Routine learning: analyzing your whereabouts

Author

Pirttikangas, Susanna ; Riekki, Jukka ; Röning, Juha

Author_Institution

Dept. of Electr. & Inf. Eng., Oulu Univ., Finland

Volume

2

fYear

2004

fDate

5-7 April 2004

Firstpage

208

Abstract

A routine is a temporal context sequence that occurs often. In routine learning, already recognized contexts are utilized in modeling the user behavior. The methodology is presented via a use case scenario. Data collected from various ubiquitous sensors are used in recognizing and defining contexts, and association rules determine the routines. The focus is on testing the suitability of the apriori algorithm for this application area. Several useful routines were derived from the user data, and the results show that data mining can be utilized in pervasive computing.

Keywords

data mining; knowledge based systems; learning (artificial intelligence); mobile handsets; ubiquitous computing; apriori algorithm; association rules; data mining; machine learning; pervasive computing; routine learning; temporal context sequence; ubiquitous sensors; user behavior modeling; Algorithm design and analysis; Association rules; Calendars; Context modeling; Data analysis; Data mining; Intelligent systems; Machine learning algorithms; Pervasive computing; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Technology: Coding and Computing, 2004. Proceedings. ITCC 2004. International Conference on

Print_ISBN

0-7695-2108-8

Type

conf

DOI

10.1109/ITCC.2004.1286633

Filename

1286633