Time Series Prediction Using Recurrent Neural Networks And Boosting: An Experimental Study In Pharmaceutical Product Formulation

Goh, Wei Yee (2002) Time Series Prediction Using Recurrent Neural Networks And Boosting: An Experimental Study In Pharmaceutical Product Formulation. Masters thesis, Universiti Sains Malaysia.

[img]
Preview
PDF
Download (641kB) | Preview

Abstract

Tesis ini berpusat pada perkembangan teknik Rangkaian Neural Buatan (ANN) dalam menyelesaikan masalah-masalah ramalan siri masa. Penyelidikan ini tertumpu kepada penggunaan·- rangkaian-rangkaian neural perulangan yang menyediakan satu kerangka yang menyeluruh bagi fonnulasi produk fannasi melalui pendekatan ramalan siri masa. Khususnya, kerangka ini telah menjelajahi paradigma pembelajaran ANN dalam mengendalikan perancangan eksperimen dan analisis. Berdasarkan kepada kaedah-kaedah yang sedia ada, reka bentuk ANN yang baru dicadangkan untuk analisis siri masa di dalam proses formulasi produk fannasi. This thesis is devoted to the development of Artificial Neural Network (ANN) techniques for solving time-series prediction problems. The research is focused on the use of recurrent neural networks for devising a comprehensible framework for pharmaceutical product formulation using time series prediction approach. In particular, the framework explores the learning paradigms of ANNs for conducting the experimental design and analysis. Based upon existing methodologies, novel ANN architectures are proposed for time series analyses in the process of pharmac~utical product formulation.

Item Type: Thesis (Masters)
Subjects: T Technology > TK Electrical Engineering. Electronics. Nuclear Engineering > TK1-9971 Electrical engineering. Electronics. Nuclear engineering
Divisions: Kampus Kejuruteraan (Engineering Campus) > Pusat Pengajian Kejuruteraaan Elektrik & Elektronik (School of Electrical & Electronic Engineering) > Thesis
Depositing User: HJ Hazwani Jamaluddin
Date Deposited: 06 Sep 2016 07:22
Last Modified: 31 May 2017 05:06
URI: http://eprints.usm.my/id/eprint/30471

Actions (login required)

View Item View Item
Share