIR and PLS regression, the spectrum of 7189-4227 cm-1 , 8813-7478 cm-1 and"second spectrum+MSC" were chosen to establishe and optimize the quantitative calibration model. For the quantitative calibration model, the r, RMSEC and RMSECV of volatile oils was 0. 9769, 0. 0907 and 0. 3773, respectively. For the prediction model, the r and RMSEP of volatile oils was 0. 9053 and 0. 1960, respective-ly. Conclusion:The established near-infrared spectroscopy quantitative model is relatively stable, accurate and reliable in the simulta-neous quantitative analysis of volatile oils, and is expected to be used for the rapid determination of volatile oils from Rhizoma wenyujin concisum.
摘要
Objective: To established a near-infrared spectroscopy quantitative model for the rapid determination of volatile oils from Rhizoma wenyujin concisum. Methods:Firstly, the volatile oils from Rhizoma wenyujin was determined by the distillation method described in Chinese Pharmacopoeia. The quantitative calibration model was established and optimized by fourier transformation near-infrared spectroscopy ( FT-NIR) combined with partial least square ( PLS) regression. The calibration model was evaluated by the coef-ficient (r), root-mean-square error of calibration (RMSEC) and root mean square of cross-validation (RMSECV) of the calibration model as well as the root mean square of prediction ( RMSEP) of prediction model. Results: In the combination of FT-NIR and PLS regression, the spectrum of 7189-4227 cm-1 , 8813-7478 cm-1 and"second spectrum+MSC" were chosen to establishe and optimize the quantitative calibration model. For the quantitative calibration model, the r, RMSEC and RMSECV of volatile oils was 0. 9769, 0. 0907 and 0. 3773, respectively. For the prediction model, the r and RMSEP of volatile oils was 0. 9053 and 0. 1960, respective-ly. Conclusion:The established near-infrared spectroscopy quantitative model is relatively stable, accurate and reliable in the simulta-neous quantitative analysis of volatile oils, and is expected to be used for the rapid determination of volatile oils from Rhizoma wenyujin concisum.
摘要
Objective To investigate the change of the content of polysaccharides in crude and processed Fructus Corni,thus to approach the process mechanism of Fructus Corni.Methods The content of polysaccharides in the crude and processed Fructus Corni was determined by phenol-sulfuric acid method.Results After processing with wine,the content of polysaccharides of Fructus Corni decreased from 10.12 %(content of total polysaccharidesbeing 51.41 %) to 5.91 %(content of total polysaccharidesbeing 53.10 %),decreased by 41.60 %as compared with that in the crude Fructus Corni.Conclusion After processing with wine,the content of polysaccharides decreases markedly.The results provide certain evidence for approaching the process mechanism of Fructus Corni.