ECG signal classification in wearable devices based on compressed domain

Wearable devices are often used to diagnose arrhythmia, but the electrocardiogram (ECG) monitoring process generates a large amount of data, which will affect the detection speed and accuracy. In order to solve this problem, many studies have applied deep compressed sensing (DCS) technology to ECG monitoring, which can under-sampling and reconstruct ECG signals, greatly optimizing the diagnosis process, but the reconstruction process is complex and expensive. In this paper, we propose an improved classification scheme for deep compressed sensing models. The framework is comprised of four modules: pre-processing; compression; and classification. Firstly, the normalized ECG signals are compressed adaptively in the three convolutional layers, and then the compressed data is directly put into the classification network to obtain the results of four kinds of ECG signals. We conducted our experiments on the MIT-BIH Arrhythmia Database and Ali Cloud Tianchi ECG signal Database to validate the robustness of our model, adopting Accuracy, Precision, Sensitivity and F1-score as the evaluation metrics. When the compression ratio (CR) is 0.2, our model has 98.16% accuracy, 98.28% average accuracy, 98.09% Sensitivity and 98.06% F1-score, all of which are better than other models.

[1]  M. Forouzanfar,et al.  Unsupervised ECG Analysis: A Review , 2022, IEEE Reviews in Biomedical Engineering.

[2]  S. Ari,et al.  A Light Weight Deep Learning based Technique for Patient-Specific ECG Beat Classification , 2022, 2022 International Conference on Recent Trends in Microelectronics, Automation, Computing and Communications Systems (ICMACC).

[3]  Paweł Pławiak,et al.  Efficient Lightweight Multimodel Deep Fusion Based on ECG for Arrhythmia Classification , 2022, Sensors.

[4]  W. Alhalabi,et al.  Machine learning algorithms for smart and intelligent healthcare system in Society 5.0 , 2022, Int. J. Intell. Syst..

[5]  A. Chakrapani,et al.  Classification of ECG signal using FFT based improved Alexnet classifier , 2022, PloS one.

[6]  Kiran Kumar Patro,et al.  A Hybrid Approach of a Deep Learning Technique for Real–Time ECG Beat Detection , 2022, Int. J. Appl. Math. Comput. Sci..

[7]  Kiran Kumar Patro,et al.  BAED: A secured biometric authentication system using ECG signal based on deep learning techniques , 2022, Biocybernetics and Biomedical Engineering.

[8]  Pawel Plawiak,et al.  Automated Detection of Myocardial Infarction and Heart Conduction Disorders Based on Feature Selection and a Deep Learning Model , 2022, Sensors.

[9]  A. J. Prakash.  Capsule Network for the Identification of Individuals Using Quantized ECG Signal Images , 2022, IEEE Sensors Letters.

[10]  Jianjun Tang,et al.  Deep Compressive Sensing on ECG Signals with Modified Inception Block and LSTM , 2022, Entropy.

[11]  Saba Zafar,et al.  The Use of Wearable ECG Devices in the Clinical Setting: a Review , 2022, Current Emergency and Hospital Medicine Reports.

[12]  Yilong Yin,et al.  Joint Dual-Domain Matrix Factorization for ECG Biometric Recognition , 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[13]  B. B. Gupta,et al.  Deep Learning Models for Arrhythmia Detection in IoT Healthcare Applications , 2022, Comput. Electr. Eng..

[14]  L. Goras,et al.  A Study on Dictionary Selection in Compressive Sensing for ECG Signals Compression and Classification , 2022, Biosensors.

[15]  Sengul Dogan,et al.  A novel Discrete Wavelet-Concatenated Mesh Tree and ternary chess pattern based ECG signal recognition method , 2022, Biomed. Signal Process. Control..

[16]  Osmar R Zaiane,et al.  Collaborative learning of graph generation, clustering and classification for brain networks diagnosis , 2022, Comput. Methods Programs Biomed..

[17]  Nirmeen A. El-Bahnasawy,et al.  Secure Health Monitoring Communication Systems Based on IoT and Cloud Computing for Medical Emergency Applications , 2021, Comput. Intell. Neurosci..

[18]  A. Majumdar,et al.  Resource Constrained CVD Classification Using Single Lead ECG On Wearable and Implantable Devices , 2021, 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

[19]  Xinwen Liu,et al.  Deep learning in ECG diagnosis: A review , 2021, Knowl. Based Syst..

[20]  Senping Tian,et al.  Effective compression and classification of ECG arrhythmia by singular value decomposition , 2021, Biomedical Engineering Advances.

