Precise Electrocardiogram Signal Analysis Using ResNet, DenseNet, and XceptionNet Models in Autistic Children
Abstract
In autistic children, one of the important physiological aspects to be examined is the heart condition, which can be assessed through electrocardiogram (ECG) signal analysis. However, ECG signals in autistic children often contain interference in the form of noise, making the analysis process, both manual and conventional, challenging. Therefore, this study aims to analyze the ECG signals of autistic children using a classification method to distinguish between two main conditions: playing and calm conditions. A deep learning approach employing the Convolutional Neural Network (CNN) architectures was used to obtain accurate results in distinguishing the heart conditions of autistic children. The data used consists of 700 ECG signal data in each class, processed through the filtering, windowing, and augmentation stages to obtain balanced data. Three CNN architectures, ResNet, DenseNet, and XceptionNet, were tested in this study. Although these architectures are originally designed for 2D and 3D image data, modifications were made to adapt the input data structure to perform 1D data calculations. The evaluation results show that the XceptionNet model achieved the best performance, with accuracy, precision, recall, and F1-score of 97,14% each, indicating a good ability in capturing the complex patterns of ECG signals. Meanwhile, the ResNet obtained good results with 96,19% accuracy, while DenseNet performed slightly lower results with 94,76% accuracy and evaluation metrics. Overall, this study demonstrates that a deep CNN architecture based on dense connections can enhance the accuracy of ECG signal classification in autistic children.
Downloads
References
A. Miranda, C. Berenguer, I. Baixauli, and B. Roselló, “Childhood language skills as predictors of social, adaptive and behavior outcomes of adolescents with autism spectrum disorder,” Res. Autism Spectr. Disord., vol. 103, no. March, 2023, doi: 10.1016/j.rasd.2023.102143.
E. C. McCanlies et al., “Parental occupational exposure to solvents and autism spectrum disorder: An exploratory look at gene-environment interactions,” Environ. Res., vol. 228, Jul. 2023, doi: 10.1016/j.envres.2023.115769.
Z. Wu, “Challenges Encountered by Children with Autism Spectrum Disorder: from the perspective of academic performances and education service providers,” Highlights Business, Econ. Manag., vol. 4, pp. 263–271, 2022, doi: 10.54097/hbem.v4i.3500.
I. da Costa, R. B. Junqueira, D. S. Faé, L. A. P. de Souza, and C. A. A. Lemos, “Increased Risk of Dentoalveolar Trauma in Patients with Autism Spectrum Disorder: A Systematic Review with Meta-Analysis,” Int. J. Environ. Res. Public Health, vol. 21, no. 12, 2024, doi: 10.3390/ijerph21121563.
C. Bosetti, L. Ferrini, A. R. Ferrari, E. Bartolini, and S. Calderoni, “Children with Autism Spectrum Disorder and Abnormalities of Clinical EEG: A Qualitative Review,” J. Clin. Med., vol. 13, no. 1, 2024, doi: 10.3390/jcm13010279.
A. Bellato, I. Arora, P. Kochhar, D. Ropar, C. Hollis, and M. J. Groom, “Heart Rate Variability in Children and Adolescents with Autism, ADHD and Co-occurring Autism and ADHD, During Passive and Active Experimental Conditions,” J. Autism Dev. Disord., vol. 52, no. 11, pp. 4679–4691, Nov. 2022, doi: 10.1007/s10803-021-05244-w.
A. Ullah, S. U. Rehman, S. Tu, R. M. Mehmood, Fawad, and M. Ehatisham-Ul-haq, “A hybrid deep CNN model for abnormal arrhythmia detection based on cardiac ECG signal,” Sensors (Switzerland), vol. 21, no. 3, pp. 1–13, Feb. 2021, doi: 10.3390/s21030951.
C. N. Nurbadriani, M. Melinda, Y. Yunidar, and F. Arnia, “Electrocardiogram Detection System of Autistic Children Based on AD8232 for Healthcare,” in Proceeding - 2023 2nd International Conference on Computer System, Information Technology, and Electrical Engineering: Sustainable Development for Smart Innovation System, COSITE 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 126–131. doi: 10.1109/COSITE60233.2023.10250117.
D. Tilwani, J. Bradshaw, A. Sheth, and C. O’Reilly, “ECG Recordings as Predictors of Very Early Autism Likelihood: A Machine Learning Approach,” Bioengineering, vol. 10, no. 7, Jul. 2023, doi: 10.3390/bioengineering10070827.
S. Suganyadevi, V. Seethalakshmi, and K. Balasamy, “A review on deep learning in medical image analysis,” Int. J. Multimed. Inf. Retr., vol. 11, no. 1, pp. 19–38, 2022, doi: 10.1007/s13735-021-00218-1.
Frasch, M. G., Shen, C., Wu, H.-T., Müller, A., Neuhaus, E., Bernier, R. A., Kamara, D., & Beauchaine, T. P. (2021). Can a composite heart rate variability biomarker shed new insights about autism spectrum disorder in school-aged children? Journal of Autism and Developmental Disorders, 51(1), 346–356. https://doi.org/10.1007/s10803-020-04467-7.
L. Billeci et al., “Heart rate variability during a joint attention task in toddlers with autism spectrum disorders,” Front. Physiol., vol. 9, no. MAY, pp. 1–11, 2018, doi: 10.3389/fphys.2018.00467.
A. Q. Alban et al., “Heart Rate as a Predictor of Challenging Behaviours among Children with Autism from Wearable Sensors in Social Robot Interactions,” Robotics, vol. 12, no. 2, 2023, doi: 10.3390/robotics12020055.
M. Ashtiyani, S. Navaei Lavasani, A. Asgharzadeh Alvar, and M. R. Deevband, “Heart rate variability classification using support vector machine and genetic algorithm,” J. Biomed. Phys. Eng., vol. 8, no. 4, pp. 423–434, 2018, doi: 10.31661/jbpe.v0i0.614.
F. Khan, X. Yu, Z. Yuan, and A. ur Rehman, “ECG classification using 1-D convolutional deep residual neural network,” PLoS One, vol. 18, no. 4 April, Apr. 2023, doi: 10.1371/journal.pone.0284791.
G. Husain, A. Siddiqua, and M. Toma, “Evaluating the Performance of DenseNet in ECG Report Automation,” Electron., vol. 14, no. 9, May 2025, doi: 10.3390/electronics14091837.
Y. Gotmare, “A Comparative Study of Feature Extraction Models for Image Caption Generation,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 12, no. 4, pp. 4821–4828, 2024, doi: 10.22214/ijraset.2024.61114.
Z. Wang, Z. Zheng, D. Song, and X. Xu, “A High-Speed Train Axle Box Bearing Fault Diagnosis Method Based on Dimension Reduction Fusion and the Optimal Bandpass Filtering Demodulation Spectrum of Multi-Dimensional Signals,” Machines, vol. 12, no. 8, Aug. 2024, doi: 10.3390/machines12080571.
L. J. Gonçales, K. Farias, L. Kupssinskü, and M. Segalotto, “The effects of applying filters on EEG signals for classifying developers’ code comprehension,” J. Appl. Res. Technol., vol. 19, no. 6, pp. 584–602, Dec. 2021, doi: 10.22201/icat.24486736e.2021.19.6.1299.
T. N. A. M. A. I. A. A. and W. A. Saleh Albahli, “AEI-DNET: A Novel DenseNet Model with an Autoencoder forthe Stock Market Predictions Using Stock Technical Indicators,” Electronics, 2022.
W. Li and J. Gao, “Automatic sleep staging by a hybrid model based on deep 1D-ResNet-SE and LSTM with single-channel raw EEG signals,” PeerJ Comput. Sci., vol. 9, 2023, doi: 10.7717/peerj-cs.1561.
A. A. Fedotov, “Selection of Parameters of Bandpass Filtering of the ECG Signal for Heart Rhythm Monitoring Systems,” Biomed. Eng. (NY)., vol. 50, no. 2, pp. 114–118, 2016, doi: 10.1007/s10527-016-9600-8.
B. Salsekar, “FILTERING OF ECG SIGNAL USING BUTTERWORTH FILTER AND ITS FEATURE EXTRACTION.” [Online]. Available: http://www.physionet.org/cgi-bin/atm/ATM
P. K. Govarthan, S. K. Peddapalli, N. Ganapathy, and J. F. A. Ronickom, “Emotion classification using electrocardiogram and machine learning: A study on the effect of windowing techniques,” Expert Syst. Appl., vol. 254, Nov. 2024, doi: 10.1016/j.eswa.2024.124371.
N. P. Martono and H. Ohwada, “Evaluating the Impact of Windowing Techniques on Fourier Transform-Preprocessed Signals for Deep Learning-Based ECG Classification,” Hearts, vol. 5, no. 4, pp. 501–515, Oct. 2024, doi: 10.3390/hearts5040037.
H. Siswono, W. Widyastuti, Y. Dovan, and D. Nur’ainingsih, “Design of Fir Digital Bandpass Filter with Hamming Window and Hanning Window Method for Fetal Doppler,” J. Ilm. Tek. Elektro Komput. dan Inform., vol. 9, no. 4, pp. 912–926, Oct. 2023, doi: 10.26555/jiteki.v9i4.26849.
