Clustering ECG complexes using Hermite functions and self-organizing maps

Abstract

Abstract-An integrated method for clustering of QRS complexes is presented which includes basis function representation and self-organizing neural networks (NN's). Each QRS complex is decomposed into Hermite basis functions and the resulting coefficients and width parameter are used to represent the complex. By means of this representation, unsupervised self-organizing NN's are employed to cluster the data into 25 groups. Using the MIT-BIH arrhythmia database, the resulting clusters are found to exhibit a very low degree of misclassification (1.5%). The integrated method outperforms, on the MIT-BIH database, both a published supervised learning method as well as a conventional template cross-correlation clustering method.

Addressing the Need for Context Awareness and Security Requirements in Wireless Body Area Networks

“…Kautz et al introduced the use of hierarchical hidden semi-Markov models (HHSMMs) for tracking daily activities [18]. Laerhoven and Cakmakci described an integrated approach with SOM and K nearest neighbour for classifying different activities [19]. For arrhythmia detection, Lagerholm et al proposed an integrated method for clustering QRS complexes by the use of self-organising maps (SOM) [20].…”

Computerized Interpretation of Cardiovascular Physiological Signals

“…It was deemed that various insignificant constituents in ECGs may be suppressed effectively. As a consequence, although the amplitudes bring important pathophysiological clues (Petrutiu et al, 2006), morphological analysis becomes more and more popular in computerized ECG interpretation (Weiben et al, 1999;Lagerholm et al, 2000;Linh et al, 2003;Chazal et al, 2004;. The pioneer investigators were interested in pulse waveform analysis and pattern recognition in the beginning of computerized ABP interpretation (Fei 2003).…”

“…It is difficult to calibrate non-invasive physiological signals with regard to the accidental instrumental inaccuracy and human artefacts as well. Thus many investigators chose to normalize those physiological signals and concentrated on morphological analysis (Weiben et al, 1999;Lagerholm et al, 2000;Linh et al, 2003;Chazal et al, 2004;. Moreover, it has been reported that the morphological features from normalized ECGs are comparable to those from original ones in computerized interpretation (Chazal et al, 2004).…”

“…To normalize physiological signals, several common filters were firstly applied to remove baseline wandering, muscular tremor, electrical line interference, and other noises (Lagerholm et al, 2000;Chazal et al, 2004;. After the basic filters, those physiological signals were then normalized, in a beat by beat manner, to the amplitudes within [-1, 1] and the intervals within [0,1].…”

“…Actually, signal representation in time domain is legible but redundant, which may be evidenced by means of PCA (Geva 1998;Stamkopoulos et al, 1998). As a consequence, morphological analysis was generally combined with domain transformation, such as Hilbert transform (Bolton & Westphal 1981), HD (Rasiah et al, 1997;Lagerholm et al, 2000;Linh et al, 2003) and WT (Senhadii et al, 1995;AI-Farhoum & Howitt 1999;Saxena et al, 2002;Engin 2007), in those published paradigms of computerized physiological signal interpretation. Domain transformation, unlike direct morphological analysis, attempts to characterize physiological signals in an alternative space, where the genuine signal components are more discernible from noises and artefacts.…”