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 » Master Theses » Teknik Elektro S2
Posted by davi at 28/12/2006 15:51:57  •  35349 Views


IDENTIFIKASI SINYAL EEG UNTUK DETEKSI POLA SPIKE EPILEPSI DENGAN JARINGAN SARAF TIRUAN

IDENTIFY EEG SINYAL TO DETECT PATERN OF EPILEPSY SPIKE WITH ARTIFICIAL NEURAL NETWORK

Author :
ARISWATI, HER GUMIWANG  




ABSTRAK

Walaupun aktifitas listrik otak manusia sudah dapat dideteksi dengan suatu instrumen kedokteran yaitu alat EEG Electroenchepalograph kenyataannya hasil pembacaan rekaman EEG dari dokter sifatnya subyetif karena bentuk output gelombang EEG yang kompleks. Metode jaringan syaraf tiruan JST dipergunakan untuk mengenal pola EEG agar lebih obyektif. Penggabungan dengan CSP Composite Spike Parameter diharapkan dapat menambah unjuk kerja sistem. Konsep pengenalan pola dengan algoritma Bach Propagation dalam jaringan syaraf tiruan dengan kontruksi 3 layer dalam susunan 50 node input layer 25 node hidden layer dan 3 node output layer melalui praproses data input penentuan faktor-faktor belajar dan penyesuain bobot dalam proses latihan kemudian pengujian unjuk kerja sistem dapat berperan dalam masalah pengenalan pola gelombang EEG. Data belajar jaringan diambil dari 2 pola standar yaitu 1 pola EEG normal dan 1 pola EEG epilepsi dengan jumlah data 100 dan keterandalan sistem diuji dengan menggunakan masing- masing 10 responden dengan data yang baru dan belum pernah dilatihkan sama sekali dengan nilai error maksimal sebesar 002. Pada proses pengujian JST pola EEG epilepsy untuk 10 responden data EEG didapatkan nilai detectability sebesar 7778 dan nilai selectivity sebesar 875 sehingga dikatakan sistem dapat mendeteksi pola epilepsi. Pengujian CSP menghasilkan detecbility A4M dan selectivity 100 Pengujian gabungan JST dan CSP menghasilkan nilai detectability sebesar 7778 dan selectivity sebesar 875 . Sehingga JST lebih baik untuk deteksi pola epilepsi dibanding CSP.


ABSTRACT

Altoughh the electric activity of human brain can be detected by medical insrument EEG the fact is the result of EGGs Enchepalograph reading print out from the doctor has a subjective quality because of the complex EEGs output wave. The Neural Network NN method is being used to know the EEGs patern supposed to be more objective. Merger with CSPComposite Parameter Spike expected can add performance system. The back propagation concept of Neural Network with architecture 3 layer in form 50 nodes input layer 25 nodes hidden layer and 3 nodes output layer by preproccess data the fixation factor of learn and weight adaption in a training procces then the test of performance system can be part in to the problem of EEGs wave patern recognition. The data of learning the network is taking from 2 standart EEG patern 1 EEG normal and 1 EEG epilepsy with quantity of the data 100 points and the system is tested by 10 respondens with the new datas form which is tested by error score worth 002. In examining process NN for EEG epilepsy patem by using 10 of EEG data the detecbility value is 7778 and the selectivity value is 875 is so that told system can detect pattern of epilepsi. Examination with CSP yield detecbility 4444 and selectivity 100 . Aliance of NN and CSP yield value of detecbility equal to 7778 and selectivity 875 . So that NN more good to detect pattern of epilepsy compared to CSP.



KeywordsNeural Network; EEG's wave; patern recognition; CSP (Composite Spike Parameter)
 
Subject:  Jaringan komputer
Contributor
  1. Ir. Djoko Purwanto, M.Eng, Ph.D
    Rachmad Setiawan, ST, MT
Date Create: 28/12/2006
Type: Text
Format: pdf ; 80 pages
Language: Indonesian
Identifier: ITS-Master-3100005022910
Collection ID: 3100005022910
Call Number: 006.32 Ari i


Source
Theses Electrical Engineering RTE 006.32 Ari i, 2005

Coverage
ITS Community

Rights
Copyright @2005 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-Master-3100005022910-374.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 54.163.20.123
using CCBot/2.0 (https://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2019 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan