Convolutional Neural Networks for patient-specific ECG classification
| Autor: | Turker Ince, Serkan Kiranyaz, Moncef Gabbouj, Ridha Hamila |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Computer science
electrocardiography Speech recognition Feature extraction Convolutional neural network Electrocardiography medicine Humans human cardiovascular diseases heart ventricle extrasystole pathophysiology supraventricular premature beat physiologic monitoring Monitoring Physiologic Atrial Premature Complexes algorithm medicine.diagnostic_test business.industry Pattern recognition Neural Networks (Computer) Patient specific Ventricular Premature Complexes Ecg monitoring ComputingMethodologies_PATTERNRECOGNITION cardiovascular system Artificial intelligence Neural Networks Computer business artificial neural network Algorithms |
| Zdroj: | EMBC |
| ISSN: | 2694-0604 |
| Popis: | We propose a fast and accurate patient-specific electrocardiogram (ECG) classification and monitoring system using an adaptive implementation of 1D Convolutional Neural Networks (CNNs) that can fuse feature extraction and classification into a unified learner. In this way, a dedicated CNN will be trained for each patient by using relatively small common and patient-specific training data and thus it can also be used to classify long ECG records such as Holter registers in a fast and accurate manner. Alternatively, such a solution can conveniently be used for real-time ECG monitoring and early alert system on a light-weight wearable device. The experimental results demonstrate that the proposed system achieves a superior classification performance for the detection of ventricular ectopic beats (VEB) and supraventricular ectopic beats (SVEB). 2015 IEEE. Scopus |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|