Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Indonesian Journal of Electrical Engineering and Computer Science eProceedings of Engineering
Iwan Iwut
Telkom University
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Optimization of Discrete Cosine Transform-Based Image Watermarking by Genetics Algorithm Iwan Iwut; Gelar Budiman; Ledya Novamizanti
Indonesian Journal of Electrical Engineering and Computer Science Vol 4, No 1: October 2016
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v4.i1.pp91-103

Abstract

data in an image file is needed by its owner to set his ownership in a logo as a watermark embedded in the image file. Hiding the logo in the image was done in several methods. One of the method is domain transform using 2D-DCT in which data is embedded in  frequency domain of the image. First, the host RGB image is converted to certain color space. The available and chosen color spaces are RGB, YCbCr or NTSC. The layer in which the watermark is embedded also can be selected. The available choices are 1st layer, 2nd layer, 3rd layer, 1st & 2nd layer, 2nd & 3rd  layer, 1st & 3rd layer and all layers.  After the selected layer of image in certain color space is transformed in block based to frequency domain by DCT, one bit watermark is embedded on the AC coefficient of each block such a way that the bit is represented by specific value called delta in a zigzag and vary length of pixel. The vary parameters optimized by Genetics Algorithm are  selected color space, selected layer, block size, length of pixel to be embedded by one bit watermark, and delta. Bit “1” is represented by +delta, and bit “0” is represented by –delta in vary length of pixel after zigzag. The simulation result performs that GA is useful to search the value of parameter that produces controllable the combination between robustness, invisibility and capacity. Thus, GA improves the  method by determining the exact value of parameter achieving BER, PSNR and payload.  
Simulasi Dan Analisis Speaker Recognition Menggunakan Metode Mel Frequency Cepstrum Coefficient (mfcc) Dan Gaussian Mixture Model (gmm) Doanda Khabi Putra; Iwan Iwut; Ratri Dwi Atmaja
eProceedings of Engineering Vol 4, No 2 (2017): Agustus, 2017
Publisher : eProceedings of Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Tugas akhir ini membahas mengenai pengenalan pembicara (speaker recognition), yaitu mekanisme pengenalan identitas subjek berdasarkan ciri suaranya. Pertama, sinyal suara subjek yang diuji diekstraksi cirinya menggunakan metode MFCC (Mel Frequency Cepstrum Coefficient). Tahapan di dalam MFCC termasuk diantaranya adalah pre-emphasis, framing, windowing, FFT (Fast Fourier Transform), mel scaling dan DCT (Discrete Cosine Transform), yang mana keluaran MFCC adalah feature vector yang dinamakan cepstrum. Selanjutnya, cepstrum dari masing-masing subjek akan dimodelkan menggunakan metode GMM (Gaussian Mixture Model). Tahapan di dalam GMM termasuk diantaranya adalah Expectation-step dan Maximization-step, yang mana keluaran GMM adalah distribusi Gaussian dengan parameter mean (µ) dan variance ( ) yang unik untuk masingmasing subjek. Proses klasifikasi dilakukan dengan membandingkan parameter distribusi Gaussian antara data latih dan data uji. Pada penelitian internasional sebelumnya oleh kelompok mahasiswa di Preston University dan Jinnah Women University, Pakistan, dengan judul “Speaker Identification Using GMM with MFCC” diperoleh akurasi sebesar 87.5% dengan metode ekstraksi ciri MFCC, metode clustering K-Means, metode modelling GMM dan diklasifikasikan menggunakan log probability. Pada tugas akhir ini, kita akan melewatkan tahap clustering dan tahap klasifikasi dilakukan dengan melakukan perbandingan pada distribusi Gaussian memanfaatkan parameter mean (µ) dan variance ( ), dimana merupakan cara paling cepat dan mudah. Pada tugas akhir ini, diusahakan akurasi yang didapat mampu mendekati penelitian yang sudah ada mengingat tahap klasifikasi yang digunakan bisa dikatakan cara ‘kasar’ dalam penggunaan Gaussian Mixture Model (GMM) sehingga tidak bisa diekspektasikan lebih baik, meskipun banyak faktor lain yang bisa mempengaruhi akurasi simulasi. Kata kunci: Speaker recognition, Mel Frequency Cepstrum Coefficient (MFCC), Gaussian Mixture Model (GMM), Expectation Maximization (EM)
Co-Authors Doanda Khabi Putra Gelar Budiman Ledya Novamizanti Ratri Dwi Atmaja