MBFRDH: Design of a Multimodal Bioinspired Feature Representation Deep Learning Model for Identification of Heart-Diseases

Article Sidebar

PDF
Published: Jul 25, 2023
DOI: https://doi.org/10.17762/ijritcc.v11i7s.7530
Keywords:
ECG, Classification, Diseases, Multiclass, Fourier, Cosine, iVector, Gabor, Wavelet, GRO, ILM, Scenarios

Main Article Content

Komal S. Jaisinghani
Research Scholar, Computer Science & Engineering Department, Oriental Uiversity, Indore, India
Sandeep Malik
Professor, Computer Science & Engineering Department, Oriental Uiversity, Indore, India

Abstract

Electrocardiograms (ECGs) are generated by checking different beating patterns of heart, and are widely used for identification of multiple heart-related issues. Existing deep learning models that are proposed for ECG analysis are either highly complex, or showcase lower scalability when applied to clinical scans. To overcome these issues, this text proposes design of a novel multimodal bioinspired feature representation deep learning model for identification of heart-diseases. The proposed model initially collects large-scale ECG datasets, and extracts Fourier, Cosine, iVector, Gabor, and Wavelet components. These components are given to a Grey Wolf Optimization (GWO) based feature selection model, which assists in identification of high-inter-class variance feature sets. This is done via modelling a variance-based fitness function and fusing it with an Iterative Learning Model (ILM) that use feedback-accuracy levels for optimization of selected feature sets. The extracted features are used to incrementally train a custom 1D Binary-Augmented Convolutional Neural Network (1D BACNN) that can be trained for multiclass scenarios. The BACNN Model is trained individually for each of the heart diseases. Each BACNN categorizes input ECG samples between ‘Normal’, and ‘Heart-Disease’ categories. Due to use of this binary-type classification, the proposed model is able to achieve a consistent 99.9% accuracy for multiple heart disease sets, which is found to be higher than most of the existing multiclass techniques. The model was tested for Angina, Arrhythmia, Valve disease, and Congenital heart conditions, and was observed to achieve 3.5% higher precision, 4.9% higher accuracy, with 1.2% increase is computational delay, which makes it highly suitable for real-time clinical use cases.

Article Details

How to Cite
Jaisinghani, K. S. ., & Malik, S. . (2023). MBFRDH: Design of a Multimodal Bioinspired Feature Representation Deep Learning Model for Identification of Heart-Diseases. International Journal on Recent and Innovation Trends in Computing and Communication, 11(7s), 691–700. https://doi.org/10.17762/ijritcc.v11i7s.7530
Issue
Vol. 11 No. 7s (2023)
Section
Articles

References

X. Xie, H. Liu, D. Chen, M. Shu and Y. Wang, "Multilabel 12-Lead ECG Classification Based on Leadwise Grouping Multibranch Network," in IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-11, 2022, Art no. 4004111, doi: 10.1109/TIM.2022.3164141.

Y. Li, Z. Zhang, F. Zhou, Y. Xing, J. Li and C. Liu, "Multi-Label Classification of Arrhythmia for Long-Term Electrocardiogram Signals With Feature Learning," in IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1-11, 2021, Art no. 2512611, doi: 10.1109/TIM.2021.3077667.

S. Nurmaini et al., "Beat-to-Beat Electrocardiogram Waveform Classification Based on a Stacked Convolutional and Bidirectional Long Short-Term Memory," in IEEE Access, vol. 9, pp. 92600-92613, 2021, doi: 10.1109/ACCESS.2021.3092631.

J. Malik, O. C. Devecioglu, S. Kiranyaz, T. Ince and M. Gabbouj, "Real-Time Patient-Specific ECG Classification by 1D Self-Operational Neural Networks," in IEEE Transactions on Biomedical Engineering, vol. 69, no. 5, pp. 1788-1801, May 2022, doi: 10.1109/TBME.2021.3135622.

