Difference between revisions of "KHealthAsthmaOntology"

From Knoesis wiki
Jump to: navigation, search
(Created page with "Knoesis Asthma Ontology (KAO) The Knoesis Asthma Ontology (KAO) is being designed to deduce abstractions from the asthma dataset provided by the kHealth project. The asthma d...")
 
(Kao Ontology: Best Practices with PerfectO (ONGOING))
 
(68 intermediate revisions by the same user not shown)
Line 1: Line 1:
Knoesis Asthma Ontology (KAO)
+
= KHealth Asthma Ontology (KAO) =
  
The Knoesis Asthma Ontology (KAO) is being designed to deduce abstractions from the asthma dataset provided by the kHealth project.
+
The KHealth Asthma Ontology (KAO) is being designed to deduce abstractions from the asthma dataset provided by the [http://wiki.knoesis.org/index.php/KHealth:_Semantic_Multisensory_Mobile_Approach_to_Personalized_Asthma_Care kHealth project].  
The asthma dataset collects data generated by IoT devices such as peak flow meter, Foobot, Fitbit, AirNow, and other Web Services obtaining parameters such as air quality, pollen index, outside humidity and temperature.
+
  
The knoesis Asthma Ontology (kAO) ontology is being created:  
+
The overall goal is to achieve the Data, Information, Knowledge, and Wisdom (DIKW) pyramid triangle vision [http://knoesis.org/sites/default/files/SAH13-IEEE-IS-PCS.pdf [Sheth et al. CPS Computing 2013]].
* W3C SOSA ontology to semantically annotate sensor observations (e.g., peak flow meter is a subclass of the ''sosa:Sensor'' class)
+
 
* the Asthma Ontology (AO ontology) from BioPortal to reuse relevant concepts
+
The asthma dataset collects data generated by IoT devices such as peak flow meter, Foobot, Fitbit, and Web Services (e.g., AirNow) to obtain parameters such as air quality, pollen index, outside humidity, and temperature.
* FOAF ontology to describe people
+
 
* weather ontology to deduce meaningful information from weather datasets.
+
= KAO Overview (ONGOING) =
 +
 
 +
The KHealth Asthma Ontology (KAO) ontology is designed and reused the ontologies as follows:  
 +
* [https://www.w3.org/TR/vocab-ssn/ W3C Semantic Sensor Network (SSN) and Sensor, Observation, Sample, and Actuator (SOSA) ontologies] to semantically annotate sensor observations (e.g., peak flow meter is a subclass of the ''sosa:Sensor'' class)
 +
* [https://bioportal.bioontology.org/ontologies/AO Asthma Ontology (AO ontology)] from BioPortal to reuse relevant concepts
 +
* [http://xmlns.com/foaf/spec/ FOAF ontology] to describe people
 +
* Weather ontologies [Staroch 2013] [Kofler et al. 2011] to deduce meaningful information from weather datasets.
 +
** [http://paul.staroch.name/thesis/SmartHomeWeather.owl Staroch's smart home and weather ontology]
 +
** [https://www.auto.tuwien.ac.at/downloads/thinkhome/ontology/WeatherOntology.owl Kofler's smart home and weather ontology]
 +
 
 +
 
 +
[https://www.draw.io/?state=%7B%22ids%22:%5B%221LaX03Aq-c5-idb-YB5Y2xv7gr9l6RNUt%22%5D,%22action%22:%22open%22,%22userId%22:%22109434321802239620132%22%7D#G1LaX03Aq-c5-idb-YB5Y2xv7gr9l6RNUt Kao ontology design picture URL]
 +
 
 +
[[File:KaoOntology.png|1600px|thumb|center|Kao Ontology (ONGOING)]]
 +
 
 +
= kao Ontology Implementation (ONGOING) =
 +
 
 +
[http://purl.org/kao# kao ontology code V2] (designed in 2018 by Utkarshani Jaimini and Amelie Gyrard)
 +
 
 +
[http://knoesis.org/ontology/kHhealth/Asthma/schema.ttl kao ontology code V1] (designed in 2016 by SoonJye Kho and Utkarshani Jaimini)
 +
 
 +
= kao Ontology Evaluation (ONGOING) =
 +
 
 +
== Kao Ontology used for automatic semantic annotation and reasoning (ONGOING) ==
 +
 
 +
The kao ontology is used to semantically annotate the IoT datasaset using [https://jena.apache.org/ Jena, a framework to build semantic web applications].
 +
 
 +
High-level abstractions (e.g., HighgPollenLevel) can be deduced by executing the [http://linkedopenreasoning.appspot.com/?p=slorv2 Sensor-based Linked Open Reasoning (S-LOR)] inference engine based on the Jena inference engine.
 +
 
 +
S-LOR inference engine is extended to interpret health measurements or any IoT datasets used within the kHealth project.
 +
 
 +
== Kao Ontology: Best Practices with PerfectO (ONGOING) ==
 +
We follow as much as possible the [http://perfectsemanticweb.appspot.com/?p=ontologyValidation PerfectO methodology] to improve the quality of the ontology and its integration with useful ontology tools to provide automatic documentation, visualization, etc.
 +
 
 +
* Usage of the PURL tool to get a permanent URL: [http://purl.org/kao# http://purl.org/kao#]
 +
 
 +
* Usage of the WebVOWL tool to provide the ontology visualization automatically: [http://visualdataweb.de/webvowl/#iri=http://purl.org/kao# http://visualdataweb.de/webvowl/#iri=http://purl.org/kao#]
 +
 
 +
* Usage of the Oops tool to improve the ontology design: [http://oops.linkeddata.es/response.jsp?uri=http://purl.org/kao# http://oops.linkeddata.es/response.jsp?uri=http://purl.org/kao#]
 +
 
 +
* Usage of the Vapour tool to improve deferencing URI and content negotiation: [http://linkeddata.uriburner.com:8000/vapour?uri=http%3A%2F%2Fpurl.org%2Fkao&acceptRdfXml=1&defaultResponse=dontmind&userAgent=http%3A%2F%2Flinkeddata.uriburner.com%3A8000%2Fvapour%23this# http://linkeddata.uriburner.com:8000/vapour?uri=http://purl.org/kao#]
 +
 
 +
* Usage of TripleChecker tool to check incorrect use of ontologies: [http://graphite.ecs.soton.ac.uk/checker/?uri=http%3A%2F%2Fpurl.org%2Fkao%23&output=html# TripleChecker with kao ontology here]
 +
 
 +
Table from [http://perfectsemanticweb.appspot.com/documentation/SemanticWebBestPracticesForDummies.pdf Semantic Web Best Practices for Dummies with PerfectO] applied to the kao ontology (July 2018):
 +
 
 +
[[File:KaoBestPractices1.png|700px|thumb|center|Kao Ontology: Best Practices with PerfectO]]
 +
[[File:KaoBestPractices2.png|700px|thumb|center|Kao Ontology: Best Practices with PerfectO]]
 +
 
 +
[[File:KaoBestPractices3.png|700px|thumb|center|Kao Ontology: Best Practices with PerfectO]]
 +
[[File:KaoBestPractices4.png|700px|thumb|center|Kao Ontology: Best Practices with PerfectO]]
 +
 
 +
[[File:KaoBestPractices5.png|700px|thumb|center|Kao Ontology: Best Practices with PerfectO]]
 +
 
 +
= Publications =
 +
 
 +
* Amelie Gyrard, Manas Gaur, Krishnaprasad Thirunarayan, Amit Sheth and Saeedeh Shekarpour. [http://knoesis.org/node/2910 Personalized Health Knowledge Graph]. 1st Workshop on Contextualized Knowledge Graph (CKG) co-located with International Semantic Web Conference (ISWC), 8-12 October 2018, Monterey, USA.
 +
 
 +
= References =
 +
 
 +
* Sheth, A., Jaimini, U., Thirunarayan, K., Banerjee, T.: Augmented personalized health: How smart data with iots and ai is about to change healthcare. In: IEEE RTSI. (2017)
 +
 
 +
* Jaimini, U., Banerjee, T., Romine, W., Thirunarayan, K., Sheth, A., Kalra, M.: Investigation of an indoor air quality sensor for asthma management in children. IEEE sensors letters (2017)
 +
 
 +
* Anantharam, P., Banerjee, T., Sheth, A., Thirunarayan, K., Marupudi, S., Sridharan, V., Forbis, S.G.: Knowledge-driven personalized contextual mhealth service for asthma management in children. In: IEEE ICMS. (2015)
 +
 
 +
* Sheth, A., Anantharam, P., Thirunarayan, K.: khealth: Proactive personalized actionable information for better healthcare. In: PDA@ IOT at VLDB. (2014)
 +
 
 +
* Sheth, A., Anantharam, P., Henson, C.: Physical-cyber-social computing: An early 21st century approach. IEEE Intelligent Systems (2013)
 +
 
 +
* Staroch, P.: A weather ontology for predictive control in smart homes. Master’s thesis (2013)
 +
 
 +
* Kofler, M., Reinisch, C., Kastner, W.: An intelligent knowledge representation of smart home energy parameters. In: Proceedings of the World Renewable Energy Congress (WREC). (2011)
 +
 
 +
= Acknowledgments =
 +
This work is partially funded by KHealth NIH 1 R01 HD087132-01. The opinions expressed are those of the authors and do not reflect those of the sponsors.

