東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Motor unit firing pattern analysis f...

Jahanmiri Nezhad, Faezeh.

Linked to FindBook

Google Book

Amazon

博客來

Motor unit firing pattern analysis for adaptive EMG signal decomposition.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Motor unit firing pattern analysis for adaptive EMG signal decomposition./
Author:	Jahanmiri Nezhad, Faezeh.
Description:	95 p.
Notes:	Source: Masters Abstracts International, Volume: 45-01, page: 0467.
Contained By:	Masters Abstracts International45-01.
Subject:	Engineering, Biomedical. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MR17185
ISBN:	9780494171851

Motor unit firing pattern analysis for adaptive EMG signal decomposition.
Jahanmiri Nezhad, Faezeh.

Motor unit firing pattern analysis for adaptive EMG signal decomposition. - 95 p.

Source: Masters Abstracts International, Volume: 45-01, page: 0467.

Thesis (M.A.Sc.)--University of Waterloo (Canada), 2006.

Decomposition of an electromyographic (EMG) signal is the process of resolving a composite EMC signal into its constituent motor unit potential trains (MUPTs) generated by different motor units (MU). Usually, after a raw EMG signal is segmented to its motor unit potentials (MUPs), unsupervised clustering and supervised classification techniques are applied to MUPs to form MUPTs. During this process, the MU firing patterns are useful sources of information that can be used beside MUP shapes to make accurate classifications. In this thesis, two different supervised classifiers were designed to characterize the state of created MUPTs based on their firing patterns, in order to detect MUP classification errors. An error-rate classifier (ERC) determines if the 'false-classification error' rate is acceptable or not, and the 'single or merged' classifier (SMC) determines if a train is representative of a single MU or not. The classifiers were trained using simulated MU firing patterns. (Abstract shortened by UMI.)

ISBN: 9780494171851Subjects--Topical Terms:

1017684
Engineering, Biomedical.

Motor unit firing pattern analysis for adaptive EMG signal decomposition.
LDR:01824nam 2200265 a 45 001 969250
005 20110920
008 110921s2006 eng d
020 $a 9780494171851
035 $a (UMI)AAIMR17185
035 $a AAIMR17185
040 $a UMI $c UMI
100 1 $a Jahanmiri Nezhad, Faezeh. $3 1293304
245 1 0 $a Motor unit firing pattern analysis for adaptive EMG signal decomposition.
300 $a 95 p.
500 $a Source: Masters Abstracts International, Volume: 45-01, page: 0467.
502 $a Thesis (M.A.Sc.)--University of Waterloo (Canada), 2006.
520 $a Decomposition of an electromyographic (EMG) signal is the process of resolving a composite EMC signal into its constituent motor unit potential trains (MUPTs) generated by different motor units (MU). Usually, after a raw EMG signal is segmented to its motor unit potentials (MUPs), unsupervised clustering and supervised classification techniques are applied to MUPs to form MUPTs. During this process, the MU firing patterns are useful sources of information that can be used beside MUP shapes to make accurate classifications. In this thesis, two different supervised classifiers were designed to characterize the state of created MUPTs based on their firing patterns, in order to detect MUP classification errors. An error-rate classifier (ERC) determines if the 'false-classification error' rate is acceptable or not, and the 'single or merged' classifier (SMC) determines if a train is representative of a single MU or not. The classifiers were trained using simulated MU firing patterns. (Abstract shortened by UMI.)
590 $a School code: 1141.
650 4 $a Engineering, Biomedical. $3 1017684
650 4 $a Engineering, Electronics and Electrical. $3 626636
650 4 $a Engineering, System Science. $3 1018128
690 $a 0541
690 $a 0544
690 $a 0790
710 2 0 $a University of Waterloo (Canada). $3 1017669
773 0 $t Masters Abstracts International $g 45-01.
790 $a 1141
791 $a M.A.Sc.
792 $a 2006
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MR17185