[21]  V. Bajaj,et al.  Analysis of Medical Modalities for Improved Diagnosis in Modern Healthcare , 2021 .

[22]  Ru San Tan,et al.  Automated arrhythmia detection with homeomorphically irreducible tree technique using more than 10, 000 individual subject ECG records , 2021, Inf. Sci..

[23]  Daniel Freedman,et al.  ECG ODE-GAN: Learning Ordinary Differential Equations of ECG Dynamics via Generative Adversarial Learning , 2021, AAAI.

[24]  L. Goras,et al.  On the Classification of ECG and EEG Signals with Various Degrees of Dimensionality Reduction , 2021, Biosensors.

[25]  Dimitris Bertsimas,et al.  Machine Learning for Real-Time Heart Disease Prediction , 2021, IEEE Journal of Biomedical and Health Informatics.

[26]  Yining Sun,et al.  Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network , 2021, Entropy.

[27]  Edmond S. L. Ho,et al.  A Multitier Deep Learning Model for Arrhythmia Detection , 2020, IEEE Transactions on Instrumentation and Measurement.

[28]  Jaya Prakash Allam,et al.  SpEC: A system for patient specific ECG beat classification using deep residual network , 2020 .

[29]  Ridha Ouni,et al.  Electrocardiogram heartbeat classification based on a deep convolutional neural network and focal loss , 2020, Comput. Biol. Medicine.

[30]  Mengshu Hou,et al.  Multi-label Arrhythmia Classification from Fixed-length Compressed ECG Segments in Real-time Wearable ECG Monitoring , 2020, 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

[31]  Weihua Zhou,et al.  A novel method for ECG signal classification via one-dimensional convolutional neural network , 2020, Multimedia Systems.

[32]  Kira Radinsky,et al.  Improving ECG Classification Using Generative Adversarial Networks , 2020, AAAI.

[33]  Jing Hua,et al.  ECG heartbeat classification in compressive domain for wearable devices , 2020, J. Syst. Archit..

[34]  Matin Hashemi,et al.  LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices , 2018, IEEE Journal of Biomedical and Health Informatics.

[35]  Xiaodai Dong,et al.  Inter-Patient CNN-LSTM for QRS Complex Detection in Noisy ECG Signals , 2019, IEEE Access.

[36]  Bin Yao,et al.  ECG Arrhythmia Classification Using STFT-Based Spectrogram and Convolutional Neural Network , 2019, IEEE Access.

[37]  Jing Hua,et al.  A Novel ECG Heartbeat Classification Approach Based on Compressive Sensing in Wearable Health Monitoring System , 2019, 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData).

[38]  U. Rajendra Acharya,et al.  A new approach for arrhythmia classification using deep coded features and LSTM networks , 2019, Comput. Methods Programs Biomed..

[39]  Timothy Lillicrap,et al.  Deep Compressed Sensing , 2019, ICML.

[40]  Jian Wang,et al.  Patient-specific ECG classification by deeper CNN from generic to dedicated , 2018, Neurocomputing.

[41]  Mohamed Hammad,et al.  Detection of abnormal heart conditions based on characteristics of ECG signals , 2018, Measurement.

[42]  David Atienza,et al.  Real-Time Event-Driven Classification Technique for Early Detection and Prevention of Myocardial Infarction on Wearable Systems , 2018, IEEE Transactions on Biomedical Circuits and Systems.

[43]  Shoushui Wei,et al.  Performance Analysis of Ten Common QRS Detectors on Different ECG Application Cases , 2018, Journal of healthcare engineering.

[44]  Jing Hua,et al.  Direct Arrhythmia Classification from Compressive ECG Signals in Wearable Health Monitoring System , 2017, J. Circuits Syst. Comput..

[45]  Alexandros G. Dimakis,et al.  Compressed Sensing using Generative Models , 2017, ICML.

[46]  Rajendra Akerkar,et al.  Knowledge Based Systems , 2017, Encyclopedia of GIS.

[47]  Turaga Pavan,et al.  Direct classification from compressively sensed images via deep Boltzmann machine , 2016 .

[48]  S. Frick,et al.  Compressed Sensing , 2014, Computer Vision, A Reference Guide.

[49]  Wen-June Wang,et al.  QRS complexes detection for ECG signal: The Difference Operation Method , 2008, Comput. Methods Programs Biomed..

[50]  O. Pahlm,et al.  Software QRS detection in ambulatory monitoring — a review , 1984, Medical and Biological Engineering and Computing.

[51]  G.B. Moody,et al.  The impact of the MIT-BIH Arrhythmia Database , 2001, IEEE Engineering in Medicine and Biology Magazine.