Sanjay Kumar Pandey; Bechoo Lal

DeepFusion-CNN: A Novel Context-aware Network for ECG-based Gender Classification

PDF (1062KB), PP.55-75

Views: 0 Downloads: 0

Author(s)

1. Department of Computer Science, Shri Jagdishprasad Jhabarmal Tibrewala University, Jhunjhunu, Rajasthan, 333010, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2026.05.04

Received: 23 Jan. 2026 / Revised: 19 Feb. 2026 / Accepted: 25 Mar. 2026 / Published: 8 Oct. 2026

Index Terms

Electrocardiogram, Gender recognition, Hybrid CNN, Pre-trained Architectures, Ensemble Learning.

Abstract

Electrocardiogram (ECG)-based gender identification, which utilizes the electrical activity of the heart, has emerged as a promising approach in biometric and healthcare applications. This study introduces DeepFusion-CNN, a context-aware fusion framework that integrates VGG-19, DenseNet-121, and ResNet-152 using a validation-driven adaptive weighting strategy to improve gender classification performance. Unlike conventional ensemble approaches that use a static averaging strategy, the proposed approach adaptively adjusts each sub-model's contribution based on its validation performance, enabling improved feature representation and classification robustness. This adaptive fusion mechanism allows better-performing models to contribute more significantly, leading to improved overall prediction accuracy compared to individual models and static fusion strategies. The ECG signals are preprocessed using band-pass filtering, followed by R-peak identification using the Pan–Tompkins algorithm. The processed signals are then segmented and converted into 225×225×3 two-dimensional images, making them suitable for transfer learning with pre-trained convolutional models. To maintain a fair evaluation, the data is partitioned on a subject basis before any augmentation, and augmentation is restricted to the training portion only. The framework is evaluated on the PTB and CYBHi datasets, achieving accuracies of 99.08% and 99.13%, respectively. Ablation test results indicate that the feature quality and classification performance are improved after preprocessing and the context-aware fusion strategy. The proposed framework shows strong potential for ECG-based gender classification and could serve as a useful foundation for future advancements in biometric systems and healthcare applications.

Cite This Paper

Sanjay Kumar Pandey, Bechoo Lal, "DeepFusion-CNN: A Novel Context-aware Network for ECG-based Gender Classification", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.18, No.5, pp. 55-75, 2026. DOI:10.5815/ijigsp.2026.05.04

Reference

[1]R. Srivastva and Y. Singh, "ECG analysis for human recognition using non-fiducial methods," IET Biometrics, vol. 8, no. 5, pp. 295–305, 2019. doi:10.1049/iet-bmt.2018.5093
[2]R. Srivastva and Y. N. Singh, "Identifying individuals using Fourier and discriminant analysis of electrocardiogram," in Mathematics and Computing. ICMC 2018. Communications in Computer and Information Science, Springer, Singapore, 2018, pp. 286–295. doi:10.1007/978-981-13-0023-3_27
[3]Z. Attia et al., "Age and sex estimation using artificial intelligence from standard 12-lead ECGs," Circulation: Arrhythmia and Electrophysiology, vol. 12, no. 9, 2019. doi:10.1161/CIRCEP.119.007284
[4]J. Cabra, D. Mendez, and L. Trujillo, "Wide machine learning algorithms evaluation applied to ECG authentication and gender recognition," in ICBEA '18: Proceedings of the 2018 2nd International Conference on Biometric Engineering and Applications, 2018, pp. 58-64. doi:10.1145/3230820.3230830
[5]Y. Hsu, J. Wang, W. Chiang, and C. Hung, "Automatic ECG-based emotion recognition in music listening," IEEE Transactions on. Affective Computing, vol. 11, no. 1, pp. 85–99, 2020. doi:10.1109/TAFFC.2017.2781732
[6]O. Kittnar, "Sex related differences in electrocardiography," Physiological Research, vol. 72, Suppl. 2, pp. S127–S135, 2023. doi: 10.33549/physiolres.934952
[7]K. Y. Halim, D. T. Nugrahadi, M. R. Faisal, R. Herteno, and I. Budiman, "Gender classification based on electrocardiogram signals using long short term memory and bidirectional long short term memory," Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, vol. 9, no. 3, pp. 606–618, 2023. doi: 10.26555/jiteki.v9i3.26354
[8]K. Siegersma et al., "Deep neural networks reveal novel sex-specific electrocardiographic features relevant for mortality risk," European Heart Journal - Digital Health, vol. 3, no. 2, pp. 245–254, 2022. doi:10.1093/ehjdh/ztac010
[9]A. Goshvarpour and A. Goshvarpour, "Gender and age classification using a new Poincaré section-based feature set of ECG," Signal, Image and Video Processing, vol. 13, no. 3, pp. 531–539, 2018. doi:10.1007/s11760-018-1379-5
[10]M. Khan et al., "Electrocardiogram based gender classification," in 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), Istanbul, Turkey, 2020, pp. 1-6. doi:10.1109/ICECCE49384.2020.9179305
[11]J. Lyle, M. Nandi, and P. Aston, "Symmetric projection attractor reconstruction: sex differences in the ECG," Frontiers in Cardiovascular Medicine, vol. 8, pp. 709457, 2021. doi:10.3389/fcvm.2021.709457
[12]S. Hicks et al., "Explaining deep neural networks for knowledge discovery in electrocardiogram analysis," Scientific Reports, vol. 11, no. 1, pp. 10949, 2021. doi:10.1038/s41598-021-90285-5
[13]J. Lopez, C. Parra, L. Gomez, and L. Trujillo, "Sex Recognition through ECG Signals aiming toward Smartphone Authentication," Applied Sciences, vol. 12, no. 13, pp. 6573, 2022. doi: 10.3390/app12136573
[14]E. Alkhammash, M. Hadjouni, and A. Elshewey, "A hybrid ensemble stacking model for gender voice recognition approach," Electronics, vol. 11, no. 11, pp. 1750, 2022. doi:10.3390/electronics11111750
[15]H. Zhang et al., "Ensemble learning based gender recognition from physiological signals," In Big Data – BigData 2018. BIGDATA 2018. Lecture Notes in Computer Science(), Springer, Cham. 2018, pp. 352–359. doi:10.1007/978-3-319-94301-5_29
[16]J. Hu, "An approach to EEG-based gender recognition using entropy measurement methods," Knowledge-Based Systems, vol. 140, pp. 134–141, 2018. doi:10.1016/j.knosys.2017.10.032
[17]P. Wang and J. Hu, "A hybrid model for EEG-based gender recognition," Cognitive Neurodynamics, vol. 13, no. 6, pp. 541–554, 2019. doi:10.1007/s11571-019-09543-y
[18]H. Mieszczanska et al., "Gender-related differences in electrocardiographic parameters and their association with cardiac events in Patients After Myocardial Infarction," The American Journal of Cardiology, vol. 101, no. 1, pp. 20–24, 2008. doi:10.1016/j.amjcard.2007.07.077
[19]M. Nakagawa et al., "Gender differences in the dynamics of terminal T wave intervals," Pacing and Clinical Electrophysiology, vol. 27, no. 6, pp. 769–774, 2004. doi: 10.1111/j.1540-8159.2004.00526.x
[20]P. Rautaharju et al., "Sex differences in the evolution of the electrocardiographic QT interval with age," Canadian Journal of Cardiology, vol. 8, no. 7, pp. 690–695, 1992.
[21]R. Khane and A. Surdi, "Gender differences in the prevalence of electrocardiogram abnormalities in the elderly : A Population Survey in India," Iranian Journal of Medical Sciences, vol. 37, no. 2, pp. 92, 2012.
[22]M. Y. Ansari et. al., “Estimating age and gender from electrocardiogram signals: A comprehensive review of the past decade,” Artificial Intelligence in Medicine, vol. 146, p. 102690, 2023. doi:10.1016/j.artmed.2023.102690
[23]N. Arif et al., "An approach to ECG-based gender recognition using random forest algorithm," Journal of Electronics Electromedical Engineering and Medical Informatics, vol. 6, no. 2, pp. 107–115, 2024. doi:10.35882/jeeemi.v6i2.363
[24]R. K. Tripathy, A. Acharya, and S. K. Choudhary, "Gender classification from ECG signal analysis using least square support vector machine," American Journal of Signal Processing, vol. 2, no. 5, pp. 145–149, 2012.
[25]H. Zacarias et al., "Gender Classification Using nonstandard ECG Signals - A Conceptual Framework of Implementation," In: IoT Technologies for HealthCare. HealthyIoT 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications. Springer, Cham, 2023, pp. 108–120. doi:10.1007/978-3-031-28663-6_9.
[26]M. Kim and S. Pan, "Deep learning based on 1-D ensemble networks using ECG for real-time user recognition," IEEE Transactions on Industrial Informatics, vol. 15, no. 10, pp. 5656–5663, 2019. doi:10.1109/TII.2019.2909730
[27]Z. Ebrahimi, M. Loni, M. Daneshtalab, and A. Gharehbaghi, "A review on deep learning methods for ECG arrhythmia classification," Expert Systems with Applications: X, vol. 7, pp. 100033, 2020. doi:10.1016/j.eswax.2020.100033
[28]Y. Ansari, O. Mourad, K. Qaraqe, and E. Serpedin, "Deep learning for ECG arrhythmia detection and classification: an overview of progress for period 2017–2023," Frontiers in Physiology, vol. 14, pp. 1246746, 2023. doi: 10.3389/fphys.2023.1246746
[29]F. Behrad and M. Abadeh, "An overview of deep learning methods for multimodal medical data mining," Expert Systems with Applications, vol. 200, pp. 117006, 2022. doi:10.1016/j.eswa.2022.117006
[30]A. Linkon, M. Labib, T.Hasan, M. Hossain, and M. Jannat, "Deep learning in prostate cancer diagnosis and Gleason grading in histopathology images: An extensive study," Informatics in Medicine Unlocked, vol. 24, pp. 100582, 2021. doi: 10.1016/j.imu.2021.100582
[31]H. Zeng et al., "DCAE: A dual conditional autoencoder framework for the reconstruction from EEG into image," Biomedical Signal Processing and Control, vol. 81, pp. 104440, 2023. doi:10.1016/j.bspc.2022.104440
[32]W. Gu, S. Bai, and L. Kong, "A review on 2D instance segmentation based on deep neural networks," Image and Vision Computing, vol. 120, pp. 104401, 2022. doi:10.1016/j.imavis.2022.104401
[33]Y. Yang et al., "A comparative analysis of eleven neural networks architectures for small datasets of lung images of COVID-19 patients toward improved clinical decisions," Computers in Biology and Medicine, vol. 139, pp. 104887, 2021. doi:10.1016/j.compbiomed.2021.104887
[34]I. Kaneko, J. Hayano, and E. Yuda, "How can gender be identified from heart rate data? Evaluation using ALLSTAR heart rate variability big data analysis," BMC Research Notes, vol. 16, no. 1, pp. 1–5, 2023. doi:10.1186/s13104-022-06270-2
[35]N. Huang et al., "The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis," In: Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences. 1998, pp. 903–995. doi:10.1098/rspa.1998.0193
[36]P. Chang and J. Wu, "A critical feature extraction by kernel PCA in stock trading model," Soft Computing, vol. 19, no. 5, pp. 1393–1408, 2015. doi:10.1007/s00500-014-1350-5
[37]M. Mansouri, M. Nounou, H. Nounou, and N. Karim, "Kernel PCA-based GLRT for nonlinear fault detection of chemical processes," Journal of Loss Prevention in the Process Industries, vol. 40, pp. 334–347, 2016. doi:10.1016/j.jlp.2016.01.011
[38]C. Cody, V. Ford, and A. Siraj, "Decision Tree Learning for Fraud Detection in Consumer Energy Consumption," in 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), Miami, FL, USA, 2015 pp. 1175–1179. doi:10.1109/ICMLA.2015.80
[39]C. Szegedy et al., "Going deeper with convolutions," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1-9. doi:10.1109/CVPR.2015.7298594
[40]V. Mayya, R. Pai, and M. Pai, "Automatic facial expression recognition using DCNN," Procedia Computer Science, vol. 93, pp. 453–461, 2016. doi:10.1016/j.procs.2016.07.233
[41]C. Wang, K. Li, Z.Wu, and Q. Zhao, " A DCNN Based Fingerprint Liveness Detection Algorithm with Voting Strategy," in Biometric Recognition. CCBR 2015. Lecture Notes in Computer Science(), Springer, 2015, vol 9428, pp. 241-249. doi:10.1007/978-3-319-25417-3_29
