ECG Compression through segment matching and progressive error encoding

Brito, Maja de; Henriques, J.; Carvalho, Paulo; Ribeiro, Bernardete; Antunes, M.

doi:10.1109/iembs.2007.4352241

Cited by 2 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many studies have focused on ECG signal modelling, including those using sequential Bayesian methods [3], extended Kalman filter [4], and segment dictionary and Bezier curve approximation [5]. In the same context, Baali et al [6] proposed a new technique for electrocardiogram (ECG) signal analysis.…”

Section: Introductionmentioning

confidence: 99%

Premature Ventricular Contraction Detection Based on Chebyshev Polynomials and K Nearest Neighbours Classifier

Guendouzi¹,

Attari²

2023

View full text Add to dashboard Cite

Premature ventricular contraction (PVC) is among the most prevalent forms of arrhythmia diagnosed in clinical settings. Arrhythmias can be recognised by analysing the ECG signal. However, it takes a lot of time for cardiologists to analyse these long-term ECG signals. The fast and accurate identification of PVCs is crucial in the treatment of cardiac diseases Here; we propose a simple and promising method for detecting PVCs in long-term ECG signals.The method is based on Chebyshev polynomial coefficients and the k-nearest neighbour (KNN) classifier. The proposed approach has been experienced on the MIT-BIH Arrhythmia Database and the results of the experiments indicate high levels of accuracy, sensitivity, and specificity, with a 99.35% accuracy rate, 99.86% sensitivity rate, and 85.11% specificity rate. The results are highly pleasing, taking into account the straightforwardness of the classification system. It is possible that the suggested approach to classification could serve as an effective means of diagnosing arrhythmias.

show abstract