M. Altuve and F. Hernández, "Multiclass Classification of Cardiac Rhythms on Short Single Lead ECG Recordings using Bidirectional Long Short-Term Memory Networks," in IEEE Latin America Transactions, vol. 19, no. 7, pp. 1207-1216, July 2021, doi: 10.1109/TLA.2021.9461850.

T. Pokaprakarn, R. R. Kitzmiller, R. Moorman, D. E. Lake, A. K. Krishnamurthy and M. R. Kosorok, "Sequence to Sequence ECG Cardiac Rhythm Classification Using Convolutional Recurrent Neural Networks," in IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 2, pp. 572-580, Feb. 2022, doi: 10.1109/JBHI.2021.3098662.

L. -H. Wang et al., "Three-Heartbeat Multilead ECG Recognition Method for Arrhythmia Classification," in IEEE Access, vol. 10, pp. 44046-44061, 2022, doi: 10.1109/ACCESS.2022.3169893.

A. N. Uwaechia and D. A. Ramli, "A Comprehensive Survey on ECG Signals as New Biometric Modality for Human Authentication: Recent Advances and Future Challenges," in IEEE Access, vol. 9, pp. 97760-97802, 2021, doi: 10.1109/ACCESS.2021.3095248.

E. Essa and X. Xie, "An Ensemble of Deep Learning-Based Multi-Model for ECG Heartbeats Arrhythmia Classification," in IEEE Access, vol. 9, pp. 103452-103464, 2021, doi: 10.1109/ACCESS.2021.3098986.

J. Zhang et al., "MLBF-Net: A Multi-Lead-Branch Fusion Network for Multi-Class Arrhythmia Classification Using 12-Lead ECG," in IEEE Journal of Translational Engineering in Health and Medicine, vol. 9, pp. 1-11, 2021, Art no. 1900211, doi: 10.1109/JTEHM.2021.3064675.

L. Sun, Y. Wang, Z. Qu and N. N. Xiong, "BeatClass: A Sustainable ECG Classification System in IoT-Based eHealth," in IEEE Internet of Things Journal, vol. 9, no. 10, pp. 7178-7195, 15 May15, 2022, doi: 10.1109/JIOT.2021.3108792.

X. Tang, S. Liu, P. Reviriego, F. Lombardi and W. Tang, "A Near-Sensor ECG Delineation and Arrhythmia Classification System," in IEEE Sensors Journal, vol. 22, no. 14, pp. 14217-14227, 15 July15, 2022, doi: 10.1109/JSEN.2022.3183136.

X. Peng et al., "DSCSSA: A Classification Framework for Spatiotemporal Features Extraction of Arrhythmia Based on the Seq2Seq Model With Attention Mechanism," in IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-12, 2022, Art no. 2515112, doi: 10.1109/TIM.2022.3194906.

P. Singh and A. Sharma, "Attention-Based Convolutional DenoisingAutoencoder for Two-Lead ECG Denoising and Arrhythmia Classification," in IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-10, 2022, Art no. 4007710, doi: 10.1109/TIM.2022.3197757.

T. H. Rafi and Y. WoongKo, "HeartNet: Self Multihead Attention Mechanism via Convolutional Network With Adversarial Data Synthesis for ECG-Based Arrhythmia Classification," in IEEE Access, vol. 10, pp. 100501-100512, 2022, doi: 10.1109/ACCESS.2022.3206431.

J. Lu et al., "Efficient Hardware Architecture of Convolutional Neural Network for ECG Classification in Wearable Healthcare Device," in IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 68, no. 7, pp. 2976-2985, July 2021, doi: 10.1109/TCSI.2021.3072622.

A. Bhattarai, D. Peng, J. Payne and H. Sharif, "Adaptive Partition of ECG Diagnosis Between Cloud and Wearable Sensor Net Using Open-Loop and Closed-Loop Switch Mode," in IEEE Access, vol. 10, pp. 63684-63697, 2022, doi: 10.1109/ACCESS.2022.3182704.

