Relevance prevails : missing data treatment in intelligent lighting

A. Kota Gopalakrishna, T. Özçelebi, A. Liotta, J.J. Lukkien

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Downloads (Pure)

Abstract

Generally, in machine learning applications, the problem of missing data has significant effect on the prediction performance. For a given missing data problem, it is not straightforward to select a treatment approach in combination with a classification model due to several factors such as the pattern of data and nature of missing data. The selection becomes more difficult for applications such as intelligent lighting, where there is high degree of randomness in the pattern of data. In this paper, we study pairs of probabilistic missing data treatment methods and classification models to identify the best pair for a dataset gathered from an office environment for intelligent lighting.We evaluate the performance in simulations using a new metric called Relevance Score. Experimental results show that the CPOF (Conditional Probability based only on the Outcome and other Features) method in combination with the DecisionTable (DT) classifier is the most suitable pair for implementation. Keywords: intelligent lighting; missing data; machine learning; classification models; relevance metric
Original languageEnglish
Title of host publicationMan-Machine Interactions 3 (Proceedings 3rd International Conference on Man-Machine Interactions, ICMMI 2013, Brenna, Poland, October 22-25, 2013)
EditorsA. Gruca, T. Czachórski, S. Kozielski
Place of PublicationHeidelberg
PublisherSpringer
Pages369-376
ISBN (Print)978-3-319-02308-3
DOIs
Publication statusPublished - 2013
Eventconference; 3rd International Conference on Man-Machine Interaction; 2013-10-22; 2013-10-25 -
Duration: 22 Oct 201325 Oct 2013

Publication series

NameAdvances in Intelligent Systems and Computing
Volume242
ISSN (Print)2194-5357

Conference

Conferenceconference; 3rd International Conference on Man-Machine Interaction; 2013-10-22; 2013-10-25
Period22/10/1325/10/13
Other3rd International Conference on Man-Machine Interaction

Fingerprint Dive into the research topics of 'Relevance prevails : missing data treatment in intelligent lighting'. Together they form a unique fingerprint.

Cite this