language en
Revision:
0.14
Download serialization:
JSON-LD RDF/XML N-Triples TTL
License:
http://insertlicenseURIhere.org
Visualization:
Visualize with WebVowl
Cite as:
Revision: 0.14.
Provenance of this page
Ontology Specification Draft

Abstract

This is a place holder text for the abstract. The abstract should contain a couple of sentences summarizing the ontology and its purpose.

Introduction back to ToC

This is a place holder text for the introduction. The introduction should briefly describe the ontology, its motivation, state of the art and goals.

Namespace declarations

Table 1: Namespaces used in the document
[Ontology NS Prefix]<http://iwu.fraunhofer.de/causalgraph>
iwu-fraunhofer-de<http://iwu.fraunhofer.de>
owl<http://www.w3.org/2002/07/owl>
rdf<http://www.w3.org/1999/02/22-rdf-syntax-ns>
xsd<http://www.w3.org/2001/XMLSchema>
rdfs<http://www.w3.org/2000/01/rdf-schema>

causalgraph-ontology: Overview back to ToC

This ontology has the following classes and properties.

Classes

Object Properties

Data Properties

causalgraph-ontology: Description back to ToC

This is a placeholder text for the description of your ontology. The description should include an explanation and a diagram explaining how the classes are related, examples of usage, etc.

Cross reference for causalgraph-ontology classes, properties and dataproperties back to ToC

This section provides details for each class and property defined by causalgraph-ontology.

Classes

CausalEdgec back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#CausalEdge

Causal Edges connect two Causal Nodes and contain information about the causal direction, as well as properties describing the nature of the causal connection.
is in domain of
has cause op, has confidence dp, has creator op, has effect op, has time lag dp
is in range of
created op, is affected by op, is causing op
is disjoint with
CausalNode c

CausalGraphc back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#CausalGraph

Causal Graphs consist of Causal Edges and Causal Nodes. In future releases the graph will be further classified into Causal Graphical Models (CGM) or Structural Causal Model (SCM), depending on the information attaches to its nodes. If it falls in between, as not all Causal Edges contain Structural Equations, it is called Hybrid Causal Model (HCM).
is equivalent to
(has component op some CausalEdge c) and (has component op some CausalNode c)

CausalNodec back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#CausalNode

A Causal Node refers to an information-carrying Node in the Causal Graph. The information can be of different types (e.g., Event, State, (Continous) Variable) and origins (created by Human or Machine).
has sub-classes
Event c, State c, Variable c
is in domain of
has creator op, is affected by op, is causing op
is in range of
created op, has cause op, has effect op
is disjoint with
CausalEdge c

Creatorc back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#Creator

The Creator of the causal individual. The creation can either be a manual process, which instantiates individuals, or software-based learning from data sources.
has sub-classes
Human Creator c, Machine Creator c
is in domain of
created op
is in range of
has creator op

Eventc back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#Event

Defines a CausalNode of with an event-like Signal Type.
has super-classes
CausalNode c
has sub-classes
HumanInput Event c, Machine Event c
is disjoint with
State c, Variable c

Human Creatorc back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#Human_Creator

The Creator of the causal individual, being a human, manually added the causal individual.
has super-classes
Creator c
is disjoint with
Machine Creator c

HumanInput Eventc back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#HumanInput_Event

An Event indicated by a Human.
has super-classes
Event c

HumanInput Statec back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#HumanInput_State

A state derived by a Human as a 'sensor'.
has super-classes
State c

HumanInput Variablec back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#HumanInput_Variable

A variable whose values are manually updated by a Human.
has super-classes
Variable c

Importer Creatorc back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#Importer_Creator

The Creator of the causal individual, being an import algorithm, which programmatically creates the causal individual based on a preexisting knowledge base, e.g. a causal graph in a different format.
has super-classes
Machine Creator c

Learning Algorithm Creatorc back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#LearningAlgorithm_Creator

The Creator of the causal individual, being a learning-algorithm, which programmatically creates the causal individual based on data.
has super-classes
Machine Creator c

Machine Creatorc back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#Machine_Creator

The Creator of the causal individual, being a software artifact, which programmatically created the causal individual.
has super-classes
Creator c
has sub-classes
Importer Creator c, Learning Algorithm Creator c
is disjoint with
Human Creator c

Machine Eventc back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#Machine_Event

An Event generated automatically by a Machine or a software artefact.
has super-classes
Event c

Machine Statec back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#Machine_State

