Automated analysis of ECG signals using nonlinearity and nonstationarity features fed into the MobilenetV2 CNN powered by transfer learning
Authors:
- 31 July 2025
- journal article
- research article
- Published by Springer Nature in Physical and Engineering Sciences in Medicine
- Vol. 48 (4) , 1667-1678
Abstract
Atrial fibrillation (AFB) and atrial flutter (AFL) are cardiac arrhythmias very often associated with the aggravation of other cardiac pathologies and increase the risk of stroke and heart failure. Their detection is therefore crucial. Automated analysis of the ECG signal has been suggested to assist cardiologists in the diagnosis of AFB and AFL. In this paper, a novel automated electrocardiogram (ECG) signal analysis method to aid in the detection of AFB and AFL is presented. The first step of the method consists of processing the original ECG signal. The second step carries out the classification using a modified MobileNetV2 convolutional neural network (CNN) powered by transfer learning. This CNN classifies the fed-in ECG signals into atrial fibrillation (AFB), atrial flutter (AFL), other (OTH), normal sinus rhythms (NOR), and noisy (NOI) recordings. The performance of the proposed method was assessed and scored using the Physio Net/Computing in Cardiology (CinC) 2017 dataset and the MIT-BIH Atrial Fibrillation Database (MIT-BIH). The experimental results showed that the proposed method gave an F1 score of 96.08%, sensitivity of 97.1%, specificity of 99.53%, and accuracy of 95.1% for atrial fibrillation, for the CinC 2017 dataset. For the MIT-BIH dataset, an F1 score of 99.54%, sensitivity of 99.51%, specificity of 99.64%, and accuracy of 99.5% were obtained. The results disclosed above on 2 databases prove that the proposed algorithm is efficient, robust, and can be used to assist cardiologists.Keywords
Funding Information
- Uppsala Universitet (Uppsala Universitet)
This publication has 47 references indexed in Scilit:
- A robust algorithm for white blood cell nuclei segmentationMultimedia Tools and Applications, 2022
- Over-fitting suppression training strategies for deep learning-based atrial fibrillation detectionMedical & Biological Engineering & Computing, 2021
- Kalman-based Spectro-Temporal ECG Analysis using Deep Convolutional Networks for Atrial Fibrillation DetectionJournal of Signal Processing Systems, 2020
- Passive–active integrators chaotic oscillator with anti-parallel diodes: analysis and its chaos-based encryption application to protect electrocardiogram signalsAnalog Integrated Circuits and Signal Processing, 2019
- A novel hybrid network of fusing rhythmic and morphological features for atrial fibrillation detection on mobile ECG signalsNeural Computing and Applications, 2019
- Period-doubling route to chaos, bistability and antimononicity in a jerk circuit with quintic nonlinearityInternational Journal of Dynamics and Control, 2018
- A Simple Method to Detect Atrial Fibrillation Using RR IntervalsThe American Journal of Cardiology, 2011
- Automatic Real Time Detection of Atrial FibrillationAnnals of Biomedical Engineering, 2009
- Identification of ECG Arrhythmias Using Phase Space ReconstructionLecture Notes in Computer Science, 2001
- Evidence of phase transitions in heart period dynamicsBiological Cybernetics, 1998