Optimization of vacuum assisted heat reflux extraction process of radix isatidis using least squares-support vector machine algorithm

Sun, Haojie; Wu, Yuxia; Wu, Zhenfeng; Han, Fei; Wang, Yaqi

doi:10.1016/j.phytol.2021.03.009

Cited by 8 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After a large amount of data processing and analysis, the category of predict model is selected. The most commonly used criterion in time series models is the Akaike information criterion (AIC) criterion, through which the fit of the model can be calculated (Sun et al, 2021). The calculation equation of the AIC criterion is shown below.

AIC = 2 k - 2 \ln (l)

In the Equation () above, k represents the actual number of parameters and l refers to the likelihood function.…”

Section: Methodsmentioning

confidence: 99%

Adoption of blockchain + Internet of Things in demand forecasting of farm supply chain

Wang

Liu

2022

Expert Systems

View full text Add to dashboard Cite

It aims to improve the application efficiency of modern science and technology in farm operation, enhance the prediction effect of machine learning and blockchain technology on farm supply and demand issues, and help enterprise managers to better manage and operate enterprise projects. First, the agricultural super business model under the blockchain + Internet of Things (IoT) is analysed, and the farm management system of the IoT + blockchain is constructed. Then, the demand forecasting model of agricultural products is established. Autoregressive Integrated Moving Average model (ARIMA) and Support Vector Machine (SVM) models are used to predict demand. Finally, the characteristics of the two models in prediction are discussed. The results show that the ARIMA model can reach 99.2% in the application efficiency evaluation of farm operation. Moreover, in the case of proper selection of model indicators, the prediction result is close to the actual value, the prediction error fluctuation is small, and the maximum error value is 0.4318. The local error of SVM model in predicting the demand of farm supply chain is slightly larger, and the maximum error value is 8.5430. By comparing the error results of the two models, the prediction accuracy of ARIMA model is higher than that of SVM model. The ARIMA model designed in this work can provide effective product demand prediction for farm operation and provide a strong technical reference for farm operation. The research not only provides technical support for machine learning and blockchain technology to predict farm supply and demand, but also contributes to the integrated management and sustainable development of enterprises.

show abstract

AIC = 2 k - 2 \ln (l)

In the Equation () above, k represents the actual number of parameters and l refers to the likelihood function.…”

Section: Methodsmentioning

confidence: 99%

Adoption of blockchain + Internet of Things in demand forecasting of farm supply chain

Wang

Liu

2022

Expert Systems

View full text Add to dashboard Cite

show abstract

“…e main idea is to find a classification hyperplane that maximizes the separation margin between two classes of samples, and it is used as a decision surface. In short, SVM is to achieve the minimum value of structural risk [18]. After the 1990s, with the development of statistical learning theory and machine learning methods, such as neural networks, SVM has received extensive attention and began to develop rapidly [19].…”

Section: Svmmentioning

confidence: 99%

Enterprise Accounting Information Identification and Strategic Management under Data Mining Technology

Shao

Lai

Zheng

et al. 2022

Mobile Information Systems

View full text Add to dashboard Cite

Present-day enterprise accounting solutions have been developed to a certain extent to provide authenticity of accounting information and to provide modules for billing, pay role, general ledger, and more, but they come with certain problems such as distortion of accounting information, incomplete selection of indicator variables, and the limited and single use of identification methods. Based on this, this study starts with two points. The first is to give the concepts of decision trees and support vector machine (SVM) in data mining. Then, the accounting distortion information identification model is constructed based on this, and the model effect is verified by setting experiments. The second is to establish a regression model on the relationship between enterprise strategy and accounting information quality to further explore the factors that affect the quality of enterprise accounting information. The following are the research results: (1) The accuracy rates of classification and identification of training set data, overall data, and test set data using the SVM-based identification model are 99.19%, 96.21%, and 94.8%, respectively. (2) The average identification rate of the sample data is 88.5% using the identification model based on the decision tree. (3) The regression coefficients of enterprise strategy and accounting information quality are −0.053 and −0.054, respectively without considering the industry and year variables and with considering the industry and year variables, both of which are negative at the 0.1 significance level. The purpose of this study is to use data mining to achieve high-quality identification of enterprise accounting information and provide some references for enterprises to choose or formulate relevant development strategies.

show abstract

“…Isatis indigotica Fort., a biennial herbaceous plant of the family Cruciferae (Chen et al 2014), it was used as traditional Chinese medicine with roots (Isatidis radix) and leaves (Isatidis folium) (Sun et al 2021). As a medicinal plant for more than 2000 years from Shen Nong's Materia Medica, Isatidis radix has a widely useful activities including anti-virus, anti-bacterial, anti-endotoxic, anti-in ammatory, and immune regulatory effects (Ding and Zhu 2020;Kong et al 2008).…”

Section: Introductionmentioning

confidence: 99%

A rapid method for identifying ploidy level in Isatis indigotica Fortune and Isatis tinctoria Linnaeus

Su¹,

Zhang²,

Guo³

et al. 2021

Preprint

View full text Add to dashboard Cite

The genus Isatis is widely distributed throughout the world. In this work, thirty-two Isatis indigotica Fortune germplasms, collected from different regions and geographical locations in China, were analyzed the ploidy levels by flow cytometry. I. indigotica Fort. and Isatis tinctoria Linnaeus distinguished with root tip chromosome compression staining and cell flow cytometry. Microscopic observation showed that the chromosome numbers of I. indigotica Fort. and I. tinctoria L. were 2n = 14 and 2n = 28, respectively. In order to establish a flow cytometric nuclear experiment system suitable for I. indigotica Fort., the leaves of I. indigotica Fort. were used to prepare nuclear suspension with LB01, OTTO, Tris·MgCl2, patent of Luochang and Galbraith extraction buffer. It was found that the histogram generated by LB01, OTTO, Tris·MgCl2 and Patent of Luochang dissociation solution has poor peak shapes and large CV values, and Galbraith dissociation solution extraction buffer was suitable for extracting nuclei from most germplasms. Flow cytometry proved to be a simple, rapid, and highly accurate method for identifying ploidy levels Isatis species.

show abstract

Optimization of vacuum assisted heat reflux extraction process of radix isatidis using least squares-support vector machine algorithm

Cited by 8 publications

References 20 publications

Adoption of blockchain + Internet of Things in demand forecasting of farm supply chain

Adoption of blockchain + Internet of Things in demand forecasting of farm supply chain

Enterprise Accounting Information Identification and Strategic Management under Data Mining Technology

A rapid method for identifying ploidy level in Isatis indigotica Fortune and Isatis tinctoria Linnaeus

Contact Info

Product

Resources

About