Classification of Normal and Abnormal ECG signals using Support Vector Machine and Fourier Decomposition Method

Kumar, Ashish; Mehla, Virender Kumar; Tomar, Harshit; Kumar, Manjeet; Komaragiri, Rama

doi:10.1109/ises50453.2020.00044

Cited by 8 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resultant signals were then classified by an SVM. Kumar [9] proposed a novel method for automatic classification between normal and abnormal signals. In their framework, features were extracted by Fourier analysis and then classified by an SVM.…”

Section: Introductionmentioning

confidence: 99%

Non-Destructive Inspection of Tile Debonding by DWT and MFCC of Tile-Tapping Sound with Machine versus Deep Learning Models

Panyavaraporn,

Horkaew

2024

ECTI-CIT Transactions

View full text Add to dashboard Cite

One of the essential processes of construction quality control is tile bonding inspection. Hollows beneath tile tessellation can lead to unbounded or completely broken tiles. An interior inspector typically used a hollowsounding technique. However, it relies on skill and judgment that greatly vary among individuals. Moreover, equipment and interpretation are difficult to calibrate and standardize. This paper addresses these issues by employing machine-learning strategies for tile-tapping sound classification. Provided that a tapping signal was digitally acquired, the proposed method was fully computerized. Firstly, the signal was analyzed and its wavelets and MFCC were extracted. The corresponding spectral features were then classified by SVM, k-NN, Naïve Bayes, and Logistic Regression algorithm, in turn. The results were subsequently compared against those from a previous works that employed a deep learning strategy. It was revealed that when the proposed method was properly configured, it required much less computing resources than the deep learning based one, while being able to distinguish dull from hollow sounding tiles with 93.67% accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Non-Destructive Inspection of Tile Debonding by DWT and MFCC of Tile-Tapping Sound with Machine versus Deep Learning Models

Panyavaraporn,

Horkaew

2024

ECTI-CIT Transactions

View full text Add to dashboard Cite

show abstract

“…Many researching papers have been investigated about classification of ECG signals. A. Kumar et al classified ECG signals using FDM and support vector machine SVM [1]. Z.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Electrocardiogram Signals Using Fourier Decomposed Method Based on Deep Learning

Azmy

2022

Preprint

View full text Add to dashboard Cite

ECG is used to measure the electrical activity of the heart. In this paper, ECG is classified into normal and Atrial Fibrillation AF patients using fourier decomposition method FDM to extract features of ECG signals. FDM used for feature extraction of ECG signals because it is nonstationary signals. It is compared with fast fourier transform FFT. The steps of extracted features from ECG signals will be discussed. First absolute of FDM of ECG signals are computed. Then, one segment of 8 segments of FDM is chosen. Then absolute of discrete cosine transform DCT algorithm is obtained. After that, skewness is calculated. Deep Learning DL with bi-long short term memory BILSTM is chosen as classification method. The maximum obtained accuracy is achieved by using DL with BILSTM layer after extracting features from ECG signals using second segment of FDM which over perform on FFT or other segments. The obtained testing accuracy is 98.79%. Receiver operating characteristics (ROC) is near to 1.Area under curve AUC equals 0.9654.

show abstract

A Review on Computational Methods for Denoising and Detecting ECG Signals to Detect Cardiovascular Diseases

Tripathi

Kumar

Komaragiri

et al. 2021

Arch Computat Methods Eng

View full text Add to dashboard Cite

Classification of Normal and Abnormal ECG signals using Support Vector Machine and Fourier Decomposition Method

Cited by 8 publications

References 17 publications

Non-Destructive Inspection of Tile Debonding by DWT and MFCC of Tile-Tapping Sound with Machine versus Deep Learning Models

Non-Destructive Inspection of Tile Debonding by DWT and MFCC of Tile-Tapping Sound with Machine versus Deep Learning Models

Analysis of Electrocardiogram Signals Using Fourier Decomposed Method Based on Deep Learning

A Review on Computational Methods for Denoising and Detecting ECG Signals to Detect Cardiovascular Diseases

Contact Info

Product

Resources

About