Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

An ECG classification based on modified local binary patterns: a novel approach

An ECG classification based on modified local binary patterns: a novel approach PurposeThe lack of a fast, reliable, and general electrocardiogram (ECG) classification algorithm remains a major challenge toward an ECG-only workflow for heart disease diagnosis. In this work, the feasibility of our proposed algorithm in classifying 11 different heartbeat arrhythmia is investigated.Methods and materialsEleven heartbeat classifications with a total of 30,790 heartbeats selected from 32 patients from MIT-BIH dataset were investigated to evaluate the proposed algorithm, which is based on Modified Local Binary Pattern (MLBP). The reference feature vector for each arrhythmia was extracted during the training phase by applying the LBP operator to all different ECG signals individually, and the log-likelihood operator is used to classify each signal MLBP vector and all reference feature vectors. To enhance the algorithm accuracy, two additional morphological features are investigated, which are variance and mean.ResultsThe proposed Mean–Variance Modified-LBP (MV-MLBP) algorithm was applied, and the average accuracy of 99.76 was obtained. The MV-MLBP was found to be noise resistance, while the reported accuracy was obtained using no pre-processing, such as drift cancelation and noise reduction. In the arrhythmia classification process, the MV-MLBP algorithm has recorded a noticeably high accuracy rate.ConclusionThe proposed LBP-based approach has great potential to be transmitted to the clinic. No pre-processing necessity, combined with the low computational complexity, has changed it to a fast and robust ECG classification algorithm. However, additional patient studies are necessary to optimize and validate the workflow. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Research on Biomedical Engineering Springer Journals

An ECG classification based on modified local binary patterns: a novel approach

Download PDF
14 pages

Loading next page...
 
/lp/springer-journals/an-ecg-classification-based-on-modified-local-binary-patterns-a-novel-BC0wXyD532
Publisher
Springer Journals
Copyright
Copyright © Sociedade Brasileira de Engenharia Biomedica 2021
ISSN
2446-4732
eISSN
2446-4740
DOI
10.1007/s42600-021-00165-0
Publisher site
See Article on Publisher Site

Abstract

PurposeThe lack of a fast, reliable, and general electrocardiogram (ECG) classification algorithm remains a major challenge toward an ECG-only workflow for heart disease diagnosis. In this work, the feasibility of our proposed algorithm in classifying 11 different heartbeat arrhythmia is investigated.Methods and materialsEleven heartbeat classifications with a total of 30,790 heartbeats selected from 32 patients from MIT-BIH dataset were investigated to evaluate the proposed algorithm, which is based on Modified Local Binary Pattern (MLBP). The reference feature vector for each arrhythmia was extracted during the training phase by applying the LBP operator to all different ECG signals individually, and the log-likelihood operator is used to classify each signal MLBP vector and all reference feature vectors. To enhance the algorithm accuracy, two additional morphological features are investigated, which are variance and mean.ResultsThe proposed Mean–Variance Modified-LBP (MV-MLBP) algorithm was applied, and the average accuracy of 99.76 was obtained. The MV-MLBP was found to be noise resistance, while the reported accuracy was obtained using no pre-processing, such as drift cancelation and noise reduction. In the arrhythmia classification process, the MV-MLBP algorithm has recorded a noticeably high accuracy rate.ConclusionThe proposed LBP-based approach has great potential to be transmitted to the clinic. No pre-processing necessity, combined with the low computational complexity, has changed it to a fast and robust ECG classification algorithm. However, additional patient studies are necessary to optimize and validate the workflow.

