scholarly journals Quantitative structure-pharmacokinetic relationship (QSPkP) analysis of the volume of distribution values of anti-infective agents from j group of the ATC classification in humans

2012 ◽  
Vol 62 (3) ◽  
pp. 305-323 ◽  
Author(s):  
Bruno Louis ◽  
Vijay K. Agrawal
Keyword(s):  
Statistical Tests ◽  
External Validation ◽  
Volume Of Distribution ◽  
Support Vector ◽  
Quantitative Structure ◽  
Beta Lactam ◽  
Svm Model ◽  
Correlation Based Feature Selection ◽  
Artificial Neural Network Ann ◽  
D Values

In this study, a quantitative structure-pharmacokinetic relationship (QSPkR) model for the volume of distribution (Vd) values of 126 anti-infective drugs in humans was developed employing multiple linear regression (MLR), artificial neural network (ANN) and support vector regression (SVM) using theoretical molecular structural descriptors. A correlation-based feature selection (CFS) was employed to select the relevant descriptors for modeling. The model results show that the main factors governing Vd of anti-infective drugs are 3D molecular representations of atomic van der Waals volumes and Sanderson electronegativities, number of aliphatic and aromatic amino groups, number of beta-lactam rings and topological 2D shape of the molecule. Model predictivity was evaluated by external validation, using a variety of statistical tests and the SVM model demonstrated better performance compared to other models. The developed models can be used to predict the Vd values of anti-infective drugs.

scholarly journals Screening for Prediabetes Using Machine Learning Models

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Soo Beom Choi ◽  
Won Jae Kim ◽  
Tae Keun Yoo ◽  
Jee Soo Park ◽  
Jai Won Chung ◽  
...  
Keyword(s):  
External Validation ◽  
Systematic Evaluation ◽  
Support Vector ◽  
Ann Model ◽  
Internal Validation ◽  
Health And Nutrition ◽  
Svm Model ◽  
Score Model ◽  
Artificial Neural Network Ann ◽  
Better Than

The global prevalence of diabetes is rapidly increasing. Studies support the necessity of screening and interventions for prediabetes, which could result in serious complications and diabetes. This study aimed at developing an intelligence-based screening model for prediabetes. Data from the Korean National Health and Nutrition Examination Survey (KNHANES) were used, excluding subjects with diabetes. The KNHANES 2010 data(n=4685)were used for training and internal validation, while data from KNHANES 2011(n=4566)were used for external validation. We developed two models to screen for prediabetes using an artificial neural network (ANN) and support vector machine (SVM) and performed a systematic evaluation of the models using internal and external validation. We compared the performance of our models with that of a screening score model based on logistic regression analysis for prediabetes that had been developed previously. The SVM model showed the areas under the curve of 0.731 in the external datasets, which is higher than those of the ANN model (0.729) and the screening score model (0.712), respectively. The prescreening methods developed in this study performed better than the screening score model that had been developed previously and may be more effective method for prediabetes screening.

Combination of Support Vector Machine and K-Fold cross-validation for prediction of long-term degradation of the compressive strength of marine concrete

2018 ◽  
Vol 1 (1) ◽  
pp. 120-130 ◽  
Author(s):  
Chunxiang Qian ◽  
Wence Kang ◽  
Hao Ling ◽  
Hua Dong ◽  
Chengyao Liang ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Environmental Factors ◽  
Cross Validation ◽  
Concrete Strength ◽  
Simulation Method ◽  
Support Vector ◽  
Svm Model ◽  
Artificial Neural Network Ann ◽  
Influence Degree ◽  
Fold Cross Validation

Support Vector Machine (SVM) model optimized by K-Fold cross-validation was built to predict and evaluate the degradation of concrete strength in a complicated marine environment. Meanwhile, several mathematical models, such as Artificial Neural Network (ANN) and Decision Tree (DT), were also built and compared with SVM to determine which one could make the most accurate predictions. The material factors and environmental factors that influence the results were considered. The materials factors mainly involved the original concrete strength, the amount of cement replaced by fly ash and slag. The environmental factors consisted of the concentration of Mg2+, SO42-, Cl-, temperature and exposing time. It was concluded from the prediction results that the optimized SVM model appeared to perform better than other models in predicting the concrete strength. Based on SVM model, a simulation method of variables limitation was used to determine the sensitivity of various factors and the influence degree of these factors on the degradation of concrete strength.

