|
|
Analýza a klasifikace dat ze snímače mozkové aktivity
Persich, Alexandr ; Grézl, František (oponent) ; Szőke, Igor (vedoucí práce)
Tato práce se zabývá snímáním, zpracováním a klasifikací mozkové aktivity snímané pomocí brain-computer interface (BCI) zařízení od společnosti OpenBCI a možnostmi využití mozkové aktivity vyvolané představovaným pohybem končetin k ovládání aplikace. K řešení zadaného problému jsou využity metody pro zpracování signálu a strojového učení. Podařilo se vytvořit program umožňující snímání, zpracovávání a klasifikaci mozkové aktivity pomocí umělé neuronové sítě. Průměrná přesnost klasifikace na umělých datech je 99.156%. Na datech reálných se podařilo dosáhnout průměrné přesnosti 73.71%.
|
|
|
Wheelchair control using EEG signal classification
Malý, Lukáš ; Sadovský, Petr (oponent) ; Žalud, Luděk (vedoucí práce)
This diploma thesis presents the concept of mind-controlled electric wheelchair designed for people who are not able to use other interfaces such as hand joystick. Four main components of concept are described: electroencephalography, brain-computer interface, shared control and the electric wheelchair. In the text used methodology is described and results of conducted experiments are presented. In conclusion suggestions for future development are outlined.
|
|
|
Person Identification and Verification Using EEG
Žitný, Roland ; Orság, Filip (oponent) ; Tinka, Jan (vedoucí práce)
The aim of this work was to create a brain-computer interface that reliably identifies and verifies a person using his electroencephalographic signals. Creating a user profile and verifying it is based on processing reactions to his own face, and the face of strangers or acquaintances. Algorithms such as bandpass and noise removal using wavelet transformation are user to filter signals. The classification of reactions is performed using a convolutional neural network or linear discriminant analysis. The average accuracy of the linear discriminant analysis is 66.2 % and of the convolutional neural network is 58.7 %. The maximum achieved accuracy was with linear discriminant analysis and at 93.7 %.
|
|
| |
|
| |
|
|
Person Identification and Verification Using EEG
Žitný, Roland ; Orság, Filip (oponent) ; Tinka, Jan (vedoucí práce)
The aim of this work was to create a brain-computer interface that reliably identifies and verifies a person using his electroencephalographic signals. Creating a user profile and verifying it is based on processing reactions to his own face, and the face of strangers or acquaintances. Algorithms such as bandpass and noise removal using wavelet transformation are user to filter signals. The classification of reactions is performed using a convolutional neural network or linear discriminant analysis. The average accuracy of the linear discriminant analysis is 66.2 % and of the convolutional neural network is 58.7 %. The maximum achieved accuracy was with linear discriminant analysis and at 93.7 %.
|
|
|
Analýza a klasifikace dat ze snímače mozkové aktivity
Persich, Alexandr ; Grézl, František (oponent) ; Szőke, Igor (vedoucí práce)
Tato práce se zabývá snímáním, zpracováním a klasifikací mozkové aktivity snímané pomocí brain-computer interface (BCI) zařízení od společnosti OpenBCI a možnostmi využití mozkové aktivity vyvolané představovaným pohybem končetin k ovládání aplikace. K řešení zadaného problému jsou využity metody pro zpracování signálu a strojového učení. Podařilo se vytvořit program umožňující snímání, zpracovávání a klasifikaci mozkové aktivity pomocí umělé neuronové sítě. Průměrná přesnost klasifikace na umělých datech je 99.156%. Na datech reálných se podařilo dosáhnout průměrné přesnosti 73.71%.
|
|
|
EEG Measuring And Analyzing System
Blažej, Svätopluk
One of the critical steps in the design of Brain-Computer Interface applications based on electroencephalography is to process and analyze signals in real-time, in order to identify the mental state of the user. Understanding of signal processing is vital for those who deal with these signals for detection, diagnosis, and treatment of brain disorders and the related diseases. The main asset of this project is to create small, reliable and inexpensive system for analysis of brain activity. This paper describes use of microcontrollers for brain waves readings. Electrodes used for this purpose have sensitive and low noise readings.
|
|
|
Wheelchair control using EEG signal classification
Malý, Lukáš ; Sadovský, Petr (oponent) ; Žalud, Luděk (vedoucí práce)
This diploma thesis presents the concept of mind-controlled electric wheelchair designed for people who are not able to use other interfaces such as hand joystick. Four main components of concept are described: electroencephalography, brain-computer interface, shared control and the electric wheelchair. In the text used methodology is described and results of conducted experiments are presented. In conclusion suggestions for future development are outlined.
|
|
|
Control of the electric wheelchair using EEG classification
Malý, L.
Electric wheelchairs are some of the most important devices to assist physically handicapped persons. This paper presents the concept of brain controlled electric wheelchair designed for people who are not able to use other interfaces such as a hand joystick, and in particular for patients suffering from amyotrophic lateral sclerosis (ALS). The objective is to control the direction of an electric wheelchair using noninvasive scalp electroencephalogram (EEG).
|
host ::
RSS.