[Study of the letter and word recognition by the brain-computer-interface with P300 wave of human visual evoked potential].

In four adult healthy subjects in 18 experiments, we studied Brain-Computer-Interface recognition of different intended words by P300 wave in the VEP. The set of optimal characteristics of visual stimulation which rise reliability of recognition up to 100 %, as well as effective registration locus (Pz) were determined. It was found that the best processing criteria for letter recognition were: P300 square and superposition of all three criteria (P300 amplitude, square and covariation coefficient).

[Use of pitch and formant analysis in speech biometry].

The goal of this work was to study the possibility of use of speech biometry for identification of speaker, determination of speech accent, and estimation of the emotional state of the speaker. It was suggested to solve these problems by analysis of the two main components of the linear model of speech production: pitch and formant frequencies. It was shown that pitch and formant analysis provided estimation of the emotional state of the speaker.

[A P300-based brain-computer interface].

The goal of this work was to describe a system for real-time typing controlled by brain biopotential signals. A 6 ( 6 matrix containing Russian alphabet letters and auxiliary symbols was shown on PC screen. Electroencephalogram was taken, and the P300 component was extracted (this component appeared only upon presentation of a significant stimulus).

[Classification of human sleep stages based on EEG processing using hidden Markov models].

The goal of this work was to describe an automated system for classification of human sleep stages. Classification of sleep stages is an important problem of diagnosis and treatment of human sleep disorders. The developed classification method is based on calculation of characteristics of the main sleep rhythms.

[Human visual evoked potentials to bars and cross-like figures].

Temporal and amplitude characteristics of averaged visual evoked potentials to presentation of lines, corners and crosses with different orientation recorded in 19 adult healthy subjects were compared in 34 derivations. In all subjects, the latencies of P1, N2, and P3 were shorter while their amplitudes were higher for crosses than for lines. The effect of lengthening of P1 peak latency from occipital to temporal cortex was mostly pronounced for EPs to a bar, whereas as increase in the P1 amplitude was most evident for a cross-like figure.