Journal

Research on Biomedical Engineering – Springer Journals

Published: Dec 1, 2021

Keywords: ECG beat classification; Local binary pattern; Variance; Mean; Data clustering

References

  • A study on ECG signal characterization and practical implementation of some ECG characterization techniques
    Appathurai, A; Carol, JJ; Raja, C; Kumar, SN; Krishnamoorthy, S
  • Support vector machine-based arrhythmia classification using reduced features of heart rate variability signal
    Asl, B; Setarehdan, SK; Mohebbi, M
  • ECG based biometric identification using one-dimensional local difference pattern
    Benouis, M; Mostefai, L; Costen, N; Regouid, M
  • Using the Wavelet Transform for T-wave alternans detection
    Boix, M
  • Fabric defect detection by Fourier analysis
    Chan, CH; Pang, G
  • A two-stage discrimination of cardiac arrhythmias using a total least squares-based prony modelling algorithm
    Chen, SW
  • Repolarization morphology in adult LQT2 carriers with borderline prolonged QTc interval
    Couderc, JP
  • ECG beat classification via deterministic learning
    Dong, X; Wang, C; Si, W
  • ECG beat classification using neuro-fuzzy network
    Engin, M
  • Cardiac arrhythmia classification using statistical and mixture modeling features of ECG signal
    GhorbaniAfkhami, R; Azarnia, G; Tinati, MA
  • ECG waveform feature extraction and its application to automated prognosis
    Jain, VK
  • Banka H, Local pattern transformation based feature extraction techniques for classification of epileptic EEG signals
    Jaiswal, AK
  • Assessment and comparison of different methods for heartbeat classification
    Jekova, I; Bortolan, G; Christov, I
  • Electrocardiogram analysis using a combination of statistical, geometric, and nonlinear heart rate variability features
    Jovic, A; Bogunovic, N
  • 1D-local binary pattern based feature extraction for classification of epileptic EEG signals
    Kaya, Y; Uyar, M; Tekin, R; Yıldırım, S
  • A novel technique for cardiac arrhythmia classification using spectral correlation and support vector machines
    Khalaf, AF; Owis, MI; Yassine, IA
  • Fabric defect segmentation using multi-channel blob detectors
    Kumar, A; Pang, G
  • Novel methodology of cardiac health recognition based on ECG signals and evolutionary-neural system
    ławiak, P
  • QRS Feature Extraction Using Linear Prediction
    Lin, KP; Chang, WH
  • Multiresolution grey scale and rotation invariant texture analysis with Local Binary Patterns
    Ojala, T; Pietikainen, M; Maenpaa, T
  • ECG beat recognition using fuzzy hybrid neural network
    Osowski, S; Linh, TH
  • Integration of type-2 fuzzy clustering and wavelet transform in a neuralnetwork based ECG classifier
    Ozbay, Y; Ceylan, R; Karlik, B
  • Advanced classification of ambulatory activities using spectral density distances and heart rate
    Rahman, HA; Ge, D; Le Faucheur, A; Prioux, J; Carrault, G
  • Classification of ECG heartbeats using nonlinear decomposition methods and support vector machine
    Rajesh Kandala, NVPS; Dhuli, R
  • T-wave alternans found in preventricular tachyarrhythmias in CCU patients using a wavelet transform-based methodology
    Romero, I
  • Chaotic based reconstructed phase space features for detecting ventricular fibrillation
    Roopaei, M
  • Vision systems for on-loom fabric inspection
    Sari-Sarraf, H; Goddard, JS
  • Assessi ng common classification methods for the identification of abnormal repolarizati on using indicators of T-wav e morphol ogy and QT interval
    Shakibfar, S; Graff, C; Ehlers, LH; Toft, E; Kanters, JK; Struijk, JJ
  • A new method to identify coronary artery disease with ECG signals and time-frequency concentrated antisymmetric biorthogonal wavelet filter bank
    Sharma, M; Rajendra, AU
  • Artificial neural networks for automatic ECG analysis
    Silipo, R; Marchesi, C
  • Automatic identification and recording of cardiac arrhythmia
    Small, M; Yu, D; Grubb, N; Simonotto, J; Fox, KAA; Harrison, RG
  • Automated analysis of ECG waveforms with atypical QRS complex morphologies
    Tafreshi, R; Jaleel, A; Lim, J; Tafreshi, L
  • A quantitative assessment of T-wave morphology in LQT1, LQT2, and healthy individuals based on Holter recording technology
    Vaglio, M
  • Mobile cloud computing for ECG telemonitoring and real-time coronary heart disease risk detection
    Venkatesan, C; Karthigaikumar, P; Satheeskumaran, S