Wyniki wyszukiwania - BazTech

1

Finding Optimal Frequency and Spatial Filters Accompanying Blind Signal Separation of EEG Data for SSVEP-based BCI

Jukiewicz M., Buchwald M., Cysewska-Sobusiak A.

International Journal of Electronics and Telecommunications

|

2018

|

Vol. 64, No. 4

439--444

EN

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.

2

Usuwanie artefaktów z sygnałów sterujących interfejsem mózg-komputer

Jukiewicz M., Buchwald M., Cysewska-Sobusiak A.

Poznan University of Technology Academic Journals. Electrical Engineering

|

2017

|

No. 89

195--204

PL

Elektroencefalografia jest metodą pozwalającą na pomiar elektrycznej aktywności mózgu. Metoda ta jest wykorzystywana do diagnostyki pracy mózgu oraz w tzw. interfejsach mózg-komputer, czyli urządzeniach pozwalających na bezpośrednią komunikację pomiędzy mózgiem a jednostką obliczeniową. Interfejsy takie tworzone są głównie z myślą o osobach częściowo sparaliżowanych lub dotkniętych syndromem zamknięcia. Jednym ze zjawisk zachodzącym w mózgu, wykorzystywanym w interfejsach mózg-komputer, są Wzrokowe Potencjały Wywołane Stanu Ustalonego SSVEP (Steady State Visually Evoked Potentials). Jeśli osoba badana obserwuje bodziec, migający z określoną częstotliwością, to sygnał o tej samej częstotliwości (dominującej) zostanie zmierzony nad korą wzrokową. W takich urządzeniach bardzo istotne jest przetwarzanie zmierzonego sygnału w taki sposób, aby zapewnić jak największą skuteczność rozpoznania na co w danej chwili patrzy osoba badana. Jednym ze sposobów na osiągnięcie tego celu może być wykorzystanie Ślepej Separacji Sygnałów BSS (Blind Source Separation), której celem jest znalezienie i usunięcie z mierzonych sygnałów niepożądanych składowych, np. związanych z mrugnięciami oczu czy napinaniem mięśni twarzy. W prezentowanym artykule zostały umówione sposoby wykorzystania Ślepej Separacji Sygnałów w badaniach elektroencefalograficznych nad Wzrokowymi Potencjałami Wywołanymi Stanu Ustalonego. Przedstawiono także wyniki skuteczności rozpoznania intencji badanego w zależności od liczby usuniętych składowych, rodzaju algorytmu Ślepej Separacji Sygnału i sposobu klasyfikacji sygnału.

EN

Electroencephalography allows recording the electrical activity of the brain. This method is used for diagnosis purposes as well as in brain–computer interfaces. Focusing on the brain–computer interface, it can be used to let the direct communication between the brain and a computing unit. This device is particularly useful for paralyzed patients or people suffering from a lock–in syndrome. Of the phenomena used in such systems, steady state visually evoked potentials (SSVEP) are probably the most common ones. If a subject is asked to focus on the flashing stimulus, a signal of the same frequency may be measured from the subject’s visual cortex. Proper preprocessing steps has to be taken in order to obtain maximally accurate stimuli recognition (as the specific frequency). One way to achieve this might be by applying the Blind Source Separation algorithms (BSS). BSS are designed to find and remove artifacts from the measured signal, e.g. noises associated with eye blinks or facial muscles contraction. In the present article an utilization of the BSS algorithms in the SSVEP–based EEG study was described. Additionally we report the accuracy of the stimuli categorization as depending on the number of removed components, kind of the blind source separation procedure and the type of the classification algorithm.

3

Application of standard algorithms of automatic signal separation in medicine

Nowak A.

Bio-Algorithms and Med-Systems

|

2011

|

Vol. 7, no. 4

29--40

EN

In the present article various methods of automatic separation of acoustic signals have been described. The biggest focus was placed on two methods, Blind signal Separation (BSS) and Independent Component Analysis (ICA). In order to verify the efficacy of these methods, selected separation algorithms have been used for deconvolution of a specially prepared sinusoidal and saw-tooth sound signals as well as natural signals such as recordings of human voice. The obtained results have been compared and presented. More accurate results have been acquired from the analysis of artificially prepared signals that is the sinusoidal and saw-tooth signals which were mixed together using numerical transformations. Due to the potential practical usage of speech signal separation in medicine, more stress has been put on the analysis of life taken signals, which were created by mixing voices of few persons speaking simultaneously. The assessment of the usability of different algorithms, which effected from the research, may have practical application due to the fact that in the available literature the authors usually limit themselves only to presenting (and praising) algorithms created on their own, scarcely mentioning algorithms of different authors predominantly without doing necessary comparative researches. These missing researches constitute the essential part of the work presented in this article.