Difference between revisions of "EMPWR: Knowledge Graph Development Platform"

From Knoesis wiