The impact of Negative to Positive Training Dataset Ratio on Atrial Fibrillation Classification Machine Learning Algorithms Performance
| Autor: | Dinna Yunika Hardiyanti, Siti Nurmaini, Sarifah Putri Rafflesia, Naufal Rachmatullah, Ahmad Zarkasi, Ferlita Pratiwi Arisanti, Firdaus, Andre Herviant Juliano |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
History
Computer science business.industry Atrial fibrillation Telehealth Machine learning computer.software_genre medicine.disease Logistic regression Computer Science Applications Education Algorithms performance Support vector machine Statistical classification medicine Deep neural networks Artificial intelligence business Classifier (UML) computer |
| Zdroj: | Journal of Physics: Conference Series. 1500:012131 |
| ISSN: | 1742-6596 1742-6588 |
| Popis: | With the few numbers of cardiologists in Indonesia who not evenly distributed, especially in rural areas, there has been a lot of smart telehealth specifically developed for heart monitoring using ECG. Many techniques have been developed to improve the accuracy of this device by using datasets that are mostly imbalanced, more positive data than negative. This paper presents the comparison of negative to positive training dataset ratio on atrial fibrillation classification machine learning algorithms performance. An AliveCor ECG recording dataset is train with deep neural networks, support vector machine and logistic regression as classifier with three different ratios, 1:1, 1:5 to 1:All. Results show an increase in classifier performance along with the increasing number of negative data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|