IIUM Repository

Identification of vessel anomaly behavior using support vector machines and Bayesian networks

Dwi Handayani, Dini Oktarina and Sediono, Wahju and Shah, Asadullah (2014) Identification of vessel anomaly behavior using support vector machines and Bayesian networks. In: International Conference on Computer and Communication Engineering (ICCCE 2014), 23-25 Sep 2014, Kuala Lumpur.

[img] PDF - Submitted Version
Restricted to Repository staff only

Download (1MB) | Request a copy
[img] PDF - Supplemental Material
Restricted to Repository staff only

Download (365kB) | Request a copy
[img]
Preview
PDF
Download (443kB) | Preview

Abstract

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

Item Type: Conference or Workshop Item (Invited Papers)
Additional Information: 6584/38408
Uncontrolled Keywords: —Maritime Surveillance, Anomaly Behaviour, Holdout, SVMs, BNs
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices > TK7885 Computer engineering
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button): Kulliyyah of Engineering > Department of Mechatronics Engineering
Depositing User: Dr.-Ing. Wahju Sediono
Date Deposited: 02 Oct 2014 12:10
Last Modified: 23 Sep 2017 11:01
URI: http://irep.iium.edu.my/id/eprint/38408

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year