Abnormal Action Detection Based on Markov Models

P. A. Osipov and A. N. Borisov

Riga Technical University, Kalku 1, Riga, LV-1658 Latvia

E-mail: pavels.osipovs@gmail.com, arkadijs.borisovs@cs.rtu.lv

Abstract—The task of using Markov chains to develop a statistical behavioral model of a DS user to
detect abnormal activity is described. In order to verify the assumption about the possibility of using this
method in electronic health records, a program system was developed. The experiments with the system
showed that the approach in question could be efficiently applied in abnormal action detection, for exam-
ple, in data systems handling sensitive information.

Keywords: Markov chain, intruder detection system, abnormal action detection, electronic health
record.

DOI: 10.3103/S0146411611020052

Pleiades Publishing home page | journal home page | top

If you have any problems with this server, contact webmaster.