Open Access Open Access  Restricted Access Subscription or Fee Access

Survey of Techniques for Clustering and Classification of ECG using WEKA

Nidhi Gupta, Prem Ranjan

Abstract


ECG analysis can be done for automatic detection of abnormality in cardiac activity. This can be helpful in generating alert for saving a precious life. Various techniques have been proposed in literature for feature detection and classification such as; fuzzy logic methods, artificial neural networks (ANN), and support vector machines (SVM), wavelet transform, Hilbert transform, etc. Recently, numerous researches and techniques have been developed for analyzing the ECG signal on WEKA platform. All these techniques and algorithms have their advantages and limitations. This proposed paper discusses various techniques and transformations proposed earlier in literature for extracting features from an ECG signal using WEKA platform. In addition, this paper also provides a comparative study of various methods proposed by researchers in extracting the features and classification of ECG signal

Keywords


ECG signal analysis, classification, WEKA, machine learning

Full Text:

PDF

References


Pawel Tadejko. Additional Data Preprocessing and Feature Extraction in Automatic Classification of Heartbeats. Technical University of Bialystok, Faculty of Computer Science, Bialystok. 2007.

Jan Bohacik, Davis Darryl N. Estimation of Cardiovascular Patient Risk with a

Bayesian Network. Transcom 2011. 27–29 Jun 2011.

WEKA (Waikato Environment for Knowledge Analysis) web site http://www.cs.waikato.ac.nz/~ml/weka/index.html

Norsys Software Corp. Netica™ Application. [http://www.norsys.com/netica.html].

Thara Soman, Bobbie Patrick O. Classification of Arrhythmia Using Machine Learning Techniques. 2004.

Makki Akasha Babikier, Mohammed Izzeldin, Ibrahim Musa Ishag, et al. Classification of Cardiac Arrhythmias using Machine Learning Techniques Based on ECG Signal Matching. 2008.

Elsayad Alaa M. Classification of ECG Arrhythmia Using Learning Vector Quantization Neural Networks. 2009.

Fahim Sufi, Ibrahim Khalil. Diagnosis of Cardiovascular Abnormalities From Compressed ECG: A Data Mining-Based

Approach. IEEE Trans Inf Technol Biomed. Jan 2011; 15(1).

Andrei Kelarev, Andrew Stranieri, John Yearwood, et al. Empirical Investigation of Consensus Clustering for Large ECG Data Sets. 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS). 2012.

Alan Jovic, Nikola Bogunovic. Analysis of ECG Records Using ECG Chaos Extractor Platform and Weka System. Proceedings of the ITI 2008 30th Int. Conf. on Information Technology Interfaces. Jun 23–26, 2008.

Alan Jovic, Nikola Bogunovic. Feature Extraction for ECG Time-Series Mining based on Chaos Theory. Proceedings of the ITI 2007 29th Int. Conf. on Information Technology Interfaces. Jun 25–28, 2007.

Alan Jovic, Nikola Bogunovic. Feature Set Extension for Heart Rate Variability Analysis by Using Non-linear, Statistical and Geometric Measures. Proceedings of the ITI 2009 31st Int. Conf. on Information Technology Interfaces. Jun 22–25, 2009.

Bashir Mohamed Ezzeldin A, Gyeong Min Yi, Minghao Piao, et al. Fine-tuning ECG

Parameters Technique for Precise Abnormalities Detection. International Conference on Bioscience, Biochemistry and Bioinformatics IPCBEE. 2011; 5.

Jensen Ulf, Matthias Ring, Bjoern Eskofier. Generic Features for Biosignal Classification. Proceedings Sportinformatik. 2012.

Robu R, Hora C. Medical Data Mining with Extended WEKA. Intelligent Engineering Systems (INES), 2012 IEEE 16th International Conference on. 2012.

Omar Al Zoubi, Calvo Rafael A, Stevens Ronald H. Classification of EEG for Affect Recognition: An Adaptive Approach. 2009 LNAI.




DOI: https://doi.org/10.37591/jomea.v3i2.5257

Refbacks

  • There are currently no refbacks.


Copyright (c) 2021 Journal of Microcontroller Engineering and Applications