Please use this identifier to cite or link to this item:
Title: Investigation of image processing algorithms for medical application
Authors: Tijani, Zhafir Aglna
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2015
Abstract: Gene Regulatory Network is the network that constitute the interaction between genes. There is a need to find an effective way for the discovery of gene regulatory network which will provide better information for further advancement in biotechnology and bioinformatics. One of the prominent approach to analyse GRN is Granger Causality Analysis. This project tries to perform comparative study between different implementation of granger causality. Specifically Multivariate Granger Causality (MVGC), Lasso Granger Causality, and Copula Granger Causality. These three methods are previously researched by other researcher, but never been compared side to side under the same condition. The project was implemented with experimental framework that utilizes 3 control variables and 7 metrics. These 7 metrics are the basis for the comparative study of the project itself. Based on the findings in the experiment, overall score favours MVGC methods as the best algorithm. However in some condition, Lasso and Copula score exceeds MVGC which indicates that the results are conditional, not absolute. It could be said that each method has the condition that maximizes their performance. This project provides analysis of these situations based on the experiment result.
Schools: School of Electrical and Electronic Engineering 
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP - Zhafir - FinalReport.pdf
  Restricted Access
FYP Report1.65 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 23, 2024


Updated on Jun 23, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.