Effect of Seedling Quality on Growth,Yield and Quality of Angelica sinensis

[Objectives]Aiming at the problems of high bolting rate,low yield and poor quality traits in the production of Angelica sinensis in Qinghai Province,this study investigated the effect of seeding quality on the growth,yield and quality of A.sinensis.[Methods]Field experiments were carried out in five aspects,including different seedling shapes,different seedling sizes,different seedling ages,different seedling raising methods,and different seedling sources.The effect of seedling quality on the survival rate,bolting rate,main quality traits(root length,root fresh weight,root head thickness,root head length)and yield of A.sinensis was investigated.[Results]The seedlings,0.2-0.5 cm in diameter,100-110-d old,raised from three-year-old provenance in cultivated land by conventional method,were more preferable,and their survival rate was high,bolting rate was low,yield is high,and quality traits performed well.[Conclusions]The seedlings,0.2-0.5 cm in diameter,100-110-d old,raised from three-year-old provenance in cultivated land by conventional method,were more preferable,and their survival rate was high,bolting rate was low,yield is high,and quality traits performed well.

Community Evolution Based on Tensor Decomposition

With the high dimensionality of data, the method of tensor decomposition has attracted much attention in the field of data research and analysis. The tensor decomposition is well reflected in the study of high-dimensional data. The existing research uses the results of tensor decomposition to conduct community discovery. Based on the existing research, this paper presents a method to study community evolution using the results of tensor decomposition. The feature matrix obtained by the tensor decomposition algorithm was analyzed, and the real-time activity of the community with the feature matrix with time slice direction was studied to obtain the event process of community evolution. Experimental results in real data sets show that this method can well analyze dynamic events in the dataset and community evolution events.

Integrated medical resource consumption stratification in hospitalized patients:an Auto Triage Management model based on accurate risk,cost and length of stay prediction

Triage management plays important roles in hospitalized patients for disease severity stratification and medical burden analysis.Although progression risks have been extensively researched for numbers of diseases,other crucial indicators that reflect patients’economic and time costs have not been systematically studied.To address the problems,we developed an automatic deep learning based Auto Triage Management(ATM)Framework capable of accurately modelling patients’disease progression risk and health economic evaluation.Based on them,we can first discover the relationship between disease progression and medical system cost,find potential features that can more precisely aid patient triage in resource allocation,and allow treatment plan searching that has cured patients.Applying ATM in COVID-19,we built a joint model to predict patients’risk,the total length of stay(Lo S)and cost when at-admission,and remaining Lo S and cost at a given hospitalized time point,with C-index0.930 and 0.869 for risk prediction,mean absolute error(MAE)of 5.61 and 5.90 days for total Lo S prediction in internal and external validation data.