Epilepsy is the most common neuropathology. Statistical studies related to the disease reported that 20%-25% of epileptic patients with occurrence of seizures were even under treatment with drugs. This article presents a strategy for improved detection of the neuropathology, based on electroencephalogram (EEG), using a classifier built with support vector machines (SVC). The SVC is designed based on feature extraction of higher order spectra of time series derived from the EEG applied to epileptic patients and control patients. As demonstrated in the study presented, the EEG time series are highly nonlinear and non-Gaussian, therefore, exhibit higher order spectra, which are extracted features that improve the accuracy in the performance of SVC. The results of this study suggest the development of highly accurate computational tools for the diagnosis of this dreaded neuropathology.

No abstract

In this article an application of the support vectors machines (SVM) is presented in the problem of the estimate of the action potential of the cellular membrane V, which is, a temporary function, highly non-linear, of the ionic concentrations of sodium and potassium. A model, for the estimate of V, is the Hodgkin-Huxley (HH) model that describes the dynamics of V similar to an electric circuit with passive elements representing the biochemical variables involved in the process. SVM are algorithms of emergent computation that have demonstrated an excellent performance in classification and regression applications; in this article they are used for the estimate of V and the result is compared with that obtained using HH, demonstrating that SVM are a promising alternative in modelling problem of biological processes.

No abstract

No abstract