Machine learning in Intelligent Buildings



AbstractThe purpose of this thesis is to explore the possibilities of developing a low cost intelligent home control system, capable of reducing the power consumption in normal households. This control system will be based on the core concepts of smart environments. The thesis will serve as a research paper on the possibilities of using machine learning algorithms to develop an advanced artificial intelligence, capable of controlling a house hold, and reducing power consumption. We have created a prototype of a smart environment, that serves as a proof of concept, and can be used as the basis for further development. The nal product shows the power of ubiquity computing, as a means of reducing energy consumption in the normal household.
TypeMaster's thesis [Academic thesis]
Year2012
PublisherTechnical University of Denmark, Department of Applied Mathematics and Computer Science
AddressRichard Petersens Plads, Building 324, DK-2800 Kgs. Lyngby, Denmark, compute@compute.dtu.dk
SeriesDTU Compute M.Sc.-2012
NoteDTU supervisor: Christian D. Jensen, cdje@dtu.dk, DTU Compute
Electronic version(s)[pdf]
Publication linkhttp://www.compute.dtu.dk/english
BibTeX data [bibtex]
IMM Group(s)Computer Science & Engineering