EMAIL: PASSWORD:
Front Office
UPT. PERPUSTAKAAN
Institut Teknologi Sepuluh Nopember Surabaya


Kampus ITS Sukolilo - Surabaya 60111

Phone : 031-5921733 , 5923623
Fax : 031-5937774
E-mail : libits@its.ac.id
Website : http://library.its.ac.id

Support (Customer Service) :
timit_perpus@its.ac.id




Welcome..guys!

Have a problem with your access?
Please, contact our technical support below:
LIVE SUPPORT


Moh. Fandika Aqsa


Davi Wahyuni


Tondo Indra Nyata


Anis Wulandari


Ansi Aflacha




ITS » Undergraduate Theses » Teknik Informatika
Posted by hassane at 09/12/2008 16:45:51  •  3965 Views


FUZZY MULTILAYER PERCEPTRON UNTUK KLASIFIKASI BERBASIS PENGETAHUAN

FUZZY MULTILAYER PERCEPTRON FOR KNOWLEDGE-BASED CLASSIFICATION

Author :
Ihsan, Rahmat 




ABSTRAK

Ruang pencarian yang besar merupakan suatu masalah khusus pada klasifikasi dengan multilayer perceptron. Beberapa usaha telah dilakukan dalam meningkatkan performa klasifikasi dan mereduksi ruang pencarian. Model seperti itu mempunyai kemampuan melebih MLP standar. Oleh karena itu sebuah algoritma baru pada klasifikasi berbasis pengetahuan dengan menggunakan fuzzy multilayer perceptron MLP akan diterapkan untuk mempersempit ruang pencarian dengan performa klasifikasi yang cukup baik. Pengetahuan yang dikumpulkan dari sebuah himpunan data pada awalnya dikodekan di antara bobot-bobot link di dalam fuzzy MLP yaitu dengan menggunakan apriori probabilitas kelas yang bersangkutan. Pengkodean ini juga melibatkan pembentukan hidden nodes yang merepresentasikan wilayah kelas-kelas pola dan juga wilayah komplemennya. Arsitektur jaringan yang dimaksud dalam hal ini yaitu node-node dan penghubungnya terus diperbaiki selama proses training berlangsung. Hasil-hasil yang dicapai pada empat kali uji coba menunjukkan bahwa kecepatan pembelajaran dan performa klasifikasi dari metode yang diusulkan adalah cukup baik pada setiap uji coba. Hanya dalam dua puluh kali iterasi jaringan syaraf mencapai solusi optimal. Sedangkan performa klasifikasi berdasarkan correct match mencapai angka rata-rata 70 persen pada tahap testing.


ABSTRACT

The large searching space is a special problem in classification using Multilayer Perceptron MLP . Recently there have been some attempts in improving the performance of MLP using knowledge-based networks. Such a model has the capability of outperforming a standard MLP as well as other related algorithms. A new scheme of knowledgebased classification using a fuzzy multilayer perceptron MLP is proposed to reduced the searching space with a good enough performance. Knowledge collected from a data set is initially encoded among the connection weights in terms of class a priori probabilities. This encoding also includes incorporation of hidden nodes corresponding to both the pattern classes and their complementary regions. The network architecture in terms of both links and nodes is then refined during training. Results on experiment data demonstrate that the speed of learning and classification performance of the proposed scheme are good enough. The proposed network model converges to a good solution in about twenty times iteration. Classification performances reach about 70 percent in the testing phase.



KeywordsKlasifikasi ; Fuzzy MLP ; Jaringan Berbasis Pengetahuan
 
Subject:  Jaringan Syaraf Tiruan
Contributor
  1. Dr. Agus Zainal Arifin, S.Kom., M.Kom
Date Create: 09/12/2008
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Undergraduate-3100008032193
Collection ID: 3100008032193
Call Number: RSIf 006.32 Ihs f


Source
Undergraduate Theses of Informatics Engineering Department, RSIf 006.32 Ihs f, 2008

Coverage
ITS Community

Rights
Copyright @2008 by ITS Library. This publication is protected by copyright and permission should be obtained from the ITS Library prior to any prohibited reproduction, storage in a retrievel system, or transmission in any form or by any means, electronic, mechanical, photocopying, recording, or likewise. For information regarding permission(s), write to ITS Library




[ Download - Summary ]

ITS-Undergraduate-3100008032193-2788.pdf




 Similar Document...




! ATTENTION !

To facilitate the activation process, please fill out the member application form correctly and completely

Registration activation of our members will process up to max 24 hours (confirm by email). Please wait patiently

POLLING

Bagaimana pendapat Anda tentang layanan repository kami ?

Bagus Sekali
Baik
Biasa
Jelek
Mengecewakan





You are connected from 3.235.85.115
using CCBot/2.0 (https://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2020 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan