An Investigation and Application of Biology and Bioinformatics for Activity Recognition
Access Status
Open access
Authors
Riedel, Daniel Erwin
Date
2014Supervisor
Assoc. Prof. Wan-Quan Liu
Prof. Svetha Venkatesh
Type
Thesis
Award
PhD
Metadata
Show full item recordSchool
Department of Computing
Collection
Abstract
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.
Related items
Showing items related by title, author, creator and subject.
-
Tugiyono (2001)The environmental health of aquatic ecosystems depends amongst others, on the chemical pollution coming from activities in the catchment's area. In the Swan River Estuary, Western Australia, the chemical pollutants of ...
-
Apikomonkon, Hataichanok (2003)Numerous Thai older people fall each year. Although it has been shown that only 3.1% of fallers sustained fractures (Nevitt, Cumming, Kidd, & Black, 1989), injuries in older people are often more serious. For example, ...
-
Beales, Darren (2009)Aberrant motor control strategies have been identified in chronic pelvic girdle pain (PGP) subjects. It has been proposed that aberrant motor control strategies could provide a mechanism for ongoing pain and disability ...