A LSTM and CNN Based Assemble Neural Network Framework for Arrhythmias Classification

This paper puts forward a LSTM and CNN based assemble neural network framework to distinguish different types of arrhythmias by integrating stacked bidirectional long shot-term memory (SB-LSTM) network and two-dimensional convolutional neural network (TD-CNN). Particularly, SB-LSTM is used to mine the long-term dependencies contained in electrocardiogram (ECG) from two directions to model the overall variation trends of ECG, while TD-CNN aims at extracting local information of ECG to characterize the local features of ECG. Moreover, we design an ensemble empirical mode decomposition (EEMD) based signal decomposition layer and a support vector machine based intermediate result fusion layer, by which ECG can be analyzed more effectively, and the final classification results can be more accurate and robust. Experimental results on public INCART arrhythmia database show that our model surpasses three state-of-the-art methods, and obtains 99.1% of accuracy, 99.3% of sensitivity and 98.5% of specificity.

[1]  U. Rajendra Acharya,et al.  A deep convolutional neural network model to classify heartbeats , 2017, Comput. Biol. Medicine.

[2]  Kandala N. V. P. S. Rajesh,et al.  Classification of ECG heartbeats using nonlinear decomposition methods and support vector machine , 2017, Comput. Biol. Medicine.

[3]  Yanchun Zhang,et al.  Arrhythmias Classification by Integrating Stacked Bidirectional LSTM and Two-Dimensional CNN , 2019, PAKDD.

[4]  Maarten De Vos,et al.  Comparing feature-based classifiers and convolutional neural networks to detect arrhythmia from short segments of ECG , 2017, 2017 Computing in Cardiology (CinC).

[5]  Hua Wang,et al.  EEG Sleep Stages Analysis and Classification Based on Weighed Complex Network Features , 2021, IEEE Transactions on Emerging Topics in Computational Intelligence.

[6]  Xiuzhen Zhang,et al.  A probabilistic method for emerging topic tracking in Microblog stream , 2016, World Wide Web.

[7]  J. Bell,et al.  Medications and Prescribing Patterns as Factors Associated with Hospitalizations from Long-Term Care Facilities: A Systematic Review , 2018, Drugs & Aging.

[8]  Zhu Wang,et al.  Identification of Hypertension by Mining Class Association Rules from Multi-dimensional Features , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[9]  M. I. Owis,et al.  A novel technique for cardiac arrhythmia classification using spectral correlation and support vector machines , 2015, Expert systems with applications.

[10]  U. Rajendra Acharya,et al.  Current methods in electrocardiogram characterization , 2014, Comput. Biol. Medicine.

[11]  Reza Ebrahimpour,et al.  Classification of ECG arrhythmia by a modular neural network based on Mixture of Experts and Negatively Correlated Learning , 2013, Biomed. Signal Process. Control..

[12]  Naomie Salim,et al.  Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals , 2016, Comput. Methods Programs Biomed..

[13]  Jinyuan He,et al.  D-ECG: A Dynamic Framework for Cardiac Arrhythmia Detection from IoT-Based ECGs , 2018, WISE.

[14]  Zhu Wang,et al.  OSA-weigher: an automated computational framework for identifying obstructive sleep apnea based on event phase segmentation , 2019, J. Ambient Intell. Humaniz. Comput..

[15]  Ji Zhang,et al.  Outlier detection from large distributed databases , 2013, World Wide Web.

[16]  Zhu Wang,et al.  A light-weight data preprocessing and integrative scheduling framework for health monitoring , 2016, 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[17]  Zhu Wang,et al.  Identifying Obstructive Sleep Apnea by Exploiting Fine-Grained BCG Features Based on Event Phase Segmentation , 2016, 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering (BIBE).

[18]  Bin Zhou,et al.  Multi-window based ensemble learning for classification of imbalanced streaming data , 2015, World Wide Web.

[19]  Fevrier Valdez,et al.  A new neural network model based on the LVQ algorithm for multi-class classification of arrhythmias , 2014, Inf. Sci..

[20]  Naif Alajlan,et al.  Deep learning approach for active classification of electrocardiogram signals , 2016, Inf. Sci..

[21]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[22]  Özal Yildirim,et al.  A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification , 2018, Comput. Biol. Medicine.

[23]  Aydin Akan,et al.  Evaluation of bagging ensemble method with time-domain feature extraction for diagnosing of arrhythmia beats , 2012, Neural Computing and Applications.

[24]  H. Huikuri,et al.  Sudden death due to cardiac arrhythmias. , 2001, The New England journal of medicine.

[25]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[26]  Özal Yildirim,et al.  Face recognition based on convolutional neural network , 2017, 2017 International Conference on Modern Electrical and Energy Systems (MEES).

[27]  Jun Dong,et al.  Premature ventricular contraction detection combining deep neural networks and rules inference , 2017, Artif. Intell. Medicine.