Identification of iage using multiwavelet and neural network
Author
Source
Issue
Vol. 6, Issue 1 (31 Dec. 2010), pp.93-106, 14 p.
Publisher
University of Thi-Qar Research and Development Department
Publication Date
2010-12-31
Country of Publication
Iraq
No. of Pages
14
Main Subjects
Information Technology and Computer Science
Abstract AR
يعد التمييز و التصنيف من العلوم المتطورة في كافة المجالات الحياة و خصوصا بعد دخول الأجهزة الحديثة و استخدام برامج متعددة و منها التحويل المويجي المتعدد و الذي يحتوي على عدد كبير من المصفوفات التناظرية مما يساعد لاستخلاص الصفات أو العناصر بطريقة أكثر كفائة من غيرها و بسبب حصول هذا التوع على نسبة نجاح مقداره 98 % و من خلال دمج هذا النوع من التحويل مع الشبكة العصبية و التي ساهمت في إنجاز هذا التمييز بمقدار 100 %.
Abstract EN
A model of multiwavelet-based neural networks is proposed.
Its universal and L2 approximation properties, together with its consistency are proved, and the convergence rates associated with these properties are estimated.
The structure of this network is similar to that of the wavelet network, except that the orthonormal scaling functions are replaced by orthonormal multiskilling functions.
The theoretical analyses show that the multiwavelet network converges more rapidly than the wavelet network, especially for smooth functions.
To make a comparison between both networks, experiments are carried out with the Daubechies2 wavelet network and the GHM multiwavelet network, and the results support the theoretical analysis well.
In addition, the results also illustrate that at the jump discontinuities, the approximation performance of the two networks are about the same.
American Psychological Association (APA)
Yasir, Suhad Abbas. 2010. Identification of iage using multiwavelet and neural network. University of Thi-Qar Journal،Vol. 6, no. 1, pp.93-106.
https://search.emarefa.net/detail/BIM-253677
Modern Language Association (MLA)
Yasir, Suhad Abbas. Identification of iage using multiwavelet and neural network. University of Thi-Qar Journal Vol. 6, no. 1 (Mar. 2010), pp.93-106.
https://search.emarefa.net/detail/BIM-253677
American Medical Association (AMA)
Yasir, Suhad Abbas. Identification of iage using multiwavelet and neural network. University of Thi-Qar Journal. 2010. Vol. 6, no. 1, pp.93-106.
https://search.emarefa.net/detail/BIM-253677
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 106
Record ID
BIM-253677