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

Nonlinear physiological system model...

Mitsis, Georgios D.,

FindBook

Google Book

Amazon

博客來

Nonlinear physiological system modeling with Laguerre-Volterra networks /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Nonlinear physiological system modeling with Laguerre-Volterra networks // Georgios D Mitsis.
作者:	Mitsis, Georgios D.,
面頁冊數:	1 electronic resource (52 pages)
附註:	Source: Masters Abstracts International, Volume: 64-04.
Contained By:	Masters Abstracts International64-04.
標題:	Biomedical research. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1409648
ISBN:	9780493698175

Nonlinear physiological system modeling with Laguerre-Volterra networks /
Mitsis, Georgios D.,

Nonlinear physiological system modeling with Laguerre-Volterra networks /Georgios D Mitsis. - 1 electronic resource (52 pages)

Source: Masters Abstracts International, Volume: 64-04.

The study of many important nonlinear systems relies on the use of Volterra models. The use of feedforward artificial neural networks for modeling nonlinear Volterra systems has been recently addressed by means of tapped delay inputs and polynomial activation functions. Previous modeling studies also demonstrated the practical advantages of using Laguerre expansions of the Volterra kernels in order to achieve model compactness and estimation accuracy. The resulting Laguerre expansion technique can be combined with the feedforward ANN utilizing polynomial activation functions in the form of the Laguerre-Volterra network (LVN). The purpose of this work is first to introduce a computationally efficient way in order to train the network parameters and also to propose an alternative form of the LVN suitable for studying systems displaying complex dynamics. Results from applying this modeling approach are presented herein and demonstrate its effectiveness and robustness.

English

ISBN: 9780493698175Subjects--Topical Terms:

3433833
Biomedical research.

Nonlinear physiological system modeling with Laguerre-Volterra networks /
LDR:02127nmm a22003613i 4500 001 2434629
005 20250923060932.5
006 m o d
007 cr|nu||||||||
008 261011s2000 miu||||||m |||||||eng d
020 $a 9780493698175
035 $a (MiAaPQD)AAI1409648
035 $a AAI1409648
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Mitsis, Georgios D., $e author. $3 3824669
245 1 0 $a Nonlinear physiological system modeling with Laguerre-Volterra networks / $c Georgios D Mitsis.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2000
300 $a 1 electronic resource (52 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 64-04.
500 $a Publisher info.: Dissertation/Thesis.
502 $b M.S. $c University of Southern California $d 2000.
520 $a The study of many important nonlinear systems relies on the use of Volterra models. The use of feedforward artificial neural networks for modeling nonlinear Volterra systems has been recently addressed by means of tapped delay inputs and polynomial activation functions. Previous modeling studies also demonstrated the practical advantages of using Laguerre expansions of the Volterra kernels in order to achieve model compactness and estimation accuracy. The resulting Laguerre expansion technique can be combined with the feedforward ANN utilizing polynomial activation functions in the form of the Laguerre-Volterra network (LVN). The purpose of this work is first to introduce a computationally efficient way in order to train the network parameters and also to propose an alternative form of the LVN suitable for studying systems displaying complex dynamics. Results from applying this modeling approach are presented herein and demonstrate its effectiveness and robustness.
546 $a English
590 $a School code: 0208
650 4 $a Biomedical research. $3 3433833
650 4 $a Electrical engineering. $3 649834
650 4 $a Biomedical engineering. $3 535387
690 $a 0541
690 $a 0544
690 $a 0800
710 2 $a University of Southern California. $e degree granting institution. $3 3771785
773 0 $t Masters Abstracts International $g 64-04.
790 $a 0208
791 $a M.S.
792 $a 2000
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1409648