Autonomous detection of heartbeats and categorizing them by using Support Vector Machines

Yazdanian, Hassan; Nomani, Ashkan; Yazdchi, Mohammadreza

doi:10.1109/icbme.2013.6782223

Cited by 11 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yazdanian et al [10] considered only five classes. Important points of each segmented heartbeat have been derived and then IET Signal Process., 2018, Vol.…”

Section: Related Workmentioning

confidence: 99%

“…(iv) Regarding the description of the heartbeats, different features have been investigated including high-order statistics features [21,22], Hermite coefficients [21,23,24], linear discriminates [25][26][27] and wavelet features [2,3,28]. (v) Different classification algorithms have been utilised successfully such as: artificial neural network [24,28], decision trees [21], self-organising map [23] and SVM [2,[10][11][12]16]. (vi) Although lead 1 and 2 record ECG from different positions, which means they do not provide the same information, the existing studies except [2] have utilised information from only one lead and neglected the other.…”

Section: Related Workmentioning

confidence: 99%

“…As previously mentioned in Section 2, the MIT-BIH database [20] is the most popular database utilised by the existing studies [2,[9][10][11][12][13][14][15][16] for training and testing purposes. The MIT-BIH database consists of 48 records, each of them is a 30 min long sample with a sampling frequency of 360 Hz but according to the ANSI/AAMI EC57: 1998 standard [29], only 44 records can be utilised as there are four paced records.…”

Section: Datasetmentioning

confidence: 99%

“…One versus all is the strategy applied in most of the previous work [2,[10][11][12]16]. In this work, there is only one SVM to classify the five categories in the first stage and then in the second classification stage there is one SVM to classify the classes of each category.…”

Section: One Versus Allmentioning

confidence: 99%

“…Moreover, arrhythmias needs accurate and early detection, especially the life threatening types [9]. Thus, the automation of ECG investigation is a very demanding issue [10,11] which has resulted in a lot of publications [2,[9][10][11][12][13][14][15][16][17][18][19] with promising results. However, most of the existing studies consider only a few arrhythmia classes.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Hybrid hierarchical method for electrocardiogram heartbeat classification

El-Saadawy

Tantawi

Shedeed

et al. 2018

IET signal process.

View full text Add to dashboard Cite

This paper proposes an automatic reliable two-stage hybrid hierarchical method for ECG heartbeat classification. The heartbeats are segmented dynamically to avoid the consequences of the heart rate variability. Discrete Wavelet Transform (DWT) is utilized to extract morphological features. The extracted features are then reduced by using Principle Component Analysis (PCA). Subsequently, the resulted features along with four RR features are fed into Support Vector Machine (SVM) to classify five categories. Thereafter, the heartbeats are further classified to one of the classes belonging to the assigned category. Two different strategies for classification have been investigated: One versus All and One versus One. The proposed method has been applied on data from lead 1 and lead 2. A new fusion step is introduced, where stacked generalisation algorithm is applied and different types of classifiers have been examined. Experiments have been carried out using a MIT_BIH database. The best overall and average accuracies obtained by the first stage are 98.40% and 97.50% respectively. For the second stage, 94.94% and 93.19% are the best overall and average accuracies obtained respectively. The best results are achieved using SVM with one versus one classification strategy for both stages and decision trees classifier for the fusion step.

show abstract

“…Yazdanian et al [10] considered only five classes. Important points of each segmented heartbeat have been derived and then IET Signal Process., 2018, Vol.…”

Section: Related Workmentioning

confidence: 99%