Application of Classification Algorithm Based on SVM for Determining the Effectiveness of Treatment of Tuberculosis

Daineko, Yevgeniya; Duisebekova, Kulanda; Mamyrbekov, A. M.; Kozhamzharova, Dinara; Astaubayeva, Gulnar; Stamkulova, K.

doi:10.1016/j.procs.2018.04.034

Cited by 16 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Every dataset divided into 80:20 standard ratios use 80% dataset for training and 20% dataset for testing purposes by implying simple random sampling technique using "train_test_split" function available in "sklearn" (referenced in Table 2). Competitive analysis of all the existing classification methods namely: K-NN [35], Logistic Regression (LR) [34], Decision trees (DT) [36], Gaussian Naive Bayes (GNB) [38], Random Forest (RF) [37], Linear Support Vector Machine (LSVM) [40], Stochastic Gradient Descent (SGD) [39], Artificial Neural Networks (ANN) [42], eXtreme Gradient Boosting (XGBoost) referred to [41] is charted. This current section further expands into four subsections to demonstrate the results namely; Confusion Matrix Results for K value five, Result Analysis of LWGMK-NN algorithm using Cross-Validation Technique for 'K' neighbor values (1 to 5), Receiver Operating Characteristic (ROC) Curve Analysis, and finally the Competitive and Performance Analysis for model generalization.…”

Section: Resultsmentioning

confidence: 99%

Improved Clinical Diagnosis Using Predictive Analytics

N¹,

S²

2022

IEEE Access

View full text Add to dashboard Cite

The strength of Predictive analytics lies in the ability to reveal interesting patterns obscured within the data and aid the decision-making process. Predictive analytics when deployed using high-end techniques, tools, and methods plays a significant life savior role in the early detection and diagnosis of several human diseases. This research work proposes implementation of predictive analytics using a multistratified algorithm named the "Local Weight Global Mean K-Nearest Neighbor (LWGMK-NN)" algorithm under the supervised classification category built over the foundation of analytical techniques without any preset assumptions to discover insights and make predictions. We have considered ten standard clinical datasets to demonstrate the performance of the proposed work against nine state-of-the-art classification algorithms: Logistic Regression, Decision trees, Gaussian Naive Bayes, Random Forest, Linear Support Vector Machine, Stochastic Gradient Descent, Artificial Neural Networks, and XGBoost as benchmark algorithms. Experimental results shown through performance metrics obtained for simple random sampling, 5-fold cross-validation-a statistical re-sampling method, and for 5 times iterated 5-fold cross-validation techniques concludes the efficiency of the LWGMK-NN algorithm and justifies its implementation as a predictive model.

show abstract

Section: Resultsmentioning

confidence: 99%

Improved Clinical Diagnosis Using Predictive Analytics

N¹,

S²

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Big data analytics is gaining popularity in medical engineering and healthcare. Stakeholders find that big data analysis reduces health costs and personalizes health care for each individual patient [32,33]. This research argues that big data analytics can be used in large-scale genetic research, public health, personalized and accurate medicine, and new drug development.…”

Section: Developing a System For Diagnosing Diabetes Mellitus Using B...mentioning

confidence: 99%

Developing a system for diagnosing diabetes mellitus using bigdata

Mukasheva

Daineko

Astaubayeva

et al. 2022

EEJET

View full text Add to dashboard Cite

Diabetes is among the socially significant diseases, which leads to high costs for the diagnosis and treatment of diabetes. Diagnosis and treatment of diabetes is currently one of the important tasks in medicine at the present stage of development of medical services. An important direction in the development of medical services for the population is the development and implementation of various problem-oriented information systems. Similar systems developed earlier did not cover the entire amount of heterogeneous information that is collected when diagnosing and prescribing the course of diabetes treatment, nor did they use technologies and cloud services as tools for Big Data. In this article, let’s make use of the predictive analytic to forecast and categorize the type of diabetes which offers an effective method for treating and curing patients at a reduced cost, with improved results such as affordability and availability. An information system platform has been developed and configured to manage the Hadoop cluster, as well as a non-relational database that uses and processes unstructured data in various formats. All experimental research, development of methods and algorithms, as well as solving computational problems were implemented using software languages for application development. The novelty lies in the research of distributed computing models that provide efficient execution of developed algorithms using the conceptual model of the processes of search, extraction and analysis of unstructured data in large data sets. The practical implementation of algorithms was carried out on the basis of methods of object-oriented programming and object-oriented databases

show abstract

“…They used PCA and kernelized SVM algorithm and embedded system by DSP. In [32], the authors have used kernelized SVM for determining the effectiveness of treatment of tuberculosis. They used SVM to check the effectiveness of the drug.…”

Section: Related Workmentioning

confidence: 99%

WR-SVM Model Based on the Margin Radius Approach for Solving the Minimum Enclosing Ball Problem in Support Vector Machine Classification

et al. 2021

View full text Add to dashboard Cite

The generalization error of conventional support vector machine (SVM) depends on the ratio of two factors; radius and margin. The traditional SVM aims to maximize margin but ignore minimization of radius, which decreases the overall performance of the SVM classifier. However, different approaches are developed to achieve a trade-off between the margin and radius. Still, the computational cost of all these approaches is high due to the requirements of matrix transformation. Furthermore, a conventional SVM tries to set the best hyperplane between classes, and due to some robust kernel tricks, an SVM is used in many non-linear and complex problems. The configuration of the best hyperplane between classes is not effective; therefore, it is required to bind a class within its limited area to enhance the performance of the SVM classifier. The area enclosed by a class is called its Minimum Enclosing Ball (MEB), and it is one of the emerging problems of SVM. Therefore, a robust solution is needed to improve the performance of the conventional SVM to overcome the highlighted issues. In this research study, a novel weighted radius SVM (WR-SVM) is proposed to determine the tighter bounds of MEB. The proposed solution uses a weighted mean to find tighter bounds of radius, due to which the size of MEB decreases. Experiments are conducted on nine different benchmark datasets and one synthetic dataset to demonstrate the effectiveness of our proposed model. The experimental results reveal that the proposed WR-SVM significantly performed well compared to the conventional SVM classifier. Furthermore, experimental results are compared with F-SVM and traditional SVM in terms of classification accuracy to demonstrate the significance of the proposed WR-SVM.

show abstract

Application of Classification Algorithm Based on SVM for Determining the Effectiveness of Treatment of Tuberculosis

Cited by 16 publications

References 2 publications

Improved Clinical Diagnosis Using Predictive Analytics

Improved Clinical Diagnosis Using Predictive Analytics

Developing a system for diagnosing diabetes mellitus using bigdata

WR-SVM Model Based on the Margin Radius Approach for Solving the Minimum Enclosing Ball Problem in Support Vector Machine Classification

Contact Info

Product

Resources

About