This paper presents the application of the fuzzy neural network for electrocardiographic (ECG) beat recognition and classification. The new classification algorithm of the ECG beats, applying the fuzzy hybrid neural network and the features drawn from the higher order statistics has been proposed in the paper. The cumulants of the second, third, and fourth orders have been used for the feature selection. The hybrid fuzzy neural network applied in the solution consists of the fuzzy self-organizing subnetwork connected in cascade with the multilayer perceptron, working as the final classifier. The c-means and Gustafson-Kessel algorithms for the self-organization of the neural network have been applied. The results of experiments of recognition of different types of beats on the basis of the ECG waveforms have confirmed good efficiency of the proposed solution. The investigations show that the method may find practical application in the recognition and classification of different type heart beats.

The paper presents the neuro-fuzzy approach to the recognition and classi£cation of heart rhythms on the basis of ECG waveforms. The important part in recognition ful£lls the Hermite characterization of the QRS complexes. The Hermite coef£cients serve as the features of the process. These features are applied to the fuzzy neural network for the recognition. The results of numerical experiments have con£rmed very good performance of such solution.

No abstract

No abstract

The paper presents the neuro-fuzy approach to the recognition and classification of heart rhythms on the basis of ECG waveforms. The important part in recognition fulfilk the Hermite characteridon of the QRS complexes. The Hermite coe@cients serve as the features of the process. These features are applied to the fuz?y neural network for the recognition. The results of numerical experiments have confirmed the very good pmformance of such solution.

No abstract

Electrocardiogram (ECG) and respiration signals are two basic and important and valuable biomedical signals as source of information used to determine a person's health status. However, ECG signals are usually of small amplitude and are susceptible to various noises such as: the 50Hz grid noise, poor electrodes’ contacts with the patient's skin, the patient's emotional variations, the respiration and movement of the patient... The idea in this paper by  filtering out the effect of the respiration in the ECG signal or by incorporating the information of breathing stage into the ECG signal classification the we can improve the reliability and accuracy of the arrythmia classification. This paper proposes a solution, which uses wavelet filter to reduce the effect of respiration in the ECG signals and will use additional information from the breathing rhythm (when available) to help better classifying the arrythmias. As the main nonlinear classifier we use the classical neuro-fuzzy TSK network. The proposed solution will be tested with data from the MIT-BIH and the MGH/MF databases.

This paper proposes a new method to address the  problem  of  blind  speech  separation  in  convolutive mixtures in the time domain. The main idea is extract the  innovation  processes  of  speech  sources  by  nonGaussianity  maximization  and  then  artificially  color them  by  re-coloration  filters.  Some  simulation experiments of the 2x2 case are presented to illustrate the proposed approach.