Latest revision as of 14:25, 20 August 2018

KHealth Asthma Ontology (KAO)

The KHealth Asthma Ontology (KAO) is being designed to deduce abstractions from the asthma dataset provided by the kHealth project.

The overall goal is to achieve the Data, Information, Knowledge, and Wisdom (DIKW) pyramid triangle vision [Sheth et al. CPS Computing 2013].

The asthma dataset collects data generated by IoT devices such as peak flow meter, Foobot, Fitbit, and Web Services (e.g., AirNow) to obtain parameters such as air quality, pollen index, outside humidity, and temperature.

KAO Overview (ONGOING)

The KHealth Asthma Ontology (KAO) ontology is designed and reused the ontologies as follows:


Kao ontology design picture URL

Kao Ontology (ONGOING)

kao Ontology Implementation (ONGOING)

kao ontology code V2 (designed in 2018 by Utkarshani Jaimini and Amelie Gyrard)

kao ontology code V1 (designed in 2016 by SoonJye Kho and Utkarshani Jaimini)

kao Ontology Evaluation (ONGOING)

Kao Ontology used for automatic semantic annotation and reasoning (ONGOING)

The kao ontology is used to semantically annotate the IoT datasaset using Jena, a framework to build semantic web applications.

High-level abstractions (e.g., HighgPollenLevel) can be deduced by executing the Sensor-based Linked Open Reasoning (S-LOR) inference engine based on the Jena inference engine.

S-LOR inference engine is extended to interpret health measurements or any IoT datasets used within the kHealth project.

Kao Ontology: Best Practices with PerfectO (ONGOING)

We follow as much as possible the PerfectO methodology to improve the quality of the ontology and its integration with useful ontology tools to provide automatic documentation, visualization, etc.

Table from Semantic Web Best Practices for Dummies with PerfectO applied to the kao ontology (July 2018):

Kao Ontology: Best Practices with PerfectO
Kao Ontology: Best Practices with PerfectO
Kao Ontology: Best Practices with PerfectO
Kao Ontology: Best Practices with PerfectO
Kao Ontology: Best Practices with PerfectO

Publications

  • Amelie Gyrard, Manas Gaur, Krishnaprasad Thirunarayan, Amit Sheth and Saeedeh Shekarpour. Personalized Health Knowledge Graph. 1st Workshop on Contextualized Knowledge Graph (CKG) co-located with International Semantic Web Conference (ISWC), 8-12 October 2018, Monterey, USA.

References

  • Sheth, A., Jaimini, U., Thirunarayan, K., Banerjee, T.: Augmented personalized health: How smart data with iots and ai is about to change healthcare. In: IEEE RTSI. (2017)
  • Jaimini, U., Banerjee, T., Romine, W., Thirunarayan, K., Sheth, A., Kalra, M.: Investigation of an indoor air quality sensor for asthma management in children. IEEE sensors letters (2017)
  • Anantharam, P., Banerjee, T., Sheth, A., Thirunarayan, K., Marupudi, S., Sridharan, V., Forbis, S.G.: Knowledge-driven personalized contextual mhealth service for asthma management in children. In: IEEE ICMS. (2015)
  • Sheth, A., Anantharam, P., Thirunarayan, K.: khealth: Proactive personalized actionable information for better healthcare. In: PDA@ IOT at VLDB. (2014)
  • Sheth, A., Anantharam, P., Henson, C.: Physical-cyber-social computing: An early 21st century approach. IEEE Intelligent Systems (2013)
  • Staroch, P.: A weather ontology for predictive control in smart homes. Master’s thesis (2013)
  • Kofler, M., Reinisch, C., Kastner, W.: An intelligent knowledge representation of smart home energy parameters. In: Proceedings of the World Renewable Energy Congress (WREC). (2011)

Acknowledgments

This work is partially funded by KHealth NIH 1 R01 HD087132-01. The opinions expressed are those of the authors and do not reflect those of the sponsors.