Abstract: A seizure prediction method is proposed by extracting
global features using phase correlation between adjacent epochs for
detecting relative changes and local features using fluctuation/
deviation within an epoch for determining fine changes of different
EEG signals. A classifier and a regularization technique are applied
for the reduction of false alarms and improvement of the overall
prediction accuracy. The experiments show that the proposed method
outperforms the state-of-the-art methods and provides high prediction
accuracy (i.e., 97.70%) with low false alarm using EEG signals in
different brain locations from a benchmark data set.
Abstract: The paper focuses on the problem of the point
correspondence matching in stereo images. The proposed matching
algorithm is based on the combination of simpler methods such as
normalized sum of squared differences (NSSD) and a more complex
phase correlation based approach, by considering the noise and other
factors, as well. The speed of NSSD and the preciseness of the
phase correlation together yield an efficient approach to find the best
candidate point with sub-pixel accuracy in stereo image pairs. The
task of the NSSD in this case is to approach the candidate pixel
roughly. Afterwards the location of the candidate is refined by an
enhanced phase correlation based method which in contrast to the
NSSD has to run only once for each selected pixel.