Název:	Methods for signal classification and their application to the design of brain-computer interfaces: technical report no. DCSE/TR-2013-4
Autoři:	Vařeka, Lukáš
Datum vydání:	2013
Nakladatel:	University of West Bohemia in Pilsen
Typ dokumentu:	zpráva report
URI:	http://www.kiv.zcu.cz/publications/ http://hdl.handle.net/11025/21543
Klíčová slova:	zpracování signálu;neuronové sítě
Klíčová slova v dalším jazyce:	signal processing;neural networks
Abstrakt v dalším jazyce:	This thesis summarizes state-of-the-art signal processing and classi cation techniques for P300 brain-computer interfaces (BCIs). BCIs allow paralyzed subjects to commu- nicate with the outside world without using their muscles. P300 BCIs are based on intermixing frequent and rare stimuli which elicit di erent responses of the brain. The main challenge we have to deal with is very low signal-to-noise ratio. Furthermore, the EEG response related to stimuli shows great subject-to-subject variability. The related state-of-the-art techniques di er both in feature extraction and classi cation. Currently, there is no approach to be state-of-the-art, instead, many approaches have been success- fully applied to di erent data-sets. Unfortunately, BCI researchers also have to cope with weaknesses of the state-of-the-art P300 BCIs. They have low bit rates and typically require new training for each individual user. In this theses, a novel approach for the de- sign of P300 BCIs is proposed. The approach is based on unsupervised neural networks.
Práva:	© University of West Bohemia
Vyskytuje se v kolekcích:	Zprávy / Reports (KIV)

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.