Speaker
Peter Posfay
(Eötvös Lóránd University)
Description
I introduce a new method called linear law-based feature space transformation (LLT) which can be applied in the analysis of time series. This method builds on ideas from physics and data science. It implements a transformation of the input time series in such a way that the resulting feature set can be effectively used for classification tasks. After describing the method, I present its application for classifying healthy and ectopic ECG signals. First the linear law-based transformation is applied on the ECG dataset than it is studied how different classification methods perform on it. Based on the method 93% - 97% accuracy can be achieved using simple methods like support vector machines, KNNs and random forests.
