PROJECT TITLE :
Real-time mining of epileptic seizure precursors via nonlinear mapping and dissimilarity features
We have a tendency to propose a novel approach for detecting precursors to epileptic seizures in intracranial electroencephalograms (iEEGs), which is based on the analysis of system dynamics. In the proposed scheme, the largest Lyapunov exponent (LLE) of wavelet entropy of the segmented EEG signals are thought-about because the discriminating features. Such features are processed by a support vector machine classifier, whose outcomes (the label and its chance for every LLE) are post-processed and fed into a unique call perform to work out whether or not the corresponding phase of the EEG signal contains a precursor to an epileptic seizure. The proposed theme is applied to the Freiburg data set, and the results show that seizure precursors are detected during a time frame that in contrast to alternative existing schemes is terribly much convenient to patients, with the sensitivity of 100percent and negligible false positive detection rates.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here