Identification of Vessel Anomaly Behavior Using Support Vector Machines and Bayesian Networks

Author

Handayani, D.O.D. ; Sediono, W. ; Shah, A.

Author_Institution

Dept. of Comput. Sci., Inf. & Commun. Technol., Int. Islamic Univ. of Malaysia, Gombak, Malaysia

fYear

2014

fDate

23-25 Sept. 2014

Firstpage

258

Lastpage

261

Abstract

In this work, a model based on Support Vector Machines (SVMs) classification to identify vessel anomaly behavior has been proposed and implemented. The results are compared to Bayesian Networks (BNs). The real world Automated Identification System (AIS) vessel reporting data is used in this work. The results shows that SVMs can achieve higher accuracy compared to BNs in both memory-test and blind-test. The effect of holdout method which are partitioned size of training and testing data set on the accuracy result are also investigated in this study. The proposed classifier demonstrates to be a viable tool for identifying the vessel anomaly behavior by its accuracy.

Keywords

belief networks; marine engineering; marine safety; pattern classification; security of data; support vector machines; surveillance; AIS vessel reporting data; BN; Bayesian networks; SVM classification; automated identification system; blind-test; holdout method; maritime surveillance; memory-test; support vector machines; vessel anomaly behavior identification; Abstracts; Accuracy; Computers; Informatics; Surveillance; Testing; Training; Anomaly Behaviour; BNs; Holdout; Maritime Surveillance; SVMs;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Communication Engineering (ICCCE), 2014 International Conference on

Conference_Location

Kuala Lumpur

Type

conf

DOI

10.1109/ICCCE.2014.80

Filename

7031651