Using Stratified Sample and Grid Search to Improve Disease Prediction Accuracy of SVM
Autor: | Hong Mei Cui, Ming Wei Len, Yu Kai Yao, Xiaoyun Chen |
---|---|
Rok vydání: | 2013 |
Předmět: |
business.industry
Computer science General Medicine computer.software_genre Machine learning Stratified sampling Support vector machine ComputingMethodologies_PATTERNRECOGNITION Ranking SVM Kernel (statistics) Hyperparameter optimization Artificial intelligence Data mining business Focus (optics) computer |
Zdroj: | Applied Mechanics and Materials. :644-647 |
ISSN: | 1662-7482 |
Popis: | SVM (Support Vector Machine) is a powerful data mining algorithm, and is mainly used to finish classification or regression tasks. In this literature, SVM is used to conduct disease prediction. We focus on integrating with stratified sample and grid search technology to improve the classification accuracy of SVM, thus, we propose an improved algorithm named SGSVM: Stratified sample and Grid search based SVM. To testify the performance of SGSVM, heart-disease data from UCI are used in our experiment, and the results show SGSVM has obvious improvement in classification accuracy, and this is very valuable especially in disease prediction. |
Databáze: | OpenAIRE |
Externí odkaz: |