Prediction of Disintegration Time of Traditional Chinese Medicine Tablets Based on Generalized Regression Neural Network / 中国实验方剂学杂志

Objective:This paper constructs a generalized regression neural network （GRNN） model to predict the disintegration time of traditional Chinese medicine （TCM） tablets. Method:Taking Astragali Radix as a model drug， the mixed Astragali Radix powders with different powder properties were prepared by mixing Astragali Radix extract powders with microcrystalline cellulose and lactose， which were made to Astragali Radix tablets by direct compression method. The powder properties of mixed Astragali Radix powders and the disintegration time of Astragali Radix tablets were determined， respectively. The correlation between the original data was eliminated by principal component analysis （PCA）. The principal component factors were used as the input layer of the GRNN model， and the disintegration time was used as the output layer for network training. Finally， the verification group data was used to predict the disintegration time， and the network prediction accuracy was calculated by comparing with the actual value. Result:Three principal component factors were obtained through PCA by analyzing the original nine variables that were correlated with each other （Hausner ratio， true density， tap density， compression degree， angle of repose， bulk density， porosity， water content and total dissolved solids）， which reduced the complexity of the network. The prediction value of the disintegration time based on this prediction method was in good agreement with the actual value， the error of disintegration time was 0.01-1.34 min and the average relative error was 3.16%. Conclusion:Based on the GRNN mathematical model， the physical properties of Astragali Radix extract powders can be used to accurately predict the disintegration time of Astragali Radix tablets， which provides a reference for studying the disintegration time of TCM tablets.

In vitro recognition of HIFU-induced biological tissue degeneration based on ultrasound / 中国医学影像技术

Objective: To explore a method to improve the identification rate of tissue degeneration caused by high intensity focused ultrasound (HIFU) based on ultrasound combining with generalized regression neural network (GRNN). Methods: Totally 300 fresh isolated pork tissue samples were selected and irradiated at different HIFU doses, then 150 denatured and 150 undenatured samples were obtained. Ultrasonic images of the samples were collected before and after irradiation, then ultrasonic subtraction images were obtained. A total of 18 characteristic parameters of ultrasonic subtractive images were extracted using gray-gradient co-occurrence matrix and gray difference statistical methods, and the best characteristic vectors were obtained with P-value significance detection method and Euclidean distance method. Among 300 samples, 198 were taken as training samples and 102 as test samples. After recognition of training samples, the feature vectors eliminated with P-value significance detection method and 2 feature vectors with the smallest Euclidean distance were taken as control group of the best feature vectors, and then were input into GRNN respectively for recognition of tissue denaturation. Correct recognition rate and total recognition rate of test samples were calculated using combining feature vectors with GRNN. Results: The best feature vectors were non-uniformity of gray distribution and non-uniformity of gradient distribution, and the total recognition rate was 90.20% and 91.18% combining with GRNN, respectively, which increased to 98.04% when both 2 best characteristic parameters combined GRNN. The feature vectors eliminated using P-value significance detection method were average value and contrast, and the total recognition rate combining with GRNN was 48.04% and 75.49%, respectively, which became 79.41% when both 2 best characteristic parameters combined GRNN. The feature vectors with the smallest euclide distance were energy and small gradient, and the total recognition rate combining with GRNN was 88.24% and 89.22%, respectively, which remained 89.22% when both 2 of them combined with GRNN. The recognition rate of the optimal feature vectors combined with GRNN for tissue denaturation was significantly higher than that of control group. Conclusion: Based on ultrasonic subtraction images, of pork tissue irradiated with HIFU, non-uniformity of gray distribution and non-uniformity of gradient distribution combined with GRNN can both improve the recognition rate of tissue denaturation, while the combination of them and GRNN is more effective in identifying tissue denaturation induced by HIFU.

Comparative study on ARIMA model and GRNN model for predicting the incidence of tuberculosis / 第二军医大学学报

Objective To compare the performance of ARIMA model and GRNN model for predicting the incidence of tuberculosis. Methods ARIMA model was set up by Eviews 7.0.0.1 and GRNN model was set up by neural network toolbox of Matlab 7.1 based on the monthly tuberculosis incidence data from January 2004 to December 2012 in China. Monthly tuberculosis incidence data in 2013 were subjected to the two models for testing, and the results were compared between the two groups. Results The Theil unequal coefficients (TIC) were 0.034 and 0.059 for ARIMA model and GRNN model, respectively, indicating that ARIMA model was better than GRNN model to fit with the monthly incidence of tuberculosis in 2013. The absolute value of the relative error for ARIMA model was only 57.19% of GRNN model. Conclusion ARIMA prediction model is more suitable for predicting the incidence of tuberculosis in China, and it is suggested a combination of models should be used to predict the incidence of tuberculosis.

Comparison of predictive effect between the single auto regressive integrated moving average (ARIMA) model and the ARIMA-generalized regression neural network (GRNN) combination model on the incidence of scarlet fever / 中华流行病学杂志

R2) of the two models were 0.801,0.872 respectively. The fitting efficacy of the ARIMA-GRNN combination model was better than the single ARIMA, which had practical value in the research on time series data such as the incidence of scarlet fever.