Metode Pemodelan Sistem Menggunakan Pengenalan Pola Berbasis Jaringan Saraf Tiruan (JST)  

Oleh:

Pandjaitan, Lanny W.

Jenis: Article from Journal - ilmiah nasional - tidak terakreditasi DIKTI - atma jaya
Dalam koleksi: Metris: Jurnal Mesin, Elektro, Industri dan Sains vol. 1 no. 1 (Mar. 2000), page 34-44.
Topik: networks; Artifical Neural Network; System Modelling; Pattern Recognition
Fulltext: metode pemodelan.pdf (7.93MB)

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: MM42.1 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

Up to now a system modelling requires the system identdIcation technique and builds the mathematical model using the input-output parameter estimation. This paper will suggest the system modeling use the learning process algorithms of Artificial Neural Network (ANN) that will not use the parameter estimation to build the mathematical model as usual. The model built on the estimation input-output parameter system will perform many times in order to find the minimum error between the estimate output and the desired output system. One of such method is known as the Auto Regressive with extensive variable (ARX). The input-output patterns are the characteristics of the system, are recognized by the ANN after the learning process. The learning process will be performed iteratively for getting the minimum difference between ANN output and desired output patterns. The learning process results are stored into the interconnection synaptic weight of the ANN.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali