Show simple item record

dc.contributor.advisorKruse, Jan
dc.contributor.advisorConnor, Andy
dc.contributor.authorRameka, Adam Norman Adrian
dc.date.accessioned2018-06-27T00:58:42Z
dc.date.available2018-06-27T00:58:42Z
dc.date.copyright2018
dc.identifier.urihttp://hdl.handle.net/10292/11617
dc.description.abstractWith the proliferation of relatively cheap Internet of Things (IoT) devices, Smart Environments have been highlighted as an example of how the IoT can make our lives easier. Each of these ‘things’ produces data which can work in unison with other devices to create an environment that can react to its users. Machine learning makes use of this data to make inferences about our habits and activities, such as our buying preferences or likely commute destinations. However, this level of human inclusion within the IoT relies on indirect inferences from the usage of these devices or services. Alternatively, Activity Recognition is already a widely researched domain and could provide a more direct way of including humans within this system. With the intended application in the IoT, this research explores the feasibility of using a cost-effective, unobtrusive, single modality ground-based sensor to track subtle direct, and indirect pressure changes. With the subsequent data, a number of machine learning classification approaches are utilised to assess the sensor's performance in activity recognition. The results indicate that accuracy in Activity Recognition classification is generally high and provides a basis for further investigation as an interface to more complex digital systems, such as the IoT.en_NZ
dc.language.isoenen_NZ
dc.publisherAuckland University of Technology
dc.subjectActivity recognitionen_NZ
dc.subjectInternet of Thingsen_NZ
dc.subjectHuman and Computer Interactionen_NZ
dc.subjectHCIen_NZ
dc.subjectIOTen_NZ
dc.subjectMachine Learningen_NZ
dc.subjectSensor trackingen_NZ
dc.subjectComputer Interfacesen_NZ
dc.subjectSmart Environmentsen_NZ
dc.subjectSmart Obejctsen_NZ
dc.subjectClassificationen_NZ
dc.titleEvaluating a single-modality ground-based activity recognition sensor for human inclusion into digital systemsen_NZ
dc.typeThesisen_NZ
thesis.degree.grantorAuckland University of Technology
thesis.degree.levelMasters Theses
thesis.degree.nameMaster of Creative Technologiesen_NZ
dc.rights.accessrightsOpenAccess
dc.date.updated2018-06-26T22:55:35Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record