Output details
11 - Computer Science and Informatics
Middlesex University
A MIXTURE MODEL CLASSIFIER AND ITS APPLICATION ON THE BIOMEDICAL TIME SERIES
<22>It is critical that a cardiac arrest patient suffering ventricular fibrillation (VF) is immediately treated by paramedics on site. This work presents a methodology based on the mixture model to classify the real ECG time series (VF data), in order to help paramedics to predict the efficiency of emergent treatment in the real time. It improves the results of our former work, which was supported by an EPSRC grant. This new work achieves the highest overall classification rate available so far, signifying that it possesses the highest prediction accuracy. It was a collaborative work between Norwegian and British scientists.