Article Per Year (5 Year)
p-Index From 2019 - 2024
0
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Indonesian Journal of Artificial Intelligence and Data Mining Seminar Nasional Teknologi Informasi Komunikasi dan Industri
Elvia Budianita
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Industrial & Manufacturing Engineering Mathematics

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Penerapan Learning Vector Quantization (LVQ) untuk Klasifikasi Status Gizi Anak Elvia Budianita; Widodo Prijodiprodjo
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 7, No 2 (2013): July
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.3354

Abstract

AbstrakPenentuan klasifikasi status gizi anak yang sering dilakukan adalah berdasarkan indeks berat badan menurut tinggi badan (BB/TB). Pada Puskesmas Batupanjang, indeks antropometri tersebut dihitung secara manual untuk menilai status gizi anak sekolah dasar dengan menggunakan daftar tabel z-skor atau simpangan baku / standar deviasi (SD) WHO NCHS (National Centre for Health Statistic). Metode Learning Vektor Quantization (LVQ) dan salah satu algoritma pengembangannya yaitu LVQ3 digunakan dalam penelitian ini untuk menangani penilaian status gizi anak berdasarkan simpangan baku rujukan terhadap indeks berat badan dan tinggi badan tersebut. Variabel yang digunakan dalam penilaian status gizi anak adalah jenis kelamin, berat badan, tinggi badan, penyakit infeksi, nafsu makan, dan pekerjaan kepala keluarga (KK). Berdasarkan dari hasil penelitian dan pembahasan yang dilakukan, algoritma LVQ3 lebih baik diterapkan untuk klasifikasi status gizi anak dibandingkan dengan algoritma LVQ1. Penggunaan parameter window (ε) pada jaringan syaraf tiruan LVQ3 memberikan pengaruh positif yakni dapat meningkatkan performa dalam klasifikasi jika dibandingkan tanpa menggunakan window (LVQ1). Kata kunci— Antropometri,  Learning Vektor Quantization,  Z-skor.  AbstractThe shortest path determination of child nutrient that common uses is based on body weight index by body high level (BB/BT). In Batupanjang Puskesmas, that anthropometry index is calculated manually for assessing  the nutrition of children in elementary school by used z-score table list or deviation standard  (SD) WHO NCHS (National Centre for Health Statistic).Learning Vektor Quantization (LVQ) Method and one of its algorithm, LVQ3 is used for this research to handle appraisal of children nutrition status based on deviation standard reference for that weight and high index. The variable that used in this appraisal are genre, body weight, body high, infection disease, appetite, and father work.Based on result of this research and discuss that has been done, LVQ3 algorithm is better applied for children nutrient status classification than LVQ1 algorithm. Using of window parameter (ε) in neural network LVQ3 effect positive impact, that is can increase perform in classification than without used window (LVQ1). Keywords—Anthropometry,  Learning Vektor Quantization,  Z-score.
Implementation of Backpropagation Neural Network to Detect Suspected Lung Disease Fadhilah Syafria; Boni Iqbal; Elvia Budianita; Iis Afrianty
Indonesian Journal of Artificial Intelligence and Data Mining Vol 1, No 1 (2018): March 2018
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (519.707 KB) | DOI: 10.24014/ijaidm.v1i1.5023

Abstract

Many People were less concerned with lung health, it caused people identified as suffering from lung diseases. Early symptoms that often appear  was cough that took a long time and could be the beginning of more severe disease. Therefore it was necessary to create application that could detect suspected person contracted lung disease. The applications were made by using artificial neural network with Backpropagation with initial input data, symptoms by patients of lung diseases. The symptoms were 22, and kind of lung diseases as a diagnosis were asthma, pneumonia, pulmonary tuberculosis and lung cancer. It used medical records of lung disease as much as 110 data. Network training uses 3 different architectures [input neurons ; hidden neurons ; output neurons], liked [22; 22 ; 2], [22 ; 33 ; 2] and [22 ; 43 ; 2]. Testing with 2 training data sharing and test data, namely comparison 90:10 and 80:20. The Parameters values were used namely learning rate 0.1, 0.3, 0.5, 0.7 and 0.9. The number of epoch was used, that is 15 epoch, 25 epoch and 35 epoch. Based on the tests performed, it was obtained an accuracy system on the 90:10 data comparison of 82% and the 80:20 data ratio of 82% as well. Thus, backpropagation method could be applied in detecting suspected lung diseases.
IMPLEMENTASI METODE SEGMENTASI DAN LVQ UNTUK IDENTIFIKASI CITRA DAGING SAPI DAN BABI Jasril Jasril; Lestari Handayani; Elvia Budianita; Fikri Utri Amri
Seminar Nasional Teknologi Informasi Komunikasi dan Industri 2017: SNTIKI 9
Publisher : UIN Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1039.897 KB)

Abstract

Tingginya permintaan daging sapi menjadi celah bagi pedagang nakal untuk melakukan pencampuran daging sapi dengan daging babi (oplosan). Hal ini sangat merugikan konsumen khususnya umat  muslim yang diharamkan mengkonsumsi daging babi. Pada penelitian ini dibangun system pengolahan citra untuk mengidentifikasi daging sapi dan babi.Terdapat dua tahapan dalam proses identifikasi yaitu tahap pelatihan (training) dan pengujian (testing). Pengambilan data latih dan uji (citradaging) menggunakan 3 jenis kamera yaitu kamera DSLR Canon EOS 70D, CAMDIG Sony DSC-W810 dan HP Lenovo A369i. Proses  identifikasi dimulai dengan melakukan segmentasi citra menggunakan metode Spatial Fuzzy C-Means untuk memisahkan objek (daging) dan background. Setelah diperoleh objek kemudian dilakukan  proses  ekstraksi ciri warna menggunakan metode HSV dan ciri tekstur dengan GLCM. Berdasarkan nilai hasil ekstrasi ciri warna (HSV) dan tekstur (GLCM), dilakukan proses klasifikasi menggunakan Learning Vector Quatization (LVQ). Data yang digunakan sebanyak 65 dengan dua variasi yaitu pertama jumlah data latih 50 dan data uji 15 serta jumlah data latih 30 dan data uji 15. Pengujian dilakukan dengan berbagai learning rate (α) yaitu 0.03, 0.05, 0.075 dan 0.1. Hasil pengujian memperlihatkan sistem yang dibangun dapat mengenali citra daging sapi dan citra daging babi dengan persentase nilai akurasi tertinggi 80 % dengan nilai learning rate (α) 0.1 dan jumlah data latih 30, nilai minimal learning rate (Mina) yang digunakan adalah 0,01 dan nilai pengurangan α adalah 0,1.
Co-Authors Boni Iqbal Fadhilah Syafria Fikri Utri Amri Iis Afrianty Jasril Jasril Widodo Prijodiprodjo