R. Dekimpe and D. Bol, "ECG Arrhythmia Classification on an Ultra-Low-Power Microcontroller," in IEEE Transactions on Biomedical Circuits and Systems, vol. 16, no. 3, pp. 456-466, June 2022, doi: 10.1109/TBCAS.2022.3182159.

H. NiyigenaIngabire et al., "Analysis of ECG Signals by Dynamic Mode Decomposition," in IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 5, pp. 2124-2135, May 2022, doi: 10.1109/JBHI.2021.3130275.

M. U. Zahid et al., "Robust R-Peak Detection in Low-Quality Holter ECGs Using 1D Convolutional Neural Network," in IEEE Transactions on Biomedical Engineering, vol. 69, no. 1, pp. 119-128, Jan. 2022, doi: 10.1109/TBME.2021.3088218.

A. Ukil, L. Marin, S. C. Mukhopadhyay and A. J. Jara, "AFSense-ECG: Atrial Fibrillation Condition Sensing From Single Lead Electrocardiogram (ECG) Signals," in IEEE Sensors Journal, vol. 22, no. 12, pp. 12269-12277, 15 June15, 2022, doi: 10.1109/JSEN.2022.3162691.

M. M. Farag, "A Self-Contained STFT CNN for ECG Classification and Arrhythmia Detection at the Edge," in IEEE Access, vol. 10, pp. 94469-94486, 2022, doi: 10.1109/ACCESS.2022.3204703.

Y. Huang, G. G. Yen and V. S. Tseng, "A Novel Constraint-Based Knee- Guided Neuroevolutionary Algorithm for Context-Specific ECG Early Classification," in IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 11, pp. 5394-5405, Nov. 2022, doi: 10.1109/JBHI.2022.3199377.

Q. Hua, Y. Yaqin, B. Wan, B. Chen, Y. Zhong and J. Pan, "An Interpretable Model for ECG Data Based on Bayesian Neural Networks," in IEEE Access, vol. 9, pp. 57001-57009, 2021, doi: 10.1109/ACCESS.2021.3071731.

K. Gupta, V. Bajaj and I. A. Ansari, "OSACN-Net: Automated Classification of Sleep Apnea Using Deep Learning Model and Smoothed Gabor Spectrograms of ECG Signal," in IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-9, 2022, Art no. 4002109, doi: 10.1109/TIM.2021.3132072.

M. N. Meqdad, F. Abdali-Mohammadi and S. Kadry, "Meta Structural Learning Algorithm With Interpretable Convolutional Neural Networks for Arrhythmia Detection of Multisession ECG," in IEEE Access, vol. 10, pp. 61410-61425, 2022, doi: 10.1109/ACCESS.2022.3181727.

Emma Smith, Deep Learning for Gesture Recognition and Human-Computer Interaction , Machine Learning Applications Conference Proceedings, Vol 3 2023.

E. Prabhakararao and S. Dandapat, "Multi-Scale Convolutional Neural Network Ensemble for Multi-Class Arrhythmia Classification," in IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 8, pp. 3802-3812, Aug. 2022, doi: 10.1109/JBHI.2021.3138986.

J. Li, G. Wang, M. Chen, Z. Ding and H. Yang, "Mixup Asymmetric Tri-Training for Heartbeat Classification Under Domain Shift," in IEEE Signal Processing Letters, vol. 28, pp. 718-722, 2021, doi: 10.1109/LSP.2021.3066068.

A. Ghazarian, J. Zheng, D. Struppa and C. Rakovski, "Assessing the Reidentification Risks Posed by Deep Learning Algorithms Applied to ECG Data," in IEEE Access, vol. 10, pp. 68711-68723, 2022, doi: 10.1109/ACCESS.2022.3185615.

P. Khan, P. Ranjan, Y. Singh and S. Kumar, "Warehouse LSTM-SVM-Based ECG Data Classification With Mitigated Device Heterogeneity," in IEEE Transactions on Computational Social Systems, vol. 9, no. 5, pp. 1495-1504, Oct. 2022, doi: 10.1109/TCSS.2021.3116428.

