Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/154943
DC FieldValue
dc.titleLOCALISED THERMAL COMFORT IN SHARED ROOMS OF EXISTING OFFICE BUILDINGS
dc.contributor.authorSINDHU SANTOSH SHETTY
dc.date.accessioned2019-05-31T18:00:24Z
dc.date.available2019-05-31T18:00:24Z
dc.date.issued2018-09-21
dc.identifier.citationSINDHU SANTOSH SHETTY (2018-09-21). LOCALISED THERMAL COMFORT IN SHARED ROOMS OF EXISTING OFFICE BUILDINGS. ScholarBank@NUS Repository.
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/154943
dc.description.abstractCooling accounts for almost 60% of end-use electricity consumption in Singapore buildings. Despite this, occupants still report thermal discomfort and dissatisfaction. Recently, the thermal comfort paradigm is shifting from traditional ‘one-fit-for-all’ approach to ‘personal comfort models’ where additional personal comfort devices like fans, are used alongside the air-conditioning system to enhance the thermal comfort of occupants and improve the energy efficiency of buildings. This thesis addresses challenges in adopting this approach for operational shared office rooms. Firstly, a localised thermal comfort framework is proposed to facilitate the data collection and deployment of personal thermal comfort models. Secondly, online presence detection methods are developed that detect individual user presence with accuracy over 80% using non-intrusive plugload meters and PIR sensors. Lastly, preference learning methods are developed that predict user desk fan usage preferences with 95% test accuracy using environmental and user presence-related factors.
dc.language.isoen
dc.subjectSmart buildings, Thermal comfort, Internet of things, Machine learning, Presence detection, Desk fan usage preferences
dc.typeThesis
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.contributor.supervisorPANDA, SANJIB KUMAR
dc.description.degreePh.D
dc.description.degreeconferredDOCTOR OF PHILOSOPHY
Appears in Collections:Ph.D Theses (Open)

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
ShettySS.pdf5.99 MBAdobe PDF

OPEN

NoneView/Download

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.