[42]K. Greff, R. Srivastava, J. Koutnik, B. Steunebrink, and J. Schmidhuber, "LSTM: A search space odyssey," IEEE Transactions on Neural Networks and Learning Systems, vol. 28, no. 10, pp. 2222–2232, 2017. doi:10.1109/TNNLS.2016.2582924
[43]F. Karim, S. Majumdar, H. Darabi, and S. Chen, "LSTM fully convolutional networks for time series classification," IEEE Access, vol. 6, pp. 1662–1669, 2018. doi:10.1109/ACCESS.2017.2779939
[44]M. Nandi and P. Aston, " Extracting new information from old waveforms: Symmetric projection attractor reconstruction: Where maths meets medicine," Experimental Physiology, vol. 105, no. 9, pp. 1444–1451, 2020. doi:10.1113/EP087873
[45]E. Alkeem et al., "Robust deep identification using ECG and multimodal biometrics for industrial internet of things," Ad Hoc Networks, vol. 121, pp. 102581, 2021. doi:10.1016/j.adhoc.2021.102581
[46]J. Lopez, C. Parra, and G. Forero, "A fast deep learning ECG sex identifier based on wavelet RGB image classification," Data, vol. 8, no. 6, pp. 97, 2023. doi:10.3390/data8060097
[47]I. Jekova and G. Bortolan, "Personal Verification/Identification via Analysis of the Peripheral ECG Leads: Influence of the Personal Health Status on the Accuracy," BioMed Research International, vol. 2015, pp. 1–13, 2015. doi:10.1155/2015/135676
[48]D. Jyotishi and S. Dandapat, "An LSTM-based model for person identification using ECG signal," IEEE Sensors Letters, vol. 4, no. 8, pp. 1–4, 2020. doi:10.1109/LSENS.2020.3012653
[49]Y. Li, Y. Pang, K. Wang, and X. Li, "Toward improving ECG biometric identification using cascaded convolutional neural networks," Neurocomputing, vol. 391, pp. 83–95, 2020. doi:10.1016/j.neucom.2020.01.019
[50]J. Kim, S. Kim, and S. Pan, "Personal recognition using convolutional neural network with ECG coupling image," Journal of Ambient Intelligence and Humanized Computing, vol. 11, no. 5, pp. 1923–1932, 2020. doi:10.1007/s12652-019-01401-3
[51]N. Demir, M. Kuncan, Y. Kaya, and F. Kuncan, "Multi-Layer co-occurrence matrices for person identification from ECG signals," Traitement du Signal, vol. 39, no. 2, pp. 431–440, 2022.
[52]I. Selvam, M. Madhavan, and S. K. Kumarasamy, "Detection and classification of electrocardiography using hybrid deep learning models," Hellenic Journal of Cardiology, vol. 81, pp. 75–84, 2025. doi: 10.1016/j.hjc.2024.08.011
[53]J. Pan and W. Tompkins, "A real-time QRS detection algorithm," IEEE Transactions on Biomedical Engineering, vol. BME-32, no. 3, pp. 230–236, 1985. doi:10.1109/TBME.1985.325532
[54]X. Wu, Z. Wang, B. Xu, and X. Ma, "Optimized Pan-Tompkins Based Heartbeat Detection Algorithms," in 2020 Chinese Control And Decision Conference (CCDC), Hefei, China, 2020, pp. 892-897. doi:10.1109/CCDC49329.2020.9164736
[55]J. Deng et al., "ImageNet: A large-scale hierarchical image database," in 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 2009, pp. 248-255. doi:10.1109/CVPR.2009.5206848
[56]A. Goldberger et al., "PhysioBank, PhysioToolkit, and PhysioNet : Components of a New Research Resource for Complex Physiologic Signals," Circulation, vol. 101, no. 23, pp. e215–e220, 2000. doi:10.1161/01.CIR.101.23.e215
[57]H. da Silva, A. Lourenço, A. Fred, N. Raposo, and M. Aires-de-Sousa, " Check Your Biosignals Here: A new dataset for off-the-person ECG biometrics," Computer Methods and Programs in Biomedicine, vol. 113, no. 2, pp. 503–514, 2014. doi:10.1016/j.cmpb.2013.11.017
[58]S. Kant, "From data to decision-making: utilizing decision tree for air quality monitoring in smart urban areas," International Journal of Information Technology, vol. 17, pp. 665-672, 2025. doi:10.1007/s41870-024-02208-y
[59]S. Jain and A. Saha, "Improving and comparing performance of machine learning classifiers optimized by swarm intelligent algorithms for code smell detection," Science of Computer Programming, vol. 237, pp. 103140, 2024. doi:10.1016/j.scico.2024.103140
[60]D. Kaur et al., “Race, Sex, and Age Disparities in the Performance of ECG Deep Learning Models Predicting Heart Failure,” Circulation: Heart Failure, vol.17, no.1, pp. e010879, 2024. doi:10.1161/CIRCHEARTFAILURE.123.010879
[61]S. Azam and K. Sidek, “Gender-based analysis of ECG biometric identification under different physiological conditions,” International Journal of Biometrics, vol. 17, no. 5, pp. 433-448, 2025. doi: 10.1504/IJBM.2025.148283

International Journal of Image, Graphics and Signal Processing (IJIGSP)