東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Addressing the challenges in signal ...

Zou, Yuan.

FindBook

Google Book

Amazon

博客來

Addressing the challenges in signal quality and calibration time of EEG-based brain-computer interface.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Addressing the challenges in signal quality and calibration time of EEG-based brain-computer interface./
作者:	Zou, Yuan.
面頁冊數:	149 p.
附註:	Source: Dissertation Abstracts International, Volume: 76-11(E), Section: B.
Contained By:	Dissertation Abstracts International76-11B(E).
標題:	Electrical engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3708524
ISBN:	9781321838978

Addressing the challenges in signal quality and calibration time of EEG-based brain-computer interface.
Zou, Yuan.

Addressing the challenges in signal quality and calibration time of EEG-based brain-computer interface. - 149 p.

Source: Dissertation Abstracts International, Volume: 76-11(E), Section: B.

Thesis (Ph.D.)--The University of Texas at Dallas, 2015.

The primary aim of a Brain-Computer Interface (BCI) is to provide communication capabilities through Electroencephalography (EEG), the recording of electrical activity produced by the firing of neurons within the brain, for those with brain disorders to be able to interact with the outside world. However, EEG recordings are always contaminated with artifacts which hinder the decoding process. Therefore, identifying and removing artifacts is an important step. An automatic algorithm for the identification of two categories of EEG artifacts is proposed in this dissertation. The proposed algorithm consists of two parts: 1) an event-related feature based clustering algorithm used to identify artifacts which have physiological origins and 2) the electrode-scalp impedance information employed for identifying non-biological artifacts. The results show that our algorithm can effectively detect, separate, and remove both physiological and non-biological artifacts. The performance results also show that our proposed method can subsequently enhance the classification accuracies compared to other commonly used automatic artifact removal methods.

ISBN: 9781321838978Subjects--Topical Terms:

649834
Electrical engineering.

Addressing the challenges in signal quality and calibration time of EEG-based brain-computer interface.
LDR:02961nmm a2200289 4500 001 2069233
005 20160510115008.5
008 170521s2015 ||||||||||||||||| ||eng d
020 $a 9781321838978
035 $a (MiAaPQ)AAI3708524
035 $a AAI3708524
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zou, Yuan. $3 1280795
245 1 0 $a Addressing the challenges in signal quality and calibration time of EEG-based brain-computer interface.
300 $a 149 p.
500 $a Source: Dissertation Abstracts International, Volume: 76-11(E), Section: B.
500 $a Adviser: Roozbeh Jafari.
502 $a Thesis (Ph.D.)--The University of Texas at Dallas, 2015.
520 $a The primary aim of a Brain-Computer Interface (BCI) is to provide communication capabilities through Electroencephalography (EEG), the recording of electrical activity produced by the firing of neurons within the brain, for those with brain disorders to be able to interact with the outside world. However, EEG recordings are always contaminated with artifacts which hinder the decoding process. Therefore, identifying and removing artifacts is an important step. An automatic algorithm for the identification of two categories of EEG artifacts is proposed in this dissertation. The proposed algorithm consists of two parts: 1) an event-related feature based clustering algorithm used to identify artifacts which have physiological origins and 2) the electrode-scalp impedance information employed for identifying non-biological artifacts. The results show that our algorithm can effectively detect, separate, and remove both physiological and non-biological artifacts. The performance results also show that our proposed method can subsequently enhance the classification accuracies compared to other commonly used automatic artifact removal methods.
520 $a Another major challenge in realization of the EEG signals is the long calibration time required since they show significant variations between recording sessions even for the same subject within the same experimental condition. This dissertation proposes a score-based adaptive training algorithm that maximally utilizes relevant information from prior recording sessions and significantly shortens the calibration time. Also a hierarchical clustering based adaptive training algorithm that captures the common information between recording sessions is proposed for real-time (zero calibration) applications. The experimental results show that by employing few letters for calibration, the score-based adaptive training algorithm can achieve 100% classification accuracy. Without calibration, the clustering-based adaptive training algorithm can achieve 95% classification accuracy.
590 $a School code: 0382.
650 4 $a Electrical engineering. $3 649834
650 4 $a Computer science. $3 523869
690 $a 0544
690 $a 0984
710 2 $a The University of Texas at Dallas. $b Electrical Engineering. $3 1679269
773 0 $t Dissertation Abstracts International $g 76-11B(E).
790 $a 0382
791 $a Ph.D.
792 $a 2015
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3708524