Brain-computer interface (BCI) is a device which allows paralyzed people to navigate a robot, prosthesis or wheelchair using only their own brains reactions. By creating a direct communication pathway between the human brain and a machine, without muscles contractions or activity from within the peripheral nervous system, BCI makes mapping persons intentions onto directive signals possible. One of the most commonly utilized phenomena in BCI is steady-state visually evoked potentials (SSVEP). If subject focuses attention on the flashing stimulus (with specified frequency) presented on the computer screen, a signal of the same frequency will appear in his or hers visual cortex and from there it can be measured. When there is more than one stimulus on the screen (each flashing with a different frequency) then based on the outcomes of the signal analysis we can predict at which of these objects (e.g., rectangles) subject was/is looking at that particular moment. Proper preprocessing steps have taken place in order to obtain maximally accurate stimuli recognition (as the specific frequency). In the current article, we compared various preprocessing and processing methods for BCI purposes. Combinations of spatial and temporal filtration methods and the proceeding blind source separation (BSS) were evaluated in terms of the resulting decoding accuracy. Canonical-correlation analysis (CCA) to signals classification was used.

The paper presents the design of a specific type of instrumented wheelset intended for continuous measuring of lateral and vertical wheel-rail interaction forces Y and Q, in accordance with regulations EN 14363 and UIC 518. The platform is a standard heavy wheelset BA314 with an axle-load of 25 tons. The key problems of smart instrumentalization are solved by the use of the wheel’s numerical FEM model, which provides a significant cost reduction in the initial stage of development of the instrumented wheelset. The main goal is to ensure high measuring accuracy. The results of the FEM calculations in ANSYS are basis for identification of the distribution of strains on the internal and external side of the wheel disc. Consequently, the most convenient radial distances for installation of strain gauges of Wheatstone measuring bridges are determined. In the next stage, the disposition, number and ways of interconnection of strain gauges in the measuring bridges are defined. Ultimately, an algorithm for inverse determination of parameters Y and Q based on mixed signals from the measuring bridges is developed. The developed solution is validated through tests on specific examples, using a created numerical FEM model. A high accuracy of estimation of unknown parameters Y and Q is obtained with an error of less than 4.5%, while the error of estimation of their ratio Y/Q is less than 2%. Therefore, the proposed solution can be efficiently used in the instrumentalization of the considered wheelset, while the problems of its practical implementation will be the subject of further research.

To overcome the detrimental influence of α impulse noise in power line communication and the trap of scarce prior information in traditional noise suppression schemes , a power iteration based fast independent component analysis (PowerICA) based noise suppression scheme is designed in this paper. Firstly, the pseudo-observation signal is constructed by weighted processing so that single-channel blind separation model is transformed into the multi-channel observed model. Then the proposed blind separation algorithm is used to separate noise and source signals. Finally, the effectiveness of the proposed algorithm is verified by experiment simulation. Experiment results show that the proposed algorithm has better separation effect, more stable separation and less implementation time than that of FastICA algorithm, which also improves the real-time performance of communication signal processing.