Skripsi
DETEKSI ATRIAL FIBRILLATION MENGGUNAKAN RECURRENT NEURAL NETWORK PADA SINYAL ELEKTROKARDIOGRAM LONG TERM
Atrial fibrillation (AF) is a heart disease characterized by an irregular heartbeat. So it can cause stroke, heart failure and even death. AF disease is the most common and mostly affects the elderly. The thing that can be done to detect AF disease is by recording an electrocardiogram (ECG) signal. The ECG has electrical recording information of the heart's activity that describes the condition of the heart's health. In this study, one of the Deep Learning methods is used, namely themethod Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM) architecture, because this method is very suitable for data related to sequential data such as ECG signals. This study classified 3 classes of ECG signals, namely normal, AF and non-AF signals on theparameters learning rate, epoch and batch size. And the results of the performance evaluation of the 3 classes of ECG signals obtained the best model with average values of accuracy, precision, sensitivity, specificity and F1 of 96.79%, 93.04%, 93.83%, 86.58%, and 89.48%.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2107004084 | T61652 | T616522021 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available