A state-signal controlled and indicated by a machine or software artefact.
has super-classes
State c

Machine Variablec back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#Machine_Variable

A variable whose values are automatically updated by a digital sensor.
has super-classes
Variable c

Statec back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#State

Defines a CausalNode with an state-like signal Type. State-like means, that the signal is shifting between discrete states. These can be binary states (for example 1/0; on/off) or signals with more than two states (for example high, mid, low).
has super-classes
CausalNode c
has sub-classes
HumanInput State c, Machine State c
is disjoint with
Event c, Variable c

Variablec back to ToC or Class ToC

IRI: http://iwu.fraunhofer.de/causalgraph#Variable

Defines a CausalNode with a signal representing a variable. The variable should be continuous in values. Therefore a variable is neither an Event nor a State.
has super-classes
CausalNode c
has sub-classes
HumanInput Variable c, Machine Variable c
is disjoint with
Event c, State c

Object Properties

createdop back to ToC or Object Property ToC

IRI: http://iwu.fraunhofer.de/causalgraph#created

has super-properties
top object property
has domain
Creator c
has range
CausalEdge c
CausalNode c
is inverse of
has creator op

has causal connectionop back to ToC or Object Property ToC

IRI: http://iwu.fraunhofer.de/causalgraph#hasCausalConnection

has characteristics: symmetric

has super-properties
top object property
has sub-properties
has cause op, has effect op, is affected by op, is causing op

has causeop back to ToC or Object Property ToC

IRI: http://iwu.fraunhofer.de/causalgraph#hasCause

A CausalEdge can only have a single 'cause' indicated via the functional 'hasCause' property.

has characteristics: functional

has super-properties
has causal connection op
has domain
CausalEdge c
has range
CausalNode c
is inverse of
is causing op

has creatorop back to ToC or Object Property ToC

IRI: http://iwu.fraunhofer.de/causalgraph#hasCreator

has super-properties
top object property
has domain
CausalEdge c
CausalNode c
has range
Creator c
is inverse of
created op

has effectop back to ToC or Object Property ToC

IRI: http://iwu.fraunhofer.de/causalgraph#hasEffect

A CausalEdge can only have a single 'effect' indicated via the functional 'hasEffect' property.

has characteristics: functional

has super-properties
has causal connection op
has domain
CausalEdge c
has range
CausalNode c
is inverse of
is affected by op

is affected byop back to ToC or Object Property ToC

IRI: http://iwu.fraunhofer.de/causalgraph#isAffectedBy

A CausalNode can be influenced by many 'causes' indicated via different CausalEdges pointing toward a CausalNode. All Edges influencing the CausalNode are gathered via the 'isAffectedBy' property.
has super-properties
has causal connection op
has domain
CausalNode c
has range
CausalEdge c
is inverse of
has effect op

is causingop back to ToC or Object Property ToC

IRI: http://iwu.fraunhofer.de/causalgraph#isCausing

A CausalNode can influence many 'effects' indicated via different CausalEdges being caused by a CausalNode. All Edges influenced from the CausalNode are gathered via the 'isCausing' property.
has super-properties
has causal connection op
has domain
CausalNode c
has range
CausalEdge c
is inverse of
has cause op

Data Properties

has confidencedp back to ToC or Data Property ToC

IRI: http://iwu.fraunhofer.de/causalgraph#hasConfidence

Functional property of a CausalEdge. Measures the Creator's confidence (e.g., a learning algorithm) in the presence of this CausalEdge. A value of 1.0 represents complete confidence in the edge's existence, while 0.0 means that this particular edge is not present.

has characteristics: functional

has super-properties
top data property
has domain
CausalEdge c
has range
double

has time lagdp back to ToC or Data Property ToC

IRI: http://iwu.fraunhofer.de/causalgraph#hasTimeLag

Functional property of a CausalEdge. Measures in SECONDS, the time lag between cause and the effect to take place. Only positive values are allowed, which means that the effect always occurs after the effect.

has characteristics: functional

has super-properties
top data property
has domain
CausalEdge c
has range
double

Legend back to ToC

c: Classes
op: Object Properties
dp: Data Properties
ni: Named Individuals

References back to ToC

Add your references here. It is recommended to have them as a list.

Acknowledgements back to ToC

The authors would like to thank Silvio Peroni for developing LODE, a Live OWL Documentation Environment, which is used for representing the Cross Referencing Section of this document and Daniel Garijo for developing Widoco, the program used to create the template used in this documentation.