Upload
arno974
View
226
Download
2
Tags:
Embed Size (px)
Citation preview
1/24
A semi-supervised learning framework based A semi-supervised learning framework based
on spatio-temporal semantic events on spatio-temporal semantic events
for maritime anomaly detection and behaviour analysisfor maritime anomaly detection and behaviour analysis
Arnaud VandecasteeleArnaud VandecasteeleRodolphe DevillersRodolphe Devillers
Aldo NapoliAldo Napoli
CoastGIS - GIS and New Technologies - June 20
2/24
Background & Research problemsMaritime domain Problem
Semantic Event ModellingWhat is an ontology ?Simple Event ModelVessels behaviours analysis
Prototype & examplesPrototype architectureComponents of the architectureExamples
3/24
Context
Economic
90% of world trade is transported by sea In Europe 90% of oil and gas are transported by sea
Illegal Fishing
Only 6% of illegal fishing frauds are detected 88% of fishing stocks in the EU are overexploited
Illegal immigration
55% of illegal border crossing immigration is done by sea (EU) 3000 illegal ''known'' immigrants lost their life at sea every year
Source : ICC International Maritime Bureau
Maritime domain
Background & Research problems >Background & Research problems > Semantic Event Modelling > Prototype & examples
4/24
Poor interface
Data Overflow
Few information
Large surveillance area
High maritime traffic density
Cognitive Overflow
No tools for automatic detection
Maritime information system
Background & Research problems >Background & Research problems > Semantic Event Modelling > Prototype & examples
5/24
?
ImproveImprove Detection & Analysis
Better understandingunderstanding for maritime surveillance
High volume of data
Heterogeneous data and knowledge
Distributeddata and knowledge
Analysis ofcomplex information
Research problem
Background & Research problems >Background & Research problems > Semantic Event Modelling > Prototype & examples
6/24
Improve UnderstandingAn enriched formalization with spatial capabilities offers a better
way to describe and analyze the behaviour of the vessels 1
Formalize expert knowledge
Automatedspatial reasoning
Spatial Ontologies
2 Integrate the spatial dimension into ontologies
Automatic detectionof suspicious events
Automatic identificationof abnormal behaviours
Research problem
Background & Research problems >Background & Research problems > Semantic Event Modelling > Prototype & examples
7/24
Formalize Vocabulary
RepresentReuse
SharingKnowledge
Automated Reasoning
Humans & Systems Interoperability
“an ontology is a formal, explicit specification of a shared conceptualisation”Studer, 1998
Hepp, 2008
Why an ontology ?
Background & Research problems > Semantic Event Modelling > Semantic Event Modelling > Prototype & examples
8/24
Concept A Concept BRelations
Individual 1Properties1properties2
Individual 2
Ontology components
Vessel Type of VesselhasType
Vessel 1IMO: 1234562
Speed: 12
Tanker
Example : how to describe a tanker ?
hasType
subConcept1 subConcept2
subClassOf subClassOf
Background & Research problems > Semantic Event Modelling > Semantic Event Modelling > Prototype & examples
9/24
“Function played”
ROLE
ACTOR
PLACE“Who”
“Where”
“With What”
“What”
EVENT
Simple Event Model: 5 cores classes
Background & Research problems > Semantic Event Modelling > Semantic Event Modelling > Prototype & examples
Van Hage, 2012
10/24
“Function played”
ROLE
ACTOR
PLACE“Who”
“Where”
“Whit What”
“What”
EVENT
Time-Stamped Entity
subClassOfsubClassOf
subClassOf
subClassOfsubClassOf
TimeStamp
Linked to a Time-Stamped Entity
Background & Research problems > Semantic Event Modelling > Semantic Event Modelling > Prototype & examples
11/24
ROLE
ACTOR
PLACE
EVENT
Time-Stamped Entity
subClassOfsubClassOf
subClassOf
subClassOfsubClassOf
Takes place in
TimeStamp
Participates inas role
(begins in place - ends in place)
hasRole
Takes place in
Takes place in
Involves inParticipates in
Linked together
Background & Research problems > Semantic Event Modelling > Semantic Event Modelling > Prototype & examples
12/24
Actor TypeRole Type Event Type Object Type Place Type
ROLE
ACTOR
PLACE
EVENT
Time-Stamped Entity
subClassOfsubClassOf
subClassOf
subClassOfsubClassOf
Takes place in
TimeStamp
Participates inas role
(begins in place - ends in place)
hasRole
Takes place in
Takes place in
Involves inParticipates in
Has role type
Has Actor type
Has Event type
Has object type
Has place type
Has Actr type
Linked together with types
Background & Research problems > Semantic Event Modelling > Semantic Event Modelling > Prototype & examples
13/24Background & Research problems > Semantic Event Modelling > Semantic Event Modelling > Prototype & examples
14/24
ACTOR
PLACE
EVENT
Vesselid:mmsi
Tanker
Rdf:type
Rdf:type
Port of Vancouver
GeoNameId:6173335
Rdf:type
Eez:CanadaGeoNameId : 6251999
Lat:49°16'37" N Lon:123°07'15" W
Has Actor type
EventAnchorage
Participates inas role
2013-06-16 2013-06-20
begins at ends at
Examples : Tanker anchored in a port
Background & Research problems > Semantic Event Modelling > Semantic Event Modelling > Prototype & examples
15/24
Prototype architecture
Background & Research problems > Semantic Event Modelling > Prototype & examplesPrototype & examples
16/24
Dataset :
More than 5 millions of AIS positionsBetween February and December 2009
InformationPosition, timestamp, heading, speed...
http://www.chorochronos.org/?q=node/9
Data from the French Naval Academy Resarch Lab
Background & Research problems > Semantic Event Modelling > Prototype & examplesPrototype & examples
17/24
Vessels' positions
Spatio-Temporal interpolationof vessels' positions
Vessel's Trajectory
Spatio-Temporal interpolationof Vessel's Trajectory
Spatio-Temporal filtering
Background & Research problems > Semantic Event Modelling > Prototype & examplesPrototype & examples
Etienne, 2012
18/24
Feed Ontology
Background & Research problems > Semantic Event Modelling > Prototype & examplesPrototype & examples
19/24
Semantic Event
Background & Research problems > Semantic Event Modelling > Prototype & examplesPrototype & examples
20/24
Spatio-Temporal Semantic Events
Background & Research problems > Semantic Event Modelling > Prototype & examplesPrototype & examples
21/24
Timeline to navigatethrough time
Time widgetto animate the data
3D Web Mapping interface
Visualization of the results
Background & Research problems > Semantic Event Modelling > Prototype & examplesPrototype & examples
22/24
2D View
3D View
Example of acceleration events
Background & Research problems > Semantic Event Modelling > Prototype & examplesPrototype & examples
23/24
Conclusion
Ontologies provide a richer way to describe events
A richer description can provide a better understanding of a situation
A semantic model linked to a webmapping interface has been created
This prototype offers an interface to explore semantic events
More events type must be added
Vessels must be linked to the timeline
24/24
Arnaud Vandecasteelea.vandecasteele [at] mun.ca
Questions ?