Event recognition, separation and classification from ECG recordings

Szilagyi, S.M.

doi:10.1109/iembs.1998.745883

Cited by 9 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the model has to take in consideration extremely numerous parameter values, the problem cannot be solved in a deterministical way (we have much more unknown values then known equations). That is why a stochastical method (genetic algorithm, adaptive neural networks and fuzzy systems) should be applied to determine the values of the parameters (Szilágyi, 1998).…”

Section: The Structure Of the Combined Heart Modelmentioning

confidence: 99%

See 1 more Smart Citation

Recognition of Various Events From 3-D Heart Model

Szilagyi

Benyó

Szilágyi

2005

IFAC Proceedings Volumes

View full text Add to dashboard Cite

Section: The Structure Of the Combined Heart Modelmentioning

confidence: 99%

“…During the signal processing, if the traditional algorithm finds an unrecognisable waveform, the model-based approach is activated, which tries to estimate the causes of the encountered phenomenon (e.g. quick recognition of ventricular fibrillation) (Szilágyi, 1998).…”

Section: Introductionmentioning

confidence: 99%

Recognition of Various Events From 3-D Heart Model

Szilagyi

Benyó

Szilágyi

2005

IFAC Proceedings Volumes

View full text Add to dashboard Cite

“…3. Characteristic parameter estimation methods: the methods in this group determine the characteristic points like P, Q, R, S and T [23][24][25][26]. Feature Application of InP Neural Network to ECG Beat Classification vectors are formed by time intervals of the characteristic points and signal magnitudes at these points.…”

Section: Introductionmentioning

confidence: 99%

Application of InP Neural Network to ECG BeatClassification

Ölmez

Dokur

2003

Neural Computing & Applications

View full text Add to dashboard Cite

This paper presents an application of a hybrid neural network structure to the classification of the electrocardiogram (ECG) beats. Three different feature extraction methods are comparatively examined: discrete cosine transform, wavelet transform and a direct method. Classification performances, training times and the numbers of nodes of Kohonen network, Restricted Coulomb Energy (RCE) network and the hybrid neural network are presented. To increase the classification performance and to decrease the number of nodes, the hybrid neural network is trained by Genetic Algorithms (GAs). Ten types of ECG beats obtained from the MIT-BIH database and from a real-time ECG measurement system are classified with a success of 98% by using the hybrid neural network structure and discrete cosine transform together.

show abstract

“…These hybrid systems may activate the model-based-approach at any moment to handle correctly almost all unrecognizable waveform. The strange waveforms may appear in case of unknown patients or uncommon states, such as ventricular fibrillation [19]. In these cases the model-based approach estimates the causes of the encountered phenomenon.…”

Section: Introductionmentioning

confidence: 99%

“…In the area of data processing, numerous interesting biomedical applications of artificial neural networks are included [7]. The best known neural solutions involve multilayer perceptrons [20], Kohonen self-organizing networks [17], fuzzy or neuro-fuzzy systems [16], genetic algorithms [19] and the combination of various solutions within a hybrid system [11].…”

Section: Introductionmentioning

confidence: 99%

Unified Neural Network Based Pathologic Event Reconstruction Using Spatial Heart Model

Szilágyi

Frigy

et al.

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper presents a new way to solve the inverse problem of electrocardiography in terms of heart model parameters. The developed event estimation and recognition method uses a unified neural network (UNN)-based optimization system to determine the most relevant heart model parameters. A UNN-based preliminary ECG analyzer system has been created to reduce the searching space of the optimization algorithm. The optimal model parameters were determined by a relation between objective function minimization and robustness of the solution. The final evaluation results, validated by physicians, were about 96% correct. Starting from the fact that input ECGs contained various malfunction cases, such as Wolff-Parkinson-White (WPW) syndrome, atrial and ventricular fibrillation, these results suggest this approach provides a robust inverse solution, circumventing most of the difficulties of the ECG inverse problem.

show abstract

Event recognition, separation and classification from ECG recordings

Cited by 9 publications

References 6 publications

Recognition of Various Events From 3-D Heart Model

Recognition of Various Events From 3-D Heart Model

Application of InP Neural Network to ECG BeatClassification

Unified Neural Network Based Pathologic Event Reconstruction Using Spatial Heart Model

Contact Info

Product

Resources

About