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 » Paper and Presentation » Jaringan Cerdas Multimedia S2
Posted by tondoindra@gmail.com at 22/12/2014 22:59:49  •  1283 Views


IDENTIFIKASI PARASIT MALARIA PADA THICK - BLOOD FILM MENGGUNAKAN ARTIFICIAL NEURAL NETWORK ANN

MALARIA PARASITE IDENTIFICATION IN THICK - BLOOD FILM USING ARTIFICIAL NEURAL NETWORK ANN

Author :
RAHMANTI, FARAH ZAKIYAH ( 2211205202 )




ABSTRAK

Sediaan darah tipis biasanya digunakan untuk mengetahui jenis atau fase dari parasit malaria padahal yang banyak digunakan di Indonesia adalah sediaan darah tebal thick-blood film. Karena susahnya dalam menentukan jenis atau fase pada sediaan darah tebal maka dibutuhkan metode yang dapat mengidentifikasi parasit pada citra sediaan darah tebal dengan prosentase akurasi yang tinggi. Penelitian ini bertujuan membangun sistem klasifikasi yang lebih obyektif dalam mendiagnosis jenis parasit malaria serta fase perkembangannya. Penelitian ini mengidentifikasi parasit malaria pada citra sediaan darah tebal menggunakan artificial neural network ANN. Pada penelitian yang dilakukan memiliki tiga modul utama yaitu modul prapengolahan ekstraksi fitur dan klasifikasi. Pertama modul prapengolahan digunakan untuk proses pengolahan data asli sebelum data tersebut diolah ke dalam proses selanjutnya. Hal ini bertujuan untuk menghilangkan noise dan memperjelas fitur data sesuai kebutuhan. Modul selanjutnya yaitu ekstraksi fitur dengan pendekatan histogram warna komponen red histogram warna komponen green histogram warna komponen blue histogram HSV Hue Saturation Value komponen hue dan histogram HSI Hue Saturation Intensity komponen hue. Modul yang terakhir adalah modul klasifikasi yang bertujuan mengklasifikasikan citra parasit atau bukan parasit kemudian mengklasifikasikan berdasarkan jenis dan fasenya. Data citra parasit malaria dan bukan parasit yang digunakan dalam penelitian ini diperoleh dari Dinas Kesehatan Provinsi Jawa Timur. Hasil penelitian yang telah dilakukan dinyatakan bahwa klasifikasi menggunakan ANN dengan data latih dan data uji masing-masing 120 dan 60 untuk identifikasi terhadap 2dua kelas didapatkan nilai akurasi sebesar 9467 bukan parasit dan 94 parasit sedangkan akurasi terhadap 6enam kelas sebesar 9433 bukan parasit 7933 vivax thropozoit 82 vivax schizont 85 vivax gametocyte 93 falciparum thropozoit 8633 falciparum gametocyte. Kemudian hasil penelitian menggunakan ANN dengan data latih dan data uji masing-masing 60 dan 120 untuk identifikasi terhadap 2dua kelas didapatkan nilai akurasi sebesar 9298 bukan parasit dan 97 parasit sedangkan akurasi terhadap 6enam kelas sebesar 8850 bukan parasit 8033 vivax thropozoit 7333 vivax schizont 7750 vivax gametocyte 89 falciparum thropozoit 86 falciparum gametocyte.


ABSTRACT

The thin blood film is always used to know type and phase of the malaria parasite but which is widely used in Indonesia is the thick-blood film. Therefore we need a method that can identify parasites in thick blood film image with a high percentage of accuracy. This research aims to establish a more objective classification system and reduce the subjective factors of medical personnel in diagnosing the type of malaria parasite include its phase. The research identifies malaria parasites in thick blood films using artificial neural network ANN. It has three main stages there are preprocessing module feature extraction module and classification module. First stage is preprocessing module it is used for process of the original data before the data are processed into the next step. It aims to eliminate the noise clarify the features of data and prepare the original data into next stage processing. The next module is feature extraction using red channel color histogram green channel color histogram blue channel color histogram hue channel HSV Hue Saturation Value histogram and hue channel HSI Hue Saturation Intensity histogram. The last stage is classification module which aims to identify the thick blood film images that contains infected parasites and also to detect type and phase of the parasite. Image of malaria parasites were obtained from East Java Health Department. Outcome of research using ANN that has been conducted on 180 thick blood film images 120 data training 60 data testing that clasified into 2 two classes. Testing result have an average accuracy of 94.67 not parasites and 94 parasites. Meanwhile when system is used to classified into 6 six classes testing result have an average accuracy of 94.33 not parasites 79.33 vivax thropozoit 82 vivax schizont 85 vivax gametocytes 93 falciparum thropozoit 86.33 falciparum gametocytes. Then outcome of research using ANN with 60 data training 120 data testing that clasified into 2 two classes. Testing result have an average accuracy of 92.98 not parasites and 97 parasites. Meanwhile when system is used to clasified into 6 six classes testing result have an average accuracy of 88.50 not parasites 80.33 vivax thropozoit 73.33 vivax schizont 77.50 vivax gametocytes 89 falciparum thropozoit 86 falciparum gametocytes.



Keywordsmalaria; parasit; plasmodium vivax; plasmodium falciparum; ekstraksi fitur; klasifikasi; artificial neural network (ANN); feed-forward backpropagation
 
Subject:  Perangkat lunak komputer ; Jaringan syaraf tiruan
Contributor
  1. Prof. Ir. Mauridhi Hery Purnomo, M.Eng, Ph.D
  2. Dr. I Ketut Eddy Purnama, S.T.,M.T
Date Create: 21/07/2013
Type: Text
Format: PDF
Language: Indonesian
Identifier: ITS-paper-22121140006667
Collection ID: 22121140006667
Call Number: RTE 006.32 Rah i


Source
Paper And Presentation of Electrical Engineeing RTE 006.32 Rah i, 2014

Coverage
ITS Community

Rights
Copyright @2013 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 - Summary ]

ITS-paper-22121140006667-34984.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 54.162.166.214
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