東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Trajectory Reconstruction Models for...

Petersen, Chance.

FindBook

Google Book

Amazon

博客來

Trajectory Reconstruction Models for Maritime Vessel Anomaly Detection.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Trajectory Reconstruction Models for Maritime Vessel Anomaly Detection./
作者:	Petersen, Chance.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2019,
面頁冊數:	118 p.
附註:	Source: Masters Abstracts International, Volume: 80-12.
Contained By:	Masters Abstracts International80-12.
標題:	Computer Engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13864849
ISBN:	9781392240397

Trajectory Reconstruction Models for Maritime Vessel Anomaly Detection.
Petersen, Chance.

Trajectory Reconstruction Models for Maritime Vessel Anomaly Detection. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 118 p.

Source: Masters Abstracts International, Volume: 80-12.

Thesis (M.S.)--Stevens Institute of Technology, 2019.

This item must not be added to any third party search indexes.

In the maritime environment, vessels of certain types and sizes are required to use the Automatic Identification System (AIS). This system requires the vessels to be equipped with specialized radio transponders that regularly broadcast messages about themselves, including identification information and navigational data. The messages can then be received by any interested parties in range, notably other vessels and coastal authorities. The primary purpose of the automatic identification system is to assist in navigation to reduce congestion and prevent accidents. The effectiveness of this system is well known and has been adopted across the globe. One of the largest suppliers of AIS data, MarineTraffic, records approximately 520,000,000 messages from around 180,000 vessels each day. With this plethora of data, the system has also been used extensively in the maritime security domain.This thesis presents a method for identifying anomalous behavior in vessels using the data from AIS messages. This can be used to tag vessels to be further investigated to determine if there was malicious activity, such as smuggling, illegal off-loading of cargo, or fishing in restricted waters. The method involves the use of a variational recurrent neural network, which is a type of generative machine learning model, to reconstruct trajectories of the vessels. The model was found to be effective at learning how certain vessels behave normally in order to identify vessels that are potential anomalies, even when AIS messages are not received for some time.

ISBN: 9781392240397Subjects--Topical Terms:

1567821
Computer Engineering.
Subjects--Index Terms:

Anomaly

Trajectory Reconstruction Models for Maritime Vessel Anomaly Detection.
LDR:02912nmm a2200409 4500 001 2268824
005 20200824100403.5
008 220629s2019 ||||||||||||||||| ||eng d
020 $a 9781392240397
035 $a (MiAaPQ)AAI13864849
035 $a (MiAaPQ)stevens:10584
035 $a AAI13864849
040 $a MiAaPQ $c MiAaPQ
100 1 $a Petersen, Chance. $3 3546122
245 1 0 $a Trajectory Reconstruction Models for Maritime Vessel Anomaly Detection.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 118 p.
500 $a Source: Masters Abstracts International, Volume: 80-12.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Bunin, Barry;Man, Hong.
502 $a Thesis (M.S.)--Stevens Institute of Technology, 2019.
506 $a This item must not be added to any third party search indexes.
506 $a This item must not be sold to any third party vendors.
520 $a In the maritime environment, vessels of certain types and sizes are required to use the Automatic Identification System (AIS). This system requires the vessels to be equipped with specialized radio transponders that regularly broadcast messages about themselves, including identification information and navigational data. The messages can then be received by any interested parties in range, notably other vessels and coastal authorities. The primary purpose of the automatic identification system is to assist in navigation to reduce congestion and prevent accidents. The effectiveness of this system is well known and has been adopted across the globe. One of the largest suppliers of AIS data, MarineTraffic, records approximately 520,000,000 messages from around 180,000 vessels each day. With this plethora of data, the system has also been used extensively in the maritime security domain.This thesis presents a method for identifying anomalous behavior in vessels using the data from AIS messages. This can be used to tag vessels to be further investigated to determine if there was malicious activity, such as smuggling, illegal off-loading of cargo, or fishing in restricted waters. The method involves the use of a variational recurrent neural network, which is a type of generative machine learning model, to reconstruct trajectories of the vessels. The model was found to be effective at learning how certain vessels behave normally in order to identify vessels that are potential anomalies, even when AIS messages are not received for some time.
590 $a School code: 0733.
650 4 $a Computer Engineering. $3 1567821
650 4 $a Naval engineering. $3 3173824
650 4 $a Artificial intelligence. $3 516317
653 $a Anomaly
653 $a Automatic Identification System
653 $a Maritime vessels
653 $a Trajectory reconstruction
653 $a Variational Recurrent Neural Network
690 $a 0464
690 $a 0468
690 $a 0800
710 2 $a Stevens Institute of Technology. $b Computer Engineering. $3 2049827
773 0 $t Masters Abstracts International $g 80-12.
790 $a 0733
791 $a M.S.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13864849