Peng Ran
ABSTRACT
The classification of arrhythmia is of great significance for the prevention and treatment of heart disease. Based on the deep learning algorithm, it has excellent performance in image classification and recognition. The ECG signal is divided into two cases of abnormal interval and abnormal amplitude to perform signal image classification. The time-domain abnormal signal is directly processed into a two-dimensional image set, and the time domain information of the amplitude abnormal signal is Fourier transformed to obtain a two-dimensional time-frequency image set, and different image sets are migrated to VGG16 After the model is reduced by the PCA algorithm, it can clearly distinguish between normal ECG signals and ECG signals with abnormal intervals or amplitude abnormalities. Finally, after a fine-tuned fully connected layer, the abnormal intervals and amplitudes can be obtained. The accuracy rates of abnormal classification were 96.15% and 92.98%, respectively. After the image processing of the ECG signal, this method can effectively distinguish the abnormal signal from the normal signal.
- Arun Kumar Sangaiah, Maheswari Arumugam and Gui-Bin Bian. 2020. An intelligent learning approach for improving ECG signal classification and arrhythmia analysis. Artificial Intelligence In Medicine. http://doi.org/10.1016/j.artmed.2019.101788Google Scholar
- Selim Dilmac and Mehmet Korurek.2015.ECG heart beat classification method based on modified ABC algorithm. Applied Soft Computing. http://doi.org/10.1016/j.asoc.2015.07.010Google Scholar
- Pooja Bhardwaj, Rahul R Choudhary and Ravindra Dayama.2012. Analysis and Classification of Cardiac Arrhythmia Using ECG Signals.International Journal of Computer Applications. http://doi.org/ 10.5120/4575-6742Google Scholar
- Wisnu Jatmiko, Nulad W.P and P.Mursanto.2011. Heart Beat Classification Using Wavelet Feature Based on Neural Network.WSEAS Transaction on SystemsGoogle Scholar
- Swati Banerjee and M. Mitra. 2013.ECG beat classification based on discrete wavelet transformation and nearest neighbour classifier. Journal of Medical Engineering and Technology(4).http://doi.org/10.3109/03091902.2013.794251Google Scholar
- Fayyaz-ul-Amir Afsar Minhas and Muhammad Arif. 2008. Robust electrocardiogram (ECG) beat classification using discrete wavelet transform. Physiological Measurement(5). http://doi.org/10.1088/0967-3334/29/5/003Google Scholar
- L. G. Gamero, J. Vila and F. Palacios. 2002. Wavelet transform analysis of heart rate variability during myocardial ischaemia. Medical & Biological Engineering & Computing(1). http://doi.org/10.1007/BF02347698Google Scholar
- Daniel E. Vigo, Salvador M. Guinjoan, Mariano Scaramal and Daniel P. Cardinali. 2005. Wavelet transform shows age-related changes of heart rate variability within independent frequency components. Autonomic Neuroscience: Basic and Clinical(1). http://doi.org/10.1016/j.autneu.2005.10.004Google Scholar
- Hongtao L and Qinchuan Z. 2016. Applications of deep convolutional neural network in computer vision. Journal of Data Acquisition Processing. (01),1-17. http://doi.org/10.16337/j.1004-9037.2016.01.001Google Scholar
- Hall W Paige,,Ngatia Salome N and Van Duyne Richard P. 2011. LSPR Biosensor Signal Enhancement Using Nanoparticle-Antibody Conjugates.. The journal of physical chemistry. C, Nanomaterials and interfaces(5). http://doi.org/10.1021/jp106912pGoogle Scholar
- M.M. Al Rahhal, Yakoub Bazi, Haikel AlHichri and R.R. Yager. 2016. Deep learning approach for active classification of electrocardiogram signals. Information Sciences. http://doi.org/10.1016/j.ins.2016.01.082Google Scholar
- Özal Yildirim. 2018. A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification. Computers in Biology and Medicine. http://doi.org/10.1016/j.compbiomed.2018.03.016Google Scholar
- Ribeiro Antônio H, Ribeiro Manoel Horta, Paixão Gabriela M M, Oliveira Derick M, Gomes Paulo R, Canazart Jéssica A and Ribeiro Antonio Luiz P. 2020. Automatic diagnosis of the 12-lead ECG using a deep neural network.. Nature communications, http://doi.org/10.1038/S41467-020-15432-4Google Scholar
