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 Ekstensi - S1
Posted by ansi@its.ac.id at 14/09/2011 13:19:41  •  1773 Views


PENENTUAN STATUS BANTU ANAK ASUH PENA BANGSA MENGGUNAKAN METODE NEURO FUZZY

CLASSIFYING PENA BANGSA SCHOLARSHIP RECEIVER USING NEURO FUZZY METHOD

Author :
WAHYUDI, HENDRA BAGUS ( 5101109048 )




ABSTRAK

Sebagai program unggulan program Beasiswa Anak Asuh Peduli Anak Bangsa Yayasan Dana Sosial Al Falah PENA BANGSA YDSF memiliki kendala. YDSF masih menggunakan cara manual dalam menentukan status bantu anak. Subyektifitas surveyor di lapangan masih mempengaruhi pemberian status bantu pada anak.Oleh karena itu diperlukan suatu sistem yang dapat mengklasifikasikan status bantu anak asuh. Dalam Tugas Akhir ini akan dibahas pengklasifikasian status bantu dengan benar. Pengenalan status bantu dilakukan dalam dua tahap. Tahap Pertama adalah melaukukan fuzzifikasi input data sehingga siap digunakan untuk proses pelatihan maupun proses pengenalan pada neural network. Pada tahap kedua input yang sudah difuzzifikasi diproses dengan neural network. Arsitektur jaringan yang digunakan adalah Backpropagation dengan sebuah input layer 25 input unit sebuah hidden layer hidden unit dapat disesuaikan dan sebuah output layer 3 output unit. Dari hasil uji coba terhadap jaringan syaraf yang telah terbentuk untuk mengklasifikasikan status bantu maka didapatkan suatu kesimpulan jumlah hidden unit learning rate nilai toleransi error dan fungsi aktivasi mana yang memiliki nilai akurasi paling baik untuk mengklasifikasi status bantu. Sebagai hasil dari uji coba didapatkan suatu hasil analisis bahwa dari jumlah hidden unit nilai learning rate toleransi error dan fungsi aktivasi maka yang paling baik digunakan untuk mengklasifikasikan status bantu adalah fungsi aktivasi sigmoid biner. Dengan menggunakan hidden unit 100 momentum 0.2 learning rate 0.01 nilai toleransi error 1E-13 didapatkan tingkat akurasi sebesar 98.70 pada tahap pelatihan dan tingkat akurasi sebesar 93.63 pada tahap pengenalan.


ABSTRACT

YDSF has best program called as PENA BANGSA. Although this program categorized as best program PENA BANGSA still face some problems in its implementation. YDSF use manual way in deciding its scholarship receiver. Surveyor subjectivity in the field becomes the main standard in deciding the status of scholarship receiver. Thus YDSF needs a new system that can classify the status of its scholarship receiver based on the standard decided. In this final project researcher would like to discuss about status classification of scholarship receiver correctly. Introduction to the scholarship receiver classification will be conducted in two steps. The first step is conducting input data fuzzification this step aimed at data preparation to make it ready to be used in introduction and training process to the neural network. Network architecture that was used is backpropagation with an input layer 25 input units a hidden layer can be customizable hidden layer and output layer 3 output units. The result of the test to the neuron network made to classify the scholarship receiver the conclusions got are the hidden unit learning rate error tolerance value and activation function which have best accurate value to classify the scholarship receiver status. The test result from amount of hidden unit rate learning value error tolerance and activation function found that the activation function sigmoid biner is the best system to classify the status of scholarship receiver. Using hidden unit 100 momentum 02 learning rate 001 error tolerance value 1E-13 resulting accurate grade 9870 in the training step and 9363 in the introduction step.



KeywordsFuzzifikasi;Neural Network;Backpropagation;Fungsi Aktivasi;Hidden Unit;Learning Rate,;Momentum;Nilai Toleransi Error;Sigmoid Biner
 
Subject:  Jaringan saraf (ilmu komputer)
Contributor
  1. Ahmad Saikhu, S.Si, MT
  2. Yudhi Purwananto, S.Kom, M.Kom
Date Create: 23/02/2011
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Undergraduate-3100011042625
Collection ID: 3100011042625
Call Number: RSIf 006.32 Wah p


Source
Undergraduate Thesis, Informatics Engineering, RSIf 006.32 Wah p, 2011

Coverage
ITS Community

Rights
Copyright @2011 by ITS Library. This publication is protected by copyright and per obtained from the ITS Library prior to any prohibited reproduction, storage in a re transmission in any form or by any means, electronic, mechanical, photocopying, reco For information regarding permission(s), write to ITS Library




[ Download - Open Access ]

  1.  ITS-Undergraduate-15212-Abstract_id-pdf.pdf - 255 KB
  2.  ITS-Undergraduate-15212-Abstract_en-pdf.pdf - 262 KB
  3.  ITS-Undergraduate-15212-Conclusion-pdf.pdf - 268 KB




 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 54.196.47.128
using CCBot/2.0 (http://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2017 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan