No abstract

This paper evaluates six classification algorithms to assess the importance of individual EEG rhythms in the context of automatic classification of infant sleep. EEG features were obtained by Fourier transform and by a novel technique based on the empirical mode decomposition and generalized zero crossing method. Of six evaluated classification algorithms, the best classification results were obtained with the support vector machine for the combination of all presented features from four EEG channels. Three methods of attribute ranking were assessed: relief, principal component analysis, and wrapper-based optimized attribute weights. The outcomes revealed that the optimal selection of features requires one feature from every significant frequency band, either a spectral feature or a frequency dynamic feature. This means that reducing the number of features will have a minimal impact on the classification accuracy.

This paper shows a new DWT based OFDM algorithm which significantly simplifies signal processing in the transmitter and receiver. Unlike conventional DWT based OFDM a new algorithm does not use digital modulation of subcarriers either IDWT in the transmitter. The output signal from the transmitter is formed by summing the signals on the individual subchannels, encoded with the Manchester code and sampled at appropriate frequencies. In the receiver, the channel signal and data is reconstructed using DWT and Haar wavelet. Although the signal transmission is achieved using amplitude modulation, the paper shows that BER performance is commensurable to BPSK or DMWT based OFDM in the presence of AWGN.