Automatically Selecting Parameters for Graph-Based Clustering

Data streams present a number of challenges, caused by change in stream concepts over time. In this thesis we present a novel method for detection of concept drift within data streams by analysing geometric features of the clustering algorithm, RepStream. Further, we present novel methods for automa...

Full description

Bibliographic Details
Main Author: Callister, Ross
Format: Thesis
Published: Curtin University 2020
Online Access:http://hdl.handle.net/20.500.11937/80407
_version_ 1848764213422456832
author Callister, Ross
author_facet Callister, Ross
author_sort Callister, Ross
building Curtin Institutional Repository
collection Online Access
description Data streams present a number of challenges, caused by change in stream concepts over time. In this thesis we present a novel method for detection of concept drift within data streams by analysing geometric features of the clustering algorithm, RepStream. Further, we present novel methods for automatically adjusting critical input parameters over time, and generating self-organising nearest-neighbour graphs, improving robustness and decreasing the need to domain-specific knowledge in the face of stream evolution.
first_indexed 2025-11-14T11:15:47Z
format Thesis
id curtin-20.500.11937-80407
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:15:47Z
publishDate 2020
publisher Curtin University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-804072020-08-05T04:49:05Z Automatically Selecting Parameters for Graph-Based Clustering Callister, Ross Data streams present a number of challenges, caused by change in stream concepts over time. In this thesis we present a novel method for detection of concept drift within data streams by analysing geometric features of the clustering algorithm, RepStream. Further, we present novel methods for automatically adjusting critical input parameters over time, and generating self-organising nearest-neighbour graphs, improving robustness and decreasing the need to domain-specific knowledge in the face of stream evolution. 2020 Thesis http://hdl.handle.net/20.500.11937/80407 Curtin University fulltext
spellingShingle Callister, Ross
Automatically Selecting Parameters for Graph-Based Clustering
title Automatically Selecting Parameters for Graph-Based Clustering
title_full Automatically Selecting Parameters for Graph-Based Clustering
title_fullStr Automatically Selecting Parameters for Graph-Based Clustering
title_full_unstemmed Automatically Selecting Parameters for Graph-Based Clustering
title_short Automatically Selecting Parameters for Graph-Based Clustering
title_sort automatically selecting parameters for graph-based clustering
url http://hdl.handle.net/20.500.11937/80407