- U. Rajendra Acharya, Hamido Fujita, Shu Lih Oh, and Muhammad Adam.(2017).Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals. Information Sciences. http://doi.org/10.1016/j.ins.2017.06.027Google Scholar
- Nahian Ibn Hasan and Arnab Bhattacharjee. 2019. Deep Learning Approach to Cardiovascular Disease Classification Employing Modified ECG Signal from Empirical Mode Decomposition. Biomedical Signal Processing and Control. http://doi.org/10.1016/j.bspc.2019.04.005Google Scholar
- Özal Yıldırım, Paweł Pławiak, Ru-San Tan and U. Rajendra Acharya. 2018.Arrhythmia detection using deep convolutional neural network with long duration ECG signals. Computers in Biology and Medicine. http://doi.org/10.1016/j.compbiomed.2018.09.009Google Scholar
- Ulas Baran Baloglu, Muhammed Talo, Ozal Yildirim and U Rajendra Acharya. 2019.Classification of myocardial infarction with multi-lead ECG signals and deep CNN. Pattern Recognition Letters. http://doi.org/10.1016/j.patrec.2019.02.016Google Scholar
- Huang Jingshan, Chen Binqiang, Yao Bin and He Wangpeng. 2019. Ecg arrhythmia classification using stft-based spectrogram and convolutional neural network. IEEE Access, PP(99), 1-1.http://doi.org/10.1109/ACCESS.2019.2928017Google Scholar
- Shuwen Zeng, Ken-Tye Yong,,Indrajit Roy and Feng Luan. 2011. A Review on Functionalized Gold Nanoparticles for Biosensing Applications. Plasmonics(3). http://doi.org/10.1007/s11468-011-9228-1Google Scholar
- Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. Computer ScienceGoogle Scholar
- Groth D., Hartmann S., Klie S and Selbig J. 2013. Principal Components Analysis. In: Reisfeld B., Mayeno A. (eds) Computational Toxicology. Methods in Molecular Biology (Methods and Protocols), vol 930. Humana Press, Totowa, NJ. https://doi.org/10.1007/978-1-62703-059-5_22Google Scholar
- Shen Guohao,Lu Zhanghua and Wang Tao. 2021. Convolutional neural network two classification method of ECG signal. Journal of Electronic Measurement and Instrument, (2021) 35(03): 43-48Google Scholar
- Milad Salem, Shayan Taheri and Jiann-Shiun Yuan. 2018. ECG Arrhythmia Classification Using Transfer Learning from 2- Dimensional Deep CNN Features. 2018 IEEE Biomedical Circuits and Systems Conference (BioCAS), 2018, pp. 1-4. https://doi.org/ 10.1109/BIOCAS.2018.8584808Google Scholar
- Turker Ince, Serkan Kiranyaz, Levent Eren, Murant Askar and Moncef Gabbouj. 2016. Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks. in IEEE Transactions on Industrial Electronics, vol. 63, no. 11, pp. 7067-7075, (Nov. 2016). https://doi.org/ 10.1109/TIE.2016.2582729Google ScholarCross Ref
- Ganeshkumar, R. and Dr. YSKumaraswamy. 2012. Investigating cardiac arrhythmia in ecg using random forest classification. International Journal of Computer Applications, 37(4), 31-34.http://doi.org/10.5120/4599-6557Google Scholar
- Exploration of Depth Algorithm Applied to Time-Frequency Image Processing Method of ECG Signal
Recommendations
ECG Signal Denoising based on 2D-LMS Filter in Fractional Fourier Domain
IVSP '22: Proceedings of the 2022 4th International Conference on Image, Video and Signal ProcessingECG is a non-stationary electrical signal, and the process of collecting ECG signal inevitably contains various noises. This paper proposed a new method for ECG signal denoising in fractional Fourier domain. Firstly transform the signal into fractional ...
Atrial Fibrillation ECG Signal Processing for QRST Cancellation: Zero-Padding Versus Time Alignment
ANDESCON '12: Proceedings of the 2012 Andean Region International ConferenceIn non-invasive analysis of atrial fibrillation (AF), the QRST cancellation is commonly applied by using a time-aligned average over several ECG cycles. This paper proposes another technique with less illusive high frequency content into the residual ...
Time–frequency signal processing: Today and future
AbstractMost real-life signals exhibit non-stationary characteristics. Processing of such signals separately in the time-domain or in the frequency-domain does not provide sufficient information as their spectral properties change over time. ...
Comments