journal article·2025-08-24Open access

Hybrid CNN-Fuzzy Approach for Automatic Identification of Ventricular Fibrillation and Tachycardia

Azeddine Mjahad, Alfredo Rosado-Muñoz

Applied Sciences· Volume 15· Issue 17

Abstract

Ventricular arrhythmias such as ventricular fibrillation (VF) and ventricular tachycardia (VT) are among the leading causes of sudden cardiac death worldwide, making their timely and accurate detection a critical task in modern cardiology. This study presents an advanced framework for the automatic detection of critical cardiac arrhythmias—specifically ventricular fibrillation (VF) and ventricular tachycardia (VT)—by integrating deep learning techniques with neuro-fuzzy systems. Electrocardiogram (ECG) signals from the MIT-BIH and AHA databases were preprocessed through denoising, alignment, and segmentation. Convolutional neural networks (CNNs) were employed for deep feature extraction, and the resulting features were used as input for various fuzzy classifiers, including Fuzzy ARTMAP and the Adaptive Neuro-Fuzzy Inference System (ANFIS). Among these classifiers, ANFIS demonstrated the best overall performance. The combination of CNN-based feature extraction with ANFIS yielded the highest classification accuracy across multiple cardiac rhythm types. The classification performance metrics for each rhythm type were as follows: for Normal Sinus Rhythm, precision was 99.09%, sensitivity 98.70%, specificity 98.89%, and F1-score 98.89%. For VF, precision was 95.49%, sensitivity 96.69%, specificity 99.10%, and F1-score 96.09%. For VT, precision was 94.03%, sensitivity 94.26%, specificity 99.54%, and F1-score 94.14%. Finally, for Other Rhythms, precision was 97.74%, sensitivity 97.74%, specificity 99.40%, and F1-score 97.74%. These results demonstrate the strong generalization capability and precision of the proposed architecture, suggesting its potential applicability in real-time biomedical systems such as Automated External Defibrillators (AEDs), Implantable Cardioverter Defibrillators (ICDs), and advanced cardiac monitoring technologies.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: ECG Monitoring and Analysis

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

GDDP, Department Electronic Engineering, School of Engineering, University of Valencia, Burjassot, 46100 Valencia, Spain

References (53)

