Estimation of atrial fibrillation using arbitrary normal ECG segments based on convolutional neural networks

Kim, Hyeong-Gon; Urtnasan, Erdenebayar; Kang, Chang-Hun; Kang, Dong‐Won; Lee, Kyoung-Joung

doi:10.23919/elinfocom.2018.8330629

Cited by 1 publication

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional Neural Network (CNN) is a deep neural networks that is used to investigate the graphical pictures [34]. The standard architecture of CNN consists of four components [22]:…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

The Sensitivity of The Heart Rate Detection for Atrial Electrograms Signal

Kong¹,

Ahmad²,

Hassan³

et al. 2021

Elektrika

View full text Add to dashboard Cite

Atrial Fibrillation (AF) is the most familiar example of arrhythmia that will occur health problems such as stroke, heart failure and other complications. Globally, the number of AF patients will more than triple by 2050 worldwide. Current methods involve performing large-area ablation without knowing the exact location of key parts. The reliability of the technology can be used as a target for atrial fibrillation’s catheter ablation. The factors that leading to the onset of atrial fibrillation include the triggering factors that induce arrhythmia and the substrate that maintains the arrhythmia. The project’s aim is to create a method for identifying AF that can be used as screening tool in medical practice. The primary goals for the detection method’s design are to develop a MATLAB software program that can compare the complexity of a normal ECG signal and an AF ECG signal. Currently, this can be achieved by the ECG Signal’s R peaks and RR Interval. For AF detection, there are more R peaks and RR Intervals and it is irregular. In this research, the detection of AF is based on the heart rate (RR Intervals). For the ECG preprocessing, Pan-Tompkins Algorithm and Discrete Wavelet Transform is used to detect the sensitivity on the R peaks and RR Intervals. As a result, Discrete Wavelet Transform algorithm gives 100% sensitivity for the dataset obtained from MIT-BIH Atrial Fibrillation and MIT-BIH Arrhythmia Database.

show abstract

“…Convolutional Neural Network (CNN) is a deep neural networks that is used to investigate the graphical pictures [34]. The standard architecture of CNN consists of four components [22]:…”

Section: Convolutional Neural Networkmentioning

confidence: 99%