In this paper, a wavelet-based neural network (WNN) classifier for recognizing EEG signals is implemented and tested under three sets EEG signals (healthy subjects, patients with epilepsy and patients with epileptic syndrome during the seizure). First, the Discrete Wavelet Transform (DWT) with the Multi-Resolution Analysis (MRA) is applied to decompose EEG signal at resolution levels of the components of the EEG signal (delta, theta, alpha, beta and gamma) and the Parsevals theorem are employed to extract the percentage distribution of energy features of the EEG signal at different resolution levels. Second, the neural network (NN) classifies these extracted features to identify the EEGs type according to the percentage distribution of energy features. The performance of the proposed algorithm has been evaluated using in total 300 EEG signals. The results showed that the proposed classifier has the ability of recognizing and classifying EEG signals efficiently.

The paper presents the stratigraphy of Paleogene strata from the central part of carbonate Dinarides. The carbonate and the clastic rock units were stu died. Their contact with underlying Senonian limes tone is marked by unconformity as a result of Laramian tectonic phase. The unconformity is denoted by the abundance of bauxite deposits. The abundance of calcareous nanoplancton species as well as ben tic foraminifera points at the sedimentation of Paleogene strata during the Eocene period. The succession of sediments with easily recognizeable transgressive, inundation and regres sive features has been established. Lithostratigraphical characteristics enabled the distinguishing of larger lithofacies groups. The simultaneousness of carbonate rocks with lower part of clastic succession as well as the transitionallitho· facies have been approved. The simultaneous overburden of bauxite deposits regardless of its lithology (carbonate of clastic) speaks in favour of the unite bauxitebearing phase.

In this paper we investigate gradings on tame blocks of group algebras whose defect group is dihedral. We classify gradings on an arbitrary dihedral block up to graded Morita equivalence. We do this by computing the group of outer automorphisms that fix the isomorphism classes of simple modules. We also show how to grade these blocks via transfer of gradings via dervied equivalences.

We study the chemisorption of CO molecule into sites of different coordination on (111) surfaces of late $4d$ and $5d$ transition metals. In an attempt to solve the well-known CO adsorption puzzle, i.e., discrepancies of adsorption site preferences with experiment which appear in the standard density functional theory calculations, we have applied the relatively new van der Waals-density functional of nonlocal correlation. In all considered cases this reduces or completely solves the site preference discrepancies and improves the value of the adsorption energy. By introducing a cutoff distance for nonlocal interaction we can pinpoint the length scale at which the correlation plays a major role in the systems considered.