P. Poryzała

Cluster analysis of CCA coefficients for robust detection of the asynchronous SSVEPs in brain–computer interfaces

Abstract In this paper, a method for detection of steady-state visual evoked potentials in a non-invasive, multiple channel, asynchronous brain–computer interface is proposed. It is based on the canonical correlation analysis spatial filter for identifying optimal weighted combinations of electrode signals, followed by a cluster analysis of its coefficients for a fast and accurate SSVEP detection. High information transfer rates can be achieved after a short calibration session. The proposed algorithm, a standard spectrum analysis approach, and two competitive spatial filtering and detection methods were evaluated in a series of experiments with the use of data from 21 subjects. The obtained results showed a significant improvement in classification accuracy and in an average detection time for a large group of users.

High-speed noninvasive brain-computer interfaces

Brain computer interface (BCI) systems allow interaction with machines through a channel that does not involve the traditional motor pathways of the human nervous system. Thus they can be used by people with severe motor disabilities or those whose limbs are occupied with other tasks. In BCI systems that recently showed greatest interest of researchers, electrical brain activity is measured on the scalp, thus basically they are noninvasive. Using the EEG measurements as the input to the BCI offers the advantages of low cost and high time resolution. However, due to small amplitude of the signal components, relatively high power of noise and poor spatial resolution, achieving large speed, accuracy and the number of targets is a challenge. At present, the steady-state visual evoked potential (SSVEP) BCI paradigm is believed to provide the most promising way of optimizing the BCI performance in that sense. A review of the SSVEP BCI projects is presented, including studies of biodiversity of human EEG response to visual excitation, as well as the design of techniques for visual stimulation, EEG signal acquisition and analysis for best BCI performance. The review is based both on the literature and results of own teamwork.

Mixed-mode wireless indoor positioning system using proximity detection and database correlation

The paper presents a prototype mixed-mode wireless indoor positioning and navigation system. The main goal of the system is to provide accurate and reliable location information for visually impaired users. The system also enables access to location related context information. The radio nodes of the network can operate in two power modes providing basis for both rough and precise user positioning. The paper describes an overview of the system architecture and the user interface suited to the needs of the visually impaired. Then, the details of the implemented positioning methods are presented. Finally, the results of experimental evaluation of positioning accuracy obtained using different classification strategies are discussed.

On Possibility of Stimulus Parameter Selection for SSVEP-Based Brain-Computer Interface

It is postulated that performance of brain-computer interfaces (BCI) based on detection of steady-state visual evoked potentials (SSVEP) can be improved by proper configuration of the visual stimulator. Preliminary results of experiments are presented to confirm dependence of SSVEP characteristics on parameters of the stimulus.