SPEED: An Inhabitant Activity Prediction Algorithm for Smart Homes

Author

Alam, Mohammad Rafiqul ; Reaz, Mamun Bin Ibne ; Mohd Ali, M.A.

Author_Institution

Inst. of Microeng. & Nanoelectronic, Univ. Kebangsaan Malaysia, Bangi, Malaysia

Volume

42

Issue

4

fYear

2012

fDate

7/1/2012 12:00:00 AM

Firstpage

985

Lastpage

990

Abstract

This paper proposes an algorithm, called sequence prediction via enhanced episode discovery (SPEED), to predict inhabitant activity in smart homes. SPEED is a variant of the sequence prediction algorithm. It works with the episodes of smart home events that have been extracted based on the on -off states of home appliances. An episode is a set of sequential user activities that periodically occur in smart homes. The extracted episodes are processed and arranged in a finite-order Markov model. A method based on prediction by partial matching (PPM) algorithm is applied to predict the next activity from the previous history. The result shows that SPEED achieves an 88.3% prediction accuracy, which is better than LeZi Update, Active LeZi, IPAM, and C4.5.

Keywords

Markov processes; domestic appliances; feature extraction; home automation; pattern matching; prediction theory; ubiquitous computing; PPM algorithm; SPEED; events extraction; finite-order Markov model; home appliances; inhabitant activity prediction algorithm; on-off states; partial matching algorithm; sequence prediction algorithm; sequence prediction via enhanced episode discovery; sequential user activities; smart homes; Accuracy; Complexity theory; Context; Humans; Markov processes; Prediction algorithms; Smart homes; Activity prediction; Markov model; prediction algorithm; prediction by partial matching (PPM); smart home;

fLanguage

English

Journal_Title

Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on

Publisher

ieee

ISSN

1083-4427

Type

jour

DOI

10.1109/TSMCA.2011.2173568

Filename

6097066