An Investigation and Application of Biology and Bioinformatics for Activity Recognition

Activity recognition in a smart home context is inherently difficult due to the variable nature of human activities and tracking artifacts introduced by video-based tracking systems. This thesis addresses the activity recognition problem via introducing a biologically-inspired chemotactic approach a...

Full description

Bibliographic Details
Main Author: Riedel, Daniel Erwin
Format: Thesis
Language:English
Published: Curtin University 2014
Online Access:http://hdl.handle.net/20.500.11937/514
_version_ 1848743400025620480
author Riedel, Daniel Erwin
author_facet Riedel, Daniel Erwin
author_sort Riedel, Daniel Erwin
building Curtin Institutional Repository
collection Online Access
description Activity recognition in a smart home context is inherently difficult due to the variable nature of human activities and tracking artifacts introduced by video-based tracking systems. This thesis addresses the activity recognition problem via introducing a biologically-inspired chemotactic approach and bioinformatics-inspired sequence alignment techniques to recognise spatial activities. The approaches are demonstrated in real world conditions to improve robustness and recognise activities in the presence of innate activity variability and tracking noise.
first_indexed 2025-11-14T05:44:58Z
format Thesis
id curtin-20.500.11937-514
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T05:44:58Z
publishDate 2014
publisher Curtin University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-5142017-02-20T06:42:29Z An Investigation and Application of Biology and Bioinformatics for Activity Recognition Riedel, Daniel Erwin Activity recognition in a smart home context is inherently difficult due to the variable nature of human activities and tracking artifacts introduced by video-based tracking systems. This thesis addresses the activity recognition problem via introducing a biologically-inspired chemotactic approach and bioinformatics-inspired sequence alignment techniques to recognise spatial activities. The approaches are demonstrated in real world conditions to improve robustness and recognise activities in the presence of innate activity variability and tracking noise. 2014 Thesis http://hdl.handle.net/20.500.11937/514 en Curtin University fulltext
spellingShingle Riedel, Daniel Erwin
An Investigation and Application of Biology and Bioinformatics for Activity Recognition
title An Investigation and Application of Biology and Bioinformatics for Activity Recognition
title_full An Investigation and Application of Biology and Bioinformatics for Activity Recognition
title_fullStr An Investigation and Application of Biology and Bioinformatics for Activity Recognition
title_full_unstemmed An Investigation and Application of Biology and Bioinformatics for Activity Recognition
title_short An Investigation and Application of Biology and Bioinformatics for Activity Recognition
title_sort investigation and application of biology and bioinformatics for activity recognition
url http://hdl.handle.net/20.500.11937/514