Show source-provided references
1. Causes of sudden cardiac death in young Australians10.5694/j.1326-5377.2004.tb05830.x ↗
2. Ventricular fibrillation of long duration abolished by electric shock10.1001/jama.1947.62890150005007a ↗
3. Automatic External Defibrillators for Public Access Defibrillation: Recommendations for Specifying and Reporting Arrhythmia Analysis Algorithm Performance, Incorporating New Waveforms, and Enhancing Safety: A Statement for Health Professionals From the American Heart Association Task Force on Automatic External Defibrillation, Subcommittee on AED Safety and Efficacy10.1161/01.CIR.95.6.1677 ↗
4. Does the choice of definition for defibrillation and CPR success impact the predictability of ventricular fibrillation waveform analysis?10.1016/j.resuscitation.2016.11.022 ↗
5. Amann, A., Tratnig, R., and Unterkofler, K. (2005). Reliability of Old and New Ventricular Fibrillation Detection Algorithms for Automated External Defibrillators. BioMed. Eng. OnLine, 4.10.1186/1475-925X-4-60 ↗
6. The controversial role of dual sequential defibrillation in shockable cardiac arrest10.1016/j.ajem.2018.05.078 ↗
7. Residual Deconvolutional Networks for Brain Electron Microscopy Image Segmentation10.1109/TMI.2016.2613019 ↗
8. Providing an Efficient Algorithm for Finding R Peaks in ECG Signals and Detecting Ventricular Abnormalities With Morphological Features10.4103/2228-7477.195090 ↗
9. Real Time Detection of Ventricular Fibrillation and Tachycardia10.1088/0967-3334/25/5/007 ↗
10. Efficient classification of ventricular arrhythmias using feature selection and C4.5 classifier10.1016/j.bspc.2018.04.005 ↗
11. Machine Learning-Based Left Ventricular Hypertrophy Detection Using Multi-Lead ECG Signal10.1007/s00521-020-05238-2 ↗
12. Using Bayesian decision for ontology mapping10.1016/j.websem.2006.06.001 ↗
13. Kuzilek, J., Kremen, V., Soucek, F., and Lhotska, L. (2014). Independent Component Analysis and Decision Trees for ECG Holter Recording De-Noising. PLoS ONE, 9.10.1371/journal.pone.0098450 ↗
14. Adopting a Neuro-Fuzzy Logic Method for Fall Armyworm Detection and Monitoring Using C-Band Polarimetric Doppler Weather Radar With Field Verification10.1109/TGRS.2024.3395281 ↗
15. Research on long term power load grey combination forecasting based on fuzzy support vector machine10.1016/j.compeleceng.2024.109205 ↗
16. EOG Region Detection using Fuzzy k-NN for Virtual Reality Applications
17. Basha, M.G., Chenchireddy, K., Ahmed Sydu, S., Sultana, W., Kumar, V., and Ganesh, L.B. (2024, January 3–4). Performance Improvement of DC Motor by using ANFIS Controller. Proceedings of the 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN), Salem, India.10.1109/ICPCSN62568.2024.00157 ↗
18. A new Takagi–Sugeno–Kang model for time series forecasting10.1016/j.engappai.2024.108155 ↗
19. Lu, J., Tan, L., and Jiang, H. (2021). Review on Convolutional Neural Network (CNN) Applied to Plant Leaf Disease Classification. Agriculture, 11.10.3390/agriculture11080707 ↗
20. Guan, S., Kamona, N., and Loew, M. (2018, January 9–11). Segmentation of Thermal Breast Images Using Convolutional and Deconvolutional Neural Networks. Proceedings of the 2018 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), Washington, DC, USA.10.1109/AIPR.2018.8707379 ↗
21. DCCMED-Net: Densely connected and concatenated multi Encoder-Decoder CNNs for retinal vessel extraction from fundus images10.1016/j.mehy.2019.109426 ↗
22. Inspecting Method for Defective Casting Products with Convolutional Neural Network (CNN)10.1007/s40684-020-00197-4 ↗
23. Automatic Tuning of Hyperparameters Using Bayesian Optimization10.1007/s12530-020-09345-2 ↗
24. Young, S.R., Rose, D.C., Karnowski, T.P., Lim, S.H., and Patton, R.M. (2015, January 15). Optimizing Deep Learning Hyper-Parameters through an Evolutionary Algorithm. Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments (MLHPC ’15), Austin, TX, USA.10.1145/2834892.2834896 ↗
25. A new hyperparameters optimization method for convolutional neural networks10.1016/j.patrec.2019.02.009 ↗
26. Optimal hyperparameter tuning of convolutional neural networks based on the parameter-setting-free harmony search algorithm10.1016/j.ijleo.2018.07.044 ↗
27. RSigELU: A nonlinear activation function for deep neural networks10.1016/j.eswa.2021.114805 ↗
28. Integration of residual network and convolutional neural network along with various activation functions and global pooling for time series classification10.1016/j.neucom.2019.08.023 ↗
29. AutoFCL: Automatically tuning fully connected layers for handling small dataset10.1007/s00521-020-05549-4 ↗
30. Dahl, G.E., Sainath, T.N., and Hinton, G.E. (2013, January 26–31). Improving deep neural networks for LVCSR using rectified linear units and dropout. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada.10.1109/ICASSP.2013.6639346 ↗
31. Impact of training set batch size on the performance of convolutional neural networks for diverse datasets
32. PSO based Hyperparameter tuning of CNN Multivariate Time-Series Analysis10.15575/join.v7i2.858 ↗
33. Zeiler, M.D. (2012). Adadelta: An adaptive learning rate method. arXiv.
34. Gulcehre, C., Moczulski, M., and Bengio, Y. (2014). Adasecant: Robust adaptive secant method for stochastic gradient. arXiv.
35. A new approach to online training for the Fuzzy ARTMAP artificial neural network10.1016/j.asoc.2021.107936 ↗
36. (2023, June 14). PhysioNet. Available online: http://physionet.org.
37. (2023, June 14). American Heart Association ECG Database. Available online: http://ecri.org.
38. Kaur, M., Singh, B. (2011, January 25–26). Comparison of different approaches for removal of baseline wander from ECG signal. Proceedings of the International Conference & Workshop on Emerging Trends in Technology (ICWET ’11), Mumbai, India.10.1145/1980022.1980307 ↗
39. Removal of baseline wander and power line interference from ECG signal-a survey approach
40. Ventricular Fibrillation and Tachycardia detection from surface ECG using time-frequency representation images as input dataset for machine learning10.1016/j.cmpb.2017.02.010 ↗
41. Labatut, V., and Cherifi, H. (2012). Accuracy measures for the comparison of classifiers. arXiv.
42. Automatic histologically-closer classification of skin lesions10.1016/j.compmedimag.2018.05.004 ↗
43. Mjahad, A., Saban, M., Azarmdel, H., and Rosado-Muñoz, A. (2023). Efficient Extraction of Deep Image Features Using a Convolutional Neural Network (CNN) for Detecting Ventricular Fibrillation and Tachycardia. J. Imaging, 9.10.3390/jimaging9090190 ↗
44. Mjahad, A., Frances-Villora, J.V., Bataller-Mompean, M., and Rosado-Muñoz, A. (2022). Ventricular Fibrillation and Tachycardia Detection Using Features Derived from Topological Data Analysis. Appl. Sci., 12.10.3390/app12147248 ↗
45. Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neural network10.1016/j.future.2017.08.039 ↗
46. Buscema, P.M., Grossi, E., Massini, G., Breda, M., and Della Torre, F. (2020). Computer aided diagnosis for atrial fibrillation based on new artificial adaptive systems. Comput. Methods Programs Biomed., 191.10.1016/j.cmpb.2020.105401 ↗
47. Automated diagnosis of atrial fibrillation ECG signals using entropy features extracted from flexible analytic wavelet transform10.1016/j.bbe.2018.04.004 ↗
48. Detection of life-threatening arrhythmias using feature selection and support vector machines
49. Life-threatening ventricular arrhythmia detection with personalized features10.1109/ACCESS.2017.2723258 ↗
50. Ventricular fibrillation and tachycardia classification using a machine learning approach
51. Detection of ventricular tachycardia and fibrillation using adaptive variational mode decomposition and boosted-CART classifier10.1016/j.bspc.2017.07.031 ↗
52. Role of artificial intelligence in defibrillators: A narrative review10.1136/openhrt-2022-001976 ↗
53. Predicting defibrillation success by ‘genetic’programming in patients with out-of-hospital cardiac arrest10.1016/S0300-9572(03)00030-3 ↗