An Investigation and Application of Biology and Bioinformatics for Activity Recognition
MetadataShow full item record
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.
Showing items related by title, author, creator and subject.
Metabolic enzymes and mixed-function oxygenase (MFO) system in pink snapper (Pagrus auratus): biochemical and histological relationshipsTugiyono (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, ...
Motor control during an active straight leg raise in pain free and chronic pelvic girdle pain subjectsBeales, 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 ...