A Novel Approach to Active Compounds Identification Based on Support Vector Regression Model and Mean Impact Value

Jiang, Jifa; Su, Xin; Zhang, Huan; Zhang, Xiaohang; Yang, Yuan

doi:10.1111/cbdd.12111

Cited by 45 publications

(25 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mean impact value (MIV) in this study is an important index used to select the independent features that have a great impact on the model. To date, it has been considered one of the best indexes to assess assigned coefficient values . In this study, after training the SVM model, two new training sets were obtained each time an independent feature increased or decreased 10% that were used for simulation according to the fitting model.…”

Section: Methodsmentioning

confidence: 99%

Personalized prediction model for seizure‐free epilepsy with levetiracetam therapy: a retrospective data analysis using support vector machine

Zhang

Han

Zhao

et al. 2018

Brit J Clinical Pharma

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Personalized prediction model for seizure‐free epilepsy with levetiracetam therapy: a retrospective data analysis using support vector machine

Zhang

Han

Zhao

et al. 2018

Brit J Clinical Pharma

View full text Add to dashboard Cite

show abstract

“…The mean impact value (MIV) is proposed by Dombi et al, which is considered to be one of the best indicators for evaluating the correlation of variables [43]. The FOA-GRNN model is initially trained and established by history data.…”

Section: MIVmentioning

confidence: 99%

The Influencing Factors, Regional Difference and Temporal Variation of Industrial Technology Innovation: Evidence with the FOA-GRNN Model

Zhang

Niu

et al. 2018

Sustainability

View full text Add to dashboard Cite

Technology innovation is a motivating force for sustainable development. The recognition and measurement of influencing factors are a basic prerequisite of technology innovation research. In response to the gaps and shortages of existing theories and methods, this paper builds the impact indicators of technology innovation, the proposed FOA-GRNN model, and analyzes the influencing factors, regional differences and temporal variations of technology innovation based on industrial above-scale enterprises of 31 provinces in China from 2008 to 2015. The empirical results show that innovation investment is a determinant of technology innovation in China, and is more and more significant; meanwhile a wide gap of innovation resource between Eastern China and Western China exists. In general, the enterprise scale has a negative effect: with enlargement of enterprise in China, the innovation efficiency of enterprise will decline, while the effect has regional disparity, with positive influence in Central and Western China, and negative influence in Eastern China. Government support has negative effects on technology innovation: indirect equity investment contributes more to technology innovation than direct fund support. Innovation environment has positive and weak effects on technology innovation, but it is the biggest obstacle in Western China, and the innovation environment in China has improved continuously. This paper provides new evidence that can shine some light on determining the factors affecting technology innovation, and also presents a novel approach, which comprises characteristics of nonlinear function approximation, high accuracy and a small sample.

show abstract

“…The number of lines in the network, which was computed using Pajek, was applied as the dependent variable, while the 23 static features were independent. Then the mean impact value (MIV) [9,10,11] exported by the BP neural network was used to screen the independent variables.…”

Section: The Static Features Of the Chromatin Image Network Of Nucleimentioning

confidence: 99%

Network analysis of lymphocyte nucleus staining image —Data mining of lymphocyte image

D¹,

Yang²,

Xiong³

et al. 2018

Preprint

View full text Add to dashboard Cite

Background: A complex network has been studied and applied in various disciplines. As network analysis and image processing are based on matrices, this research analysed the changes in the chromatin image of lymphocyte nuclei in peripheral blood of humans using a network motif and 1 *: Joint first author. yangxinglin. 123@163.com. Tel:+86 851 86753314 This study was supported by research grants from the Guiyang,Sci-Tech plan(2018)1-40, Taizhou 1401ky51 2 static features (static parameters), so as to complete image classification with network method.Methods: Image processing technology was used to establish a chromatin image network of a cell nucleus; Network analysis tool Pajek was used to display the special motif of an isolated structural hole with different symmetric line values; afterwards, the frequency of occurrence of this structural hole in patients with nasopharyngeal carcinoma and AIDS, and healthy people was computed. Then by applying the network static features as variables, the chromatin images of stained lymphocytes from the three groups of people were classified and recognised by using an extreme learning machine (ELM). Results: The frequency of occurrence of the isolated structural hole with different symmetric line values was adopted to distinguish the structures of the chromatins of peripheral blood lymphocytes in patients with nasopharyngeal carcinoma and AIDS, and healthy people. Similarly, The static features of the chromatin image network of a cell nucleus were applied to classify and recognise the morphological and structural changes in chromatins for peripheral blood lymphocytes in the three groups of people. Conclusion: The surface chemical and physical characteristics, as well as the polymerisation link status of biomacromolecules such as DNA, RNA, and protein in the lymphocyte nucleus change under certain pathological conditions. The change influences the combination of small molecular staining materials and any associated biomacromolecules. Therefore, various macroscopic and microscopic changes were found in the chromatin images of the cell nucleus. The microscopic changes include the variations of the extent of staining of chromatin in the nuclei, coarseness and direction of the texture therein, the size of stained conglomerations, etc. These changes contribute to the differences in chromatin image networks among the same type of cells across the three groups.Based on this, the model can be used to classify and reorganise certain diseases. The results prove that using complex network to analyse the chromatin structure of a cell nucleus is of significance.

show abstract

A Novel Approach to Active Compounds Identification Based on Support Vector Regression Model and Mean Impact Value

Cited by 45 publications

References 27 publications

Personalized prediction model for seizure‐free epilepsy with levetiracetam therapy: a retrospective data analysis using support vector machine

Personalized prediction model for seizure‐free epilepsy with levetiracetam therapy: a retrospective data analysis using support vector machine

The Influencing Factors, Regional Difference and Temporal Variation of Industrial Technology Innovation: Evidence with the FOA-GRNN Model

Network analysis of lymphocyte nucleus staining image —Data mining of lymphocyte image

Contact Info

Product

Resources

About