Login | Register

Multidimensional Proportional Data Clustering Using Shifted-Scaled Dirichlet Model

Title:

Multidimensional Proportional Data Clustering Using Shifted-Scaled Dirichlet Model

Alsuroji, Rua (2018) Multidimensional Proportional Data Clustering Using Shifted-Scaled Dirichlet Model. Masters thesis, Concordia University.

This is the latest version of this item.

[img]
Preview
Text (application/pdf)
Alsuroji, Rua_MASc_F2018.pdf - Accepted Version
1MB

Abstract

We have designed and implemented an unsupervised learning algorithm for a finite
mixture model of shifted-scaled Dirichlet distributions for the cluster analysis of multivariate
proportional data. The cluster analysis task involves model selection using Minimum
Message Length to discover the number of natural groupings a dataset is composed of.
Also, it involves an estimation step for the model parameters using the expectation maximization
framework. This thesis aims to improve the flexibility of the widely used Dirichlet
model by adding another set of parameters for the location (beside the scale parameter)
We have applied our estimation and model selection algorithm to synthetic generated
data, real data and software modules defect prediction. The experimental results show
the merits of the shifted scaled Dirichlet mixture model performance in comparison to
previously used generative models.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Concordia Institute for Information Systems Engineering
Item Type:Thesis (Masters)
Authors:Alsuroji, Rua
Institution:Concordia University
Degree Name:M.A. Sc.
Program:Quality Systems Engineering
Date:1 September 2018
Thesis Supervisor(s):Bouguila, Nizar
ID Code:984413
Deposited By: Rua Alsuroji
Deposited On:16 Nov 2018 16:45
Last Modified:16 Nov 2018 16:45

Available Versions of this Item

  • Multidimensional Proportional Data Clustering Using Shifted-Scaled Dirichlet Model. (deposited 16 Nov 2018 16:45) [Currently Displayed]
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Back to top Back to top