H. Yang and Z. Wei, "A Novel Approach for Heart Ventricular and Atrial Abnormalities Detection via an Ensemble Classification Algorithm Based on ECG Morphological Features," in IEEE Access, vol. 9, pp. 54757-54774, 2021, doi: 10.1109/ACCESS.2021.3071273.

H. Tesfai et al., "Lightweight Shufflenet Based CNN for Arrhythmia Classification," in IEEE Access, vol. 10, pp. 111842-111854, 2022, doi: 10.1109/ACCESS.2022.3215665.

M. Dey, N. Omar and M. A. Ullah, "Temporal Feature-Based Classification Into Myocardial Infarction and Other CVDs Merging CNN and Bi-LSTM From ECG Signal," in IEEE Sensors Journal, vol. 21, no. 19, pp. 21688-21695, 1 Oct.1, 2021, doi: 10.1109/JSEN.2021.3079241.

J. Yang and R. Yan, "A Multidimensional Feature Extraction and Selection Method for ECG Arrhythmias Classification," in IEEE Sensors Journal, vol. 21, no. 13, pp. 14180-14190, 1 July1, 2021, doi: 10.1109/JSEN.2020.3047962.

B. Fatimah, P. Singh, A. Singhal and R. B. Pachori, "Biometric Identification From ECG Signals Using Fourier Decomposition and Machine Learning," in IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-9, 2022, Art no. 4008209, doi: 10.1109/TIM.2022.3199260.

J. Xiao et al., "ULECGNet: An Ultra-Lightweight End-to-End ECG Classification Neural Network," in IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 1, pp. 206-217, Jan. 2022, doi: 10.1109/JBHI.2021.3090421.

L. -H. Wang et al., "Automated Classification Model With OTSU and CNN Method for Premature Ventricular Contraction Detection," in IEEE Access, vol. 9, pp. 156581-156591, 2021, doi: 10.1109/ACCESS.2021.3128736.

Sunil Kumar, M. ., Kumarasamy, M. ., Madhavi, N. B. ., Dhariwal, S. ., Sampath Kumar, R. ., & Oyebode, O. J. . (2023). Reinforcement Based Concrete Modelling in Commercial Buildings Using Machine Learning Simulations. International Journal of Intelligent Systems and Applications in Engineering, 11(4s), 118–126. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/2578

X. Tang and W. Tang, "An ECG Delineation and Arrhythmia Classification System Using Slope Variation Measurement by Ternary Second-Order Delta Modulators for Wearable ECG Sensors," in IEEE Transactions on Biomedical Circuits and Systems, vol. 15, no. 5, pp. 1053-1065, Oct. 2021, doi: 10.1109/TBCAS.2021.3113665.

Dr. V. Arthi. (2020). A Novel Channel Estimation Technique in MIMO-OFDM Mobile Communication Systems. International Journal of New Practices in Management and Engineering, 9(02), 08 - 14. https://doi.org/10.17762/ijnpme.v9i02.84

Z. Ahmad, A. Tabassum, L. Guan and N. M. Khan, "ECG Heartbeat Classification Using Multimodal Fusion," in IEEE Access, vol. 9, pp. 100615-100626, 2021, doi: 10.1109/ACCESS.2021.3097614.

P. Tripathi et al., "Ensemble Computational Intelligent for Insomnia Sleep Stage Detection via the Sleep ECG Signal," in IEEE Access, vol. 10, pp. 108710-108721, 2022, doi: 10.1109/ACCESS.2022.3212120.

B. -H. Kung, P. -Y. Hu, C. -C. Huang, C. -C. Lee, C. -Y. Yao and C. -H. Kuan, "An Efficient ECG Classification System Using Resource-Saving Architecture and Random Forest," in IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 6, pp. 1904-1914, June 2021, doi: 10.1109/JBHI.2020.3035191.