A Comparison of Similarity Measures for Clustering of QRS Complexes

Chang, Kai‐Chih; Cheng, Wen; Yeh, Ming‐Feng; Lee, Ren-Guey

doi:10.4015/s1016237205000482

Cited by 5 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Along with L1, the L2 distance (both normalized with the (p2pXbeat/p2pXcentr) factor) has also been calculated and these two features, combined with the centroid-to-beat correlation coefficient, have been the main features for the similarity evaluation of the QRST complex under investigation. The significance of these selected features has been suggested by the good results obtained using K-means with the signal representation F 3 and by previous studies (Morales et al 1997, Chang et al 2005.…”

Section: Clustering By a Two-phase Ad Hoc Algorithmmentioning

confidence: 98%

“…These problems may be insignificant when only a few features of the ECG are used, but they become quite serious when the number of features becomes large. Chang et al (2005) compared the L1 and L2 distances, the normalized cross correlation and the simplified gray relational grade (SGRG) as similarity measures. MIT-BIH AD was used (excluding the four records containing paced beats) without feature extraction, using 73 samples for each QRS complex.…”

Section: Background Informationmentioning

confidence: 99%

See 1 more Smart Citation

The morphological classification of heartbeats as dominant and non-dominant in ECG signals

2010

View full text Add to dashboard Cite

Surface electrocardiography (ECG) is the art of analyzing the heart's electrical activity by applying electrodes to certain positions on the body and measuring potentials at the body surface resulting from this electrical activity. Usually, significant clinical information can be obtained from analysis of the dominant beat morphology. In this respect, identification of the dominant beats and their averaging can be very helpful, allowing clinicians to carry out the measurement of amplitudes and intervals on a beat much cleaner from noise than a generic beat selected from the entire ECG recording. In this paper a standard clustering algorithm for the morphological grouping of heartbeats has been analyzed based on K-means, different signal representations, distance metrics and validity indices. The algorithm has been tested on all the records of the MIT-BIH Arrhythmia Database (MIT-BIH AD) obtaining satisfying performances in terms of averaged dominant beat estimation, but the results have not been fully satisfactory in terms of sensitivity and specificity. In order to improve the clustering accuracy, an ad hoc algorithm based on a two-phase decision tree, which integrates additional specific knowledge related to the ECG domain, has been implemented. Similarity features extracted from every beat have been used in the decision trees for the identification of different morphological classes of ECG beats. The results, in terms of dominant beat discrimination, have been evaluated on all annotated beats of the MIT-BIH AD with sensitivity = 99.05%, specificity = 93.94%, positive predictive value = 99.32% and negative predictive value = 91.69%. Further tests have shown a very slight decrement of the performances on all detected beats of the same database using an already published QRS detector, demonstrating the validity of the algorithm in real unsupervised clustering situations where annotated beat positions are not available but beats are detected with a high-performance beat detector.

show abstract

Section: Clustering By a Two-phase Ad Hoc Algorithmmentioning

confidence: 98%

Section: Background Informationmentioning

confidence: 99%

The morphological classification of heartbeats as dominant and non-dominant in ECG signals

2010

View full text Add to dashboard Cite

show abstract

“…Beat classification is based on the shape and width of the QRS complex and the length of time intervals between adjacent beats. According to [11] there are two main methods for classifying beats namely, methods based on correlation with templates [12] and methods based on feature extraction [13].…”

Section: Introductionmentioning

confidence: 99%

ECG signal acquisition and analysis for telemonitoring

Plesnik

Malgina

Tasič

et al. 2010

Melecon 2010 - 2010 15th IEEE Mediterranean Electrotechnical Conference

View full text Add to dashboard Cite

The goal of this article is to present an algorithm for QRS complex detection in an electrocardiogram (ECG) signal, realized in Matlab software. The algorithm was tested on real ECG signals acquired with a commercial monitoring system Alive Heart Monitor [1] and also for reference on signals from MIT-BIH online ECG signal database [2]. The goal of our research is to import signals from the monitoring system to a PDA or a Smart Phone via wireless network for signal processing and use in telehealthcare and telemonitoring. Therefore, we examine the concept of wireless acquisition and digital signal processing of ECG (electrocardiogram) signal, which, in addition to traditional medicine is increasingly used in the field of telemedicine as well as in completely non-medical areas, such as sport, entertainment, marketing, etc. Furthermore, we describe the fundamental architecture of an electrocardiograph and describe and overview the basic methods for ECG signal processing.

show abstract