Skripsi
DETEKSI SINYAL ATRIAL FIBRILLATION PADA ELEKTROKARDIOGRAM MENGGUNAKAN CONVOLUTION NEURAL NETWORK 1-DIMENSI
Atrial fibrillation (AF) is one of the most common chronic heart diseases suffered by the elderly. AF is a potentially lethal arrhythmia that increases the risk of heart failure and stroke if not properly identified and diagnosed. Signs of AF are excessive upper atrial contraction, as well as P sine wave failure and significant irregularity of the QRS complex sequence on the electrocardiogram (ECG). Doctors need trained skills and technical knowledge to accurately explain the ECG and it also takes a long time to visually examine the ECG signal. Therefore, the development of algorithms for the automatic detection of atrial fibrillation is urgently needed. For accurate automatic detection, fast and reliable diagnosis is expected. The method used in this research is 1-Dimensional Convolution Neural Network. In this study, classification for 6 signal classes was carried out on the parameters of learning rate, batch size and epoch. The results of the performance evaluation of the classification of 6 classes of ECG signals with average values of accuracy, sensitivity, specificity, precision and F1 of 99.5%, 89.2%, 99.6%, 84.8% and 86.5%.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2107002227 | T52645 | T526452021 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available