UI - Tesis Membership :: Back

UI - Tesis Membership :: Back

Pengembangan metode prediksi multi-step ahead (MSA) pada sistem chaos menggunakan som RBFNN = Development of multi-step ahead (MSA) prediction method for chaotic system using som RBFNN / Akhmad Faqih

Akhmad Faqih; Benyamin Kusumoputro, supervisor; Wahidin Wahab, examiner; Feri Yusifar, examiner; Abdul Halim, examiner ([Publisher not identified] , 2018)

 Abstract

ABSTRAK
Pada masa sekarang ini, teknologi semakin berkembang dan terus berkembang dengan cepat. Terutama kebutuhan adanya teknologi prediksi yang memerlukan pengembangan lebih dalam lagi sehingga dapat menghasilkan teknologi yang dapat memprediksi masa depan Multi-Step Ahead MSA secara lebih akurat. Salah satunya untuk teknologi prediksi peramalan cuaca sistem Chaos yang dapat membantu masyarakat dalam mempersiapkan aktifitas yang akan dilakukan. Penelitian ini melakukan simulasi percobaan penerapan Jaringan Saraf Tiruan berbasis Radial Basis Function RBF pada sistem prediksi data Chaos, data Lorenz dan data Mackey-Glass. Berdasarkan hasil percobaan dapat dilihat dari nilai bahwa penerapan jaringan saraf tiruan berbasis Radial Basis Function RBF memiliki tingkat keakuratan yang baik untuk memprediksi lebih dari 100 langkah kedepan.

ABSTRACT
Recently, technologies have been growing and growing fast. Especially, the need of prediction technology that need to be developed more so that it could create a technology that is capable to predict the future Multi Step Ahead MSA more accurate. One of the applied field of this prediction method is for forecasting Chaotic System which help the society in order to prepare their activity that will be scheduled. This research performs simulation experiments in applying the Artificial Neural Network based on Radial Basis Function RBF of prediction system for chaotic data, Mackey Glass equation and Lorenz rsquo s system. As can be seen from the values of the experimental results, applying Artificial Neural Network based on Radial Basis Function results high accuracy for predicting more than 100 steps ahead.

 Digital Files: 1

Shelf
 T51190-Akhmad Faqih.pdf :: Download

LOGIN required

 Metadata

Collection Type : UI - Tesis Membership
Call Number : T51190
Main entry-Personal name :
Additional entry-Personal name :
Additional entry-Corporate name :
Study Program :
Subject :
Publishing : [Place of publication not identified]: [Publisher not identified], 2018
Cataloguing Source LibUI ind rda
Content Type text
Media Type unmediated ; computer
Carrier Type volume ; online resource
Physical Description xvi, 88 pages : illustration ; 28 cm + appendix
Concise Text
Holding Institution Universitas Indonesia
Location Perpustakaan UI, Lantai 3
  • Availability
  • Review
  • Cover
Call Number Barcode Number Availability
T51190 15-19-810648744 TERSEDIA
Review:
No review available for this collection: 20476039
Cover