ECG Arrhythmia Classification with Support Vector Machines and Genetic Algorithm

Nasiri, Jalal A.; Naghibzadeh, Mahmoud; Yazdi, Hadi Sadoghi; Naghibzadeh, Bahram

doi:10.1109/ems.2009.39

Cited by 90 publications

(31 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, selection of significant features plays a vital role in the classification, particularly when the ECG data is noisy. Current reduction/optimization methods to solve the feature reduction problem in ECG classification include Genetic Algorithm (GA) with Support Vector Machine (SVM) [5], Principal Component Analysis (PCA) with SVM, Linear Discriminant Analysis (LDA) with SVM [6], Cartesian Genetic Programming (CGP) with Neural Network (NN) [7], Firefly and Particle Swarm Optimization (FFPSO) technique with Levenberg Marquardt Neural Network (LMNN) [8]. Existing methods were tested on noise-free ECG data, which produced accurate classification results [9].…”

Section: Introductionmentioning

confidence: 99%

A Genetic Algorithm:Neural Network Wrapper Approach for Bundle Branch Block Detection

Allami¹,

Stranieri²,

Balasubramanian³

et al. 2016

2016 Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

A Genetic Algorithm:Neural Network Wrapper Approach for Bundle Branch Block Detection

Allami¹,

Stranieri²,

Balasubramanian³

et al. 2016

2016 Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

show abstract

“…They may be able to capture changes in the heart rhythm, such as sinus rhythm versus fibrillation, in which the complexes exhibit different morphologies. Some works focus on time interval features to characterize the dynamics of ECG phenomena such as QRS duration, QT interval or heart rate, defined as the number of beats per unit of time [22,23,31,46,55]. Morphological features include the coefficients of the Hermite transform, the wavelet transform or the discrete cosine transform [29,32] that aim to model the ECG beat instead of extracting features from the raw data.…”

Section: Feature Extraction and Dimensionality Reductionmentioning

confidence: 99%

“…As many features can be extracted from ECG signals, dimensionality reduction algorithms are often performed before running the classifier. Examples of dimensionality reduction techniques include PCA (linear or nonlinear) [22] or linear discriminant analysis [18]. Feature selection selects only a small subset of the most significant features in the classification.…”

Section: Feature Extraction and Dimensionality Reductionmentioning

confidence: 99%

“…Feature selection selects only a small subset of the most significant features in the classification. For this purpose, some studies include an optimization step testing different feature combinations (via an optimization algorithm such as genetic algorithm or particle swarm optimization, or statistical distribution analysis such as Gini's index) and retrieving only the relevant features for further analysis [20,22,57]. For example, Mar et al [58] performed classification between normal, ventricular, premature ventricular and fusion beats based on the idea of Llamedo & Martínez [4] to use the sequential forward floating search (SFFS) feature selection procedure.…”

Section: Feature Extraction and Dimensionality Reductionmentioning

confidence: 99%

See 1 more Smart Citation

Computational techniques for ECG analysis and interpretation in light of their contribution to medical advances

Lyon

Mincholé

Martínez

et al. 2018

J. R. Soc. Interface.

163

View full text Add to dashboard Cite

Widely developed for clinical screening, electrocardiogram (ECG) recordings capture the cardiac electrical activity from the body surface. ECG analysis can therefore be a crucial first step to help diagnose, understand and predict cardiovascular disorders responsible for 30% of deaths worldwide. Computational techniques, and more specifically machine learning techniques and computational modelling are powerful tools for classification, clustering and simulation, and they have recently been applied to address the analysis of medical data, especially ECG data. This review describes the computational methods in use for ECG analysis, with a focus on machine learning and 3D computer simulations, as well as their accuracy, clinical implications and contributions to medical advances. The first section focuses on heartbeat classification and the techniques developed to extract and classify abnormal from regular beats. The second section focuses on patient diagnosis from whole recordings, applied to different diseases. The third section presents real-time diagnosis and applications to wearable devices. The fourth section highlights the recent field of personalized ECG computer simulations and their interpretation. Finally, the discussion section outlines the challenges of ECG analysis and provides a critical assessment of the methods presented. The computational methods reported in this review are a strong asset for medical discoveries and their translation to the clinical world may lead to promising advances.

