Multi-objective approach for support vector machine parameter optimization and variable selection in cardiovascular predictive modeling : доклад, тезисы доклада
доклад, тезисы доклада, статья из сборника материалов конференций
Библиографическое описание:Multi-objective approach for support vector machine parameter optimization and variable selection in cardiovascular predictive modeling : доклад, тезисы доклада / C. Brester [et al.]. - Текст : непосредственный // ICINCO 2018 - Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics : 15 / 15th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2018 (2018 ; 29.07 - 31.07 ; Porto). - 2018. - 1. - P. 199-205.
Аннотация:We present a heuristic-based approach for Support Vector Machine (SVM) parameter optimization and variable selection using a real-valued cooperative Multi-Objective Evolutionary Algorithm (MOEA). Due to the possibility to optimize several criteria simultaneously, we aim to maximize the SVM performance as well as minimize the number of input variables. The second criterion is important especially if obtaining new observations for the training data is expensive. In the field of epidemiology, additional model inputs mean more clinical tests and higher costs. Moreover, variable selection should lead to performance improvement of the model used. Therefore, to train an accurate model predicting cardiovascular diseases, we decided to take a SVM model, optimize its meta and kernel function parameters on a true population cohort variable set. The proposed approach was tested on the Kuopio Ischemic Heart Disease database, which is one of the most extensively characterized epidemiological databases. In our experiment, we made predictions on incidents of cardiovascular diseases with the prediction horizon of 7–9 years and found that use of MOEA improved model performance from 66.8% to 70.5% and reduced the number of inputs from 81 to about 58, as compared to the SVM model with default parameter values on the full set of variables.
Источник:ICINCO 2018 - Proceedings of the 15th International Conference on Informatics in Control, Automation and Robotics
Выпуск:1
Мероприятие:International Conference on Informatics in Control, Automation and Robotics, ICINCO 2018 (Porto, 2018 ; 29.07 - 31.07)
Номера страниц:199-205
Держатель оригинала документа:Department of Environmental and Biological Sciences,University of Eastern Finland, Institute of Computer Sciences and Telecommunication,Reshetnev Siberian State University of Science and Technology, Institute of Public Health and Clinical Nutrition,University of Eastern Finland
Количество экземпляров:
Твёрдая копия издания отсутствует в фонде библиотеки
