Detection of Arrhythmia from ECG Signals by a Robust Approach to Outliers

The study focuses on arrhythmia detection from ECG signals, and for this aim it uses Fuzzy C-means (FCM) and Single Neuron Perceptron (SNP). FCM clustering adapted to time-series transforms ECG signals into useful features, and then SNP classifies them. We use MITBIH Arrhythmia database. The database is utilized for two experiments in the study. In the first experiment, RR intervals trimmed from the database are prepared for training the model, and in the second one ECG segments are used for real time simulation. Obtained results are compared with some other studies. According to the results, the proposed approach is good at arrhythmia detection as well as at least the studies in the literature. Lastly we interpret the results and present some studies for the future.

---

W artykule skoncentrowano się na detekcji arytmii na podstawie sygnału ECG przy wykorzystaniu pojedynczego perceptronu i algorytmu FCM. Do badań wykorzystano bazę danych MIT-BIH Arrhythmia. W artykule oceniono zastosowaną metodę, przedstawiono interpretację wyników i dalsze propozycje.