show abstract

“…Sebagian peneliti mengaplikasikan teori fuzzy untuk deteksi aritmia [9][10][11]. Kombinasi Algoritma Genetika [12] atau Particle Swarm Optimization (PSO) dengan Support Vector Machine (SVM) [7][13] [14] juga telah dikembangkan untuk pengenalan pola beat aritmia. Perbandingan beberapa metode ekstraksi fitur seperti PCA, transformasi wavelet, algoritma morfologi yang diimplementasikan dalam algoritma klasifikasi berbasis JST [15] dan SVM [16].…”

Section: Pendahuluanunclassified

Untitled

Imah¹,

Basaruddin²

2012

Jurnal Ilmu Komputer dan Informasi

View full text Add to dashboard Cite

AbstrakPengenalan pola beat dalam analisa rekaman elektrokardiogram (EKG) menjadi bagian yang penting dalam deteksi penyakit jantung terutama aritmia. Banyak metode yang dikembangkan terkait dengan pengenalan pola beat, namun sebagian besar masih mengunakan algoritma klasifikasi klasik di mana masih belum mampu mengenali outlier klasifikasi. Fuzzy Learning Vector Quantization (FLVQ) merupakan salah satu algoritma yang mampu untuk mengenali outlier klasifikasi tetapi juga memiliki kelemahan untuk sistem uji yang bukan data berkelompok. Dalam tulisan ini peneliti mengusulkan Fuzzy Wavelet LearningVector Quantization (FWLVQ), yaitu modifikasi FLVQ sehingga mampu mengatasi data crisp maupun data fuzzy dan juga memodifikasi inferensi sistemnya sebagai perpaduan model fuzzy Takagi Sugeno Kang dengan wavelet. Sinyal EKG diperoleh dari database MIT-BIH. Sistem pengenalan pola beat secara keseluruhan terbagi atas dua bagian yaitu data pra proses dan klasifikasi. Hasil percobaan diperoleh bahwa FWLVQ memiliki akurasi sebesar 90.20% untuk data yang tidak mengandung outlier klasifikasi dan 87.19% untuk data yang melibatkan outlier klasifikasi dengan rasio data uji outlier klasifikasi dengan data non-outlier sebesar 1:1. Kata Kunci: aritmia, EKG, FLVQ, fuzzy wavelet, FWLVQ AbstractThe recognition of beat pattern in analysis of recording an electrocardiogram (ECG) becomes an important detection of heart disease, especially arrhythmias. Many methods are developed related to the recognition of beat patterns, but most still use the classical classification algorithms which are still not able to identify outlier classification. Fuzzy Learning Vector Quantization (FLVQ) is one of the algorithms that can identify outlier classification but also has a weakness for test systems that are not grouped data. In this paper we propose a Fuzzy Wavelet Quantization Learning Vector (FWLVQ), which is modified so as to overcome FLVQ crisp data and fuzzy data and also modify the inference system as a combination of Takagi Sugeno Kang fuzzy model with the wavelet. ECG signal obtained from the MIT-BIH database. Beat pattern recognition system as a whole is divided into two parts: data pre-processing and classification. The experimental results obtained that FWLVQ has an accuracy 90.20% for data that does not contain outlier classification and 87.19% for the classification of data involving outlier ratio outlier test data classification with non-outlier data of 1:1.

show abstract

ECG Arrhythmia Classification with Support Vector Machines and Genetic Algorithm

Cited by 90 publications

References 15 publications

A Genetic Algorithm:Neural Network Wrapper Approach for Bundle Branch Block Detection

A Genetic Algorithm:Neural Network Wrapper Approach for Bundle Branch Block Detection

Computational techniques for ECG analysis and interpretation in light of their contribution to medical advances

Untitled

Contact Info

Product

Resources

About