A. Pant, A. Kumar, C. Verma, and Z. Illés, “Comparative exploration on EEG signal filtering using window control methods,” Results Control Optim., vol. 17, Dec. 2024, doi: 10.1016/j.rico.2024.100485.
A. Kebaili, J. Lapuyade-Lahorgue, and S. Ruan, “Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review,” Apr. 01, 2023, MDPI. doi: 10.3390/jimaging9040081.
Y. Dai, Y. Gao, and F. Liu, “Transmed: Transformers advance multi-modal medical image classification,” Diagnostics, vol. 11, no. 8, Aug. 2021, doi: 10.3390/diagnostics11081384.
K. Munadi et al., “A Deep Learning Method for Early Detection of Diabetic Foot Using Decision Fusion and Thermal Images,” Appl. Sci., vol. 12, no. 15, Aug. 2022, doi: 10.3390/app12157524.
F. L. Becerra-Suarez, H. Alvarez-Vasquez, and M. G. Forero, “Improvement of Bank Fraud Detection Through Synthetic Data Generation with Gaussian Noise,” Technologies, vol. 13, no. 4, 2025, doi: 10.3390/technologies13040141.
W. Ge, P. Lalbakhsh, L. Isai, A. Lensky, and H. Suominen, “Comparing Deep Learning Models for the Task of Volatility Prediction Using Multivariate Data,” Jun. 2023, [Online]. Available: http://arxiv.org/abs/2306.12446
P. C. Chang, Y. S. Chen, and C. H. Lee, “MS-SincResNet: Joint learning of 1D and 2D kernels using multi-scale SincNet and ResNet for music genre classification,” in ICMR 2021 - Proceedings of the 2021 International Conference on Multimedia Retrieval, Association for Computing Machinery, Inc, Aug. 2021, pp. 29–36. doi: 10.1145/3460426.3463619.
S. U. Kim and J. Y. Kim, “Improving Human Activity Recognition Through 1D-ResNet: A Wearable Wristband for 14 Workout Movements,” Processes, vol. 13, no. 1, Jan. 2025, doi: 10.3390/pr13010207.
M. M. A. Rahhal, Y. Bazi, H. Alhichri, N. Alajlan, F. Melgani, and R. R. Yager, “Deep learning approach for active classification of electrocardiogram signals,” Inf. Sci. (Ny)., vol. 345, pp. 340–354, 2016, doi: 10.1016/j.ins.2016.01.082.
A. A. Laghari, Y. Sun, M. Alhussein, K. Aurangzeb, M. S. Anwar, and M. Rashid, “Deep residual-dense network based on bidirectional recurrent neural network for atrial fibrillation detection,” Sci. Rep., vol. 13, no. 1, Dec. 2023, doi: 10.1038/s41598-023-40343-x.
A. Ayad and M. E. Abdulmunim, “Detecting Abnormal Driving Behavior Using Modified DenseNet,” Iraqi J. Comput. Sci. Math., vol. 4, no. 3, pp. 48–65, 2023, doi: 10.52866/ijcsm.2023.02.03.005.
F. Saleem, Z. Ahmad, M. F. Siddique, M. Umar, and J. M. Kim, “Acoustic Emission-Based Pipeline Leak Detection and Size Identification Using a Customized One-Dimensional DenseNet,” Sensors, vol. 25, no. 4, Feb. 2025, doi: 10.3390/s25041112.
A. Tibrewal, Shikha, and D. Sethia, “The Effectiveness of Advance Deep Learning Architectures for Classification of Stress using Raw EEG Data,” in 2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/APCIT62007.2024.10673521.
I. Vallés-Pérez, J. Gómez-Sanchis, M. Martínez-Sober, J. Vila-Francés, A. J. Serrano-López, and E. Soria-Olivas, “End-to-end Keyword Spotting using Xception-1d,” Oct. 2021, [Online]. Available: http://arxiv.org/abs/2110.07498
H. Xu, “Users’ perceptions of managerial measurements for cloud computing’s cybersecurity – importance-performance analysis,” Inf. Comput. Secur., vol. ahead-of-p, no. ahead-of-print, Jan. 2025, doi: 10.1108/ICS-12-2023-0264.
S. Szeghalmy and A. Fazekas, “A Comparative Study of the Use of Stratified Cross-Validation and Distribution-Balanced Stratified Cross-Validation in Imbalanced Learning,” Sensors, vol. 23, no. 4, 2023, doi: 10.3390/s23042333.
Copyright (c) 2025 Yunidar Yunidar, Melinda Melinda, Al Bahri, Hanum Aulia Ramadhani, Herlina Dimiati
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
