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 » S1 Teknik Elektro
Posted by aguss at 04/01/2009 19:29:18  •  8525 Views


IMPLEMENTASI MIKROKONTROLER AVR UNTUK PENGENALAN AUDIO PADA FREKUENSI RENDAH

IMPLEMENTATION AVR MICROCONTROLLER FOR AUDIO RECOGNATION AT LOW FREQUENCY

Author :
Trianto 




ABSTRAK

Suatu sinyal audio yang merupakan sinyal multifrekuensi tersusun atas banyak sinyal sinus penyusun. Dari komposisi penyusunnya sinyal audio dapat dibedakan satu sama lain. Analisa sinyal penyusun dapat dilakukan dengan Transformasi Fourier. Tugas akhir ini mengimplementasikan mikrokontroler AVR untuk membuat suatu pengenal audio pada frekuensi rendah dengan menggunakan tranformasi fourier dan metode Jaringan Syaraf Tiruan backpropagation. Pengenal audio ini digunakan untuk mengategorikan audio kedalam empat kategori berdasarkan frekuensi rendahnya. Sinyal audio diterima menggunakan condenser di sampling dengan jumlah sample 256. Konversi ke bentuk digital dilakukan menggunakan ADC internal mikrokontroler Atmega32. Sinyal kemudian ditransformasi menggunakan Real-Valued Fast Fourier Transform dengan fungsi Hanning window. Hasil transformasi berupa 128 subband dikelompokan menjadi 6 band. Rata-rata dari nilai magnitudo 6 band dari 25 kali penyamplingan ini dikenali dengan menggunakan Jaringan Syaraf Tiruan Backpropagation dengan 6 neuron input layer 15 neuron hidden layer dan 4 neuron output layer. Jenis audio dikenali dan dikategorikan menjadi 4 jenis yaitu berita musik 1 musik 2 dan sinyal input lemah. Dari hasil pengujian didapatkan bahwa proses learning lambat untuk 23 pasangan pembelajaran dibutuhkan 5-9 jam untuk mendapat error total pasangan pembelajaran 0.1. Proses pengenalan dengan input berupa input pembelajaran berhasil dengan baik. Sedangkan input dengan audio lain keberhasilan berkisar 50. Dengan Tugas Akhir ini diharapkan memberikan kontribusi dalam pendesainan peralatan audio sound system.


ABSTRACT

An audio signal is multi frequency signal that consist of large number of sine signal. Audio signal can be recognize base on composition of sine signal. Audio signal analysis can be done using Fourier Transform In this Final Project AVR microcontroller will be implemented to make an audio recognizer at low frequency using fourier transform and artificial neural network This audio recognizer categorize audio in to 4 category base on their low frequency. Audio signal received by condenser and will be sampled the number of sample is 256. Conversion in to digital using internal ADC of ATMega 32 microcontroller. Then signal be transformed using Real-valued Fast Fourier Transform with Hanning Window function. Result of Fourier Transform in the form of 128 point frequency is grouped in to 6 band. Mean of magnitude of band from 25 sampling will is recoqnize using artificial neural network backpropagation with 6 input layer neuron 15 hidden layer neuron and 4 ouput layer neuron. The number of audio type that can be recoqnize is 4 type that is news 1st music 2nd music and low power input signal. From the examination can be concluded that learning process was very slow with 23 learning datathis microcontroller need 5-9 hours to get error 0.1. Recognizing process with input are learning is success. But with other input 50 success. With this final project we hope have contribution in sund system designing.



KeywordsBack-Propagation, Jaringan Syaraf Tiruan, Audio,spektrum, Fast Fourier Transform, Mikrokontroler
 
Subject:  Kontrol elektronis
Contributor
  1. DR. Muhammad Rivai,ST, MT.
Date Create: 04/01/2009
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Undergraduate-3100008031891
Collection ID: 3100008031891
Call Number: RSE 629.89 Tri i


Source
Undergraduate Theses, Electrical Engineering, RSE 629.89 Tri i, 2008

Coverage
ITS Community

Rights
Copyright @2008 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-Undergraduate-3100008031891-3304.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 3.227.2.109
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