scholarly journals Simulating the Stress-Strain Relationship of Geomaterials by Support Vector Machine

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Hongbo Zhao ◽  
Zenghui Huang ◽  
Zhengsheng Zou
Keyword(s):  
Support Vector Machine ◽  
Constitutive Relationship ◽  
Support Vector ◽  
Nonlinear Relationship ◽  
Ann Model ◽  
Stress Strain ◽  
Svm Model ◽  
Strain Relationship ◽  
Artificial Neural Network Ann ◽  
Relationship Of

Stress-strain relationship of geomaterials is important to numerical analysis in geotechnical engineering. It is difficult to be represented by conventional constitutive model accurately. Artificial neural network (ANN) has been proposed as a more effective approach to represent this complex and nonlinear relationship, but ANN itself still has some limitations that restrict the applicability of the method. In this paper, an alternative method, support vector machine (SVM), is proposed to simulate this type of complex constitutive relationship. The SVM model can overcome the limitations of ANN model while still processing the advantages over the traditional model. The application examples show that it is an effective and accurate modeling approach for stress-strain relationship representation for geomaterials.

Water quality prediction using machine learning methods

2018 ◽  
Vol 53 (1) ◽  
pp. 3-13 ◽  
Author(s):  
Amir Hamzeh Haghiabi ◽  
Ali Heidar Nasrolahi ◽  
Abbas Parsaie
Keyword(s):  
Water Quality ◽  
Kernel Functions ◽  
Support Vector ◽  
Group Method ◽  
Water Quality Prediction ◽  
Machine Learning Methods ◽  
Svm Model ◽  
Different Types ◽  
Artificial Neural Network Ann ◽  
Southwest Of Iran

Abstract This study investigates the performance of artificial intelligence techniques including artificial neural network (ANN), group method of data handling (GMDH) and support vector machine (SVM) for predicting water quality components of Tireh River located in the southwest of Iran. To develop the ANN and SVM, different types of transfer and kernel functions were tested, respectively. Reviewing the results of ANN and SVM indicated that both models have suitable performance for predicting water quality components. During the process of development of ANN and SVM, it was found that tansig and RBF as transfer and kernel functions have the best performance among the tested functions. Comparison of outcomes of GMDH model with other applied models shows that although this model has acceptable performance for predicting the components of water quality, its accuracy is slightly less than ANN and SVM. The evaluation of the accuracy of the applied models according to the error indexes declared that SVM was the most accurate model. Examining the results of the models showed that all of them had some over-estimation properties. By evaluating the results of the models based on the DDR index, it was found that the lowest DDR value was related to the performance of the SVM model.

Prediction of the optimal FSW process parameters for joints using machine learning techniques

2021 ◽  
Vol 63 (12) ◽  
pp. 1104-1111
Author(s):  
Furkan Sarsilmaz ◽  
Gürkan Kavuran
Keyword(s):  
Mechanical Properties ◽  
Tensile Strength ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Ann Model ◽  
Friction Stir ◽  
Learning Techniques ◽  
Svm Model ◽  
Artificial Neural Network Ann ◽  
Fsw Parameters

Abstract In this work, a couple of dissimilar AA2024/AA7075 plates were experimentally welded for the purpose of considering the effect of friction-stir welding (FSW) parameters on mechanical properties. First, the main mechanical properties such as ultimate tensile strength (UTS) and hardness of welded joints were determined experimentally. Secondly, these data were evaluated through modeling and the optimization of the FSW process as well as an optimal parametric combination to affirm tensile strength and hardness using a support vector machine (SVM) and an artificial neural network (ANN). In this study, a new ANN model, including the Nelder-Mead algorithm, was first used and compared with the SVM model in the FSW process. It was concluded that the ANN approach works better than SVM techniques. The validity and accuracy of the proposed method were proved by simulation studies.

scholarly journals Use of GA-ANN and GA-SVM for a QSPR study on aqueous solubility of pesticides

2020 ◽  
pp. 66-66
Author(s):  
Amel Bouakkadia ◽  
Noureddine Kertiou ◽  
Rana Amiri ◽  
Youssouf Driouche ◽  
Djelloul Messadi
Keyword(s):  
Pearson Correlation ◽  
Chemical Properties ◽  
Aqueous Solubility ◽  
Important Variable ◽  
Support Vector ◽  
Ann Model ◽  
Experimental Procedure ◽  
Svm Model ◽  
Artificial Neural Network Ann ◽  
Selection Of

The partitioning tendency of pesticides, in these study herbicides in particular, into different environmental compartments depends mainly of the physic-chemical properties of the pesticides itself. Aqueous solubility (S) indicates the tendency of a pesticide to be removed from soil by runoff or irrigation and to reach surface water. The experimental procedure determining aqueous solubility of pesticides is very expensive and difficult. QSPR methods are often used to estimate the aqueous solubility of herbicides. The artificial neural network (ANN) and support vector machine (SVM) methods, every time associated with genetic algorithm (GA) selection of the most important variable, were used to develop QSPR models to predict the aqueous solubility of a series 80 herbicides. The values of log S of the studied compounds were well correlated with de descriptors. Considering the pertinent descriptors, a Pearson Correlation Squared (R2) coefficient of 0.8 was obtained for the ANN model with a structure of 5-3-1 and 0.8 was obtained for the SVM model using the RBF function for the optimal parameters values: C = 11.12; ? = 0.1111 and ? = 0.222.

A Novel SVM-Based Method for Seismic First-Arrival Detecting

2010 ◽  
Vol 29-32 ◽  
pp. 973-978 ◽  
Author(s):  
Ming Chen ◽  
Yong Li ◽  
Jun Xie
Keyword(s):  
Support Vector ◽  
The Novel ◽  
Ann Model ◽  
Seismic Record ◽  
Feature Vectors ◽  
Svm Model ◽  
First Arrival ◽  
Ann Models ◽  
Novel Method ◽  
Artificial Neural Network Ann

First arrivals detecting on seismic record is important at all times. A novel support vector machine (SVM)-based method for seismic first-arrival pickup is proposed in this research. Firstly, the multi-resolution wavelet decomposition is used to de-noise the seismic record. And then, feature vectors are extracted from the denoise data. Finally, both SVM and artificial neural network (ANN) models are employed to train and predict the feature vectors. Experimental results demonstrate that the SVM model gives better accuracy than the ANN model. It is promising that the novel method is very prospective.

scholarly journals Trabeculae microstructure parameters serve as effective predictors for marginal bone loss of dental implant in the mandible

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Hengguo Zhang ◽  
Jie Shan ◽  
Ping Zhang ◽  
Xin Chen ◽  
Hongbing Jiang
Keyword(s):  
Bone Loss ◽  
Dental Implant ◽  
Alveolar Bone ◽  
Early Stage ◽  
Support Vector ◽  
Marginal Bone Loss ◽  
Svm Model ◽  
Microstructure Parameters ◽  
Artificial Neural Network Ann ◽  
Normal Controls

Abstract Marginal bone loss (MBL) is one of the leading causes of dental implant failure. This study aimed to investigate the feasibility of machine learning (ML) algorithms based on trabeculae microstructure parameters to predict the occurrence of severe MBL. Eighty-one patients (41 severe MBL cases and 40 normal controls) were involved in the current study. Four ML models, including support vector machine (SVM), artificial neural network (ANN), logistic regression (LR), and random forest (RF), were employed to predict severe MBL. The area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity were used to evaluate the performance of these models. At the early stage of functional loading, severe MBL cases showed a significant increase of structure model index and trabecular pattern factor in peri-implant alveolar bone. The SVM model exhibited the best outcome in predicting MBL (AUC = 0.967, sensitivity = 91.67%, specificity = 100.00%), followed by ANN (AUC = 0.928, sensitivity = 91.67%, specificity = 93.33%), LR (AUC = 0.906, sensitivity = 91.67%, specificity = 93.33%), RF (AUC = 0.842, sensitivity = 75.00%, specificity = 86.67%). Together, ML algorithms based on the morphological variation of trabecular bone can be used to predict severe MBL.

Detecting SIM Box Fraud by Using Support Vector Machine and Artificial Neural Network

2015 ◽  
Vol 74 (1) ◽  
Author(s):  
Roselina Sallehuddin ◽  
Subariah Ibrahim ◽  
Azlan Mohd Zain ◽  
Abdikarim Hussein Elmi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Support Vector Machine ◽  
Model Building ◽  
Computational Time ◽  
Support Vector ◽  
Ann Model ◽  
Svm Model ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Fraud in communication has been increasing dramatically due to the new modern technologies and the global superhighways of communication, resulting in loss of revenues and quality of service in telecommunication providers especially in Africa and Asia.  One of the dominant types of fraud is SIM box bypass fraud whereby SIM cards are used to channel national and multinational calls away from mobile operators and deliver as local calls. Therefore it is important to find techniques that can detect this type of fraud efficiently. In this paper, two classification techniques, Artificial Neural Network (ANN) and Support Vector Machine (SVM) were developed to detect this type of fraud.   The classification uses nine selected features of data extracted from Customer Database Record.  The performance of ANN is compared with SVM to find which model gives the best performance. From the experiments, it is found that SVM model gives higher accuracy compared to ANN by giving the classification accuracy of 99.06% compared with ANN model, 98.71% accuracy. Besides, better accuracy performance, SVM also requires less computational time compared to ANN since it takes lesser amount of time in model building and training.

scholarly journals Quantitative Structure – Pharmacokinetics Relationships Analysis of Basic Drugs: Volume of Distribution

2015 ◽  
Vol 18 (3) ◽  
pp. 515 ◽  
Author(s):  
Zvetanka Dobreva Zhivkova ◽  
Tsvetelina Mandova ◽  
Irini Doytchinova
Keyword(s):  
External Validation ◽  
Model Development ◽  
Predictive Ability ◽  
Structural Features ◽  
Volume Of Distribution ◽  
Pharmacokinetic Parameters ◽  
Basic Drugs ◽  
Quantitative Structure ◽  
Data Set ◽  
Rapid Discrimination

Purpose. The early prediction of pharmacokinetic behavior is of paramount importance for saving time and resources and for increasing the success of new drug candidates. The steady-state volume of distribution (VDss) is one of the key pharmacokinetic parameters required for the design of a suitable dosage regimen. The aim of the study is to propose a quantitative structure – pharmacokinetics relationships (QSPkR) for VDss of basic drugs. Methods: The data set consists of 216 basic drugs, divided to a modeling (n = 180) and external validation set (n = 36). 179 structural and physicochemical descriptors are calculated using validated commercial software. Genetic algorithm, stepwise regression and multiple linear regression are applied for variable selection and model development. The models are validated by internal and external test sets. Results: A number of significant QSPkRs are developed. The most frequently emerged descriptors are used to derive the final consensus model for VDss with good explanatory (r2 0.663) and predictive ability (q2LOO-CV 0.606 and r2pred 0.593). The model reveals clear structural features determining VDss of basic drugs which are summarized in a short list of criteria for rapid discrimination between drugs with a large and small VDss. Conclusions: Descriptors like lipophilicity, fraction ionized as a base at pH 7.4, number of cycles and fused aromatic rings, presence of Cl and F atoms contribute positively to VDss, while polarity and presence of strong electrophiles have a negative effect. This article is open to POST-PUBLICATION REVIEW. Registered readers (see “For Readers”) may comment by clicking on ABSTRACT on the issue’s contents page.

Sign in / Sign up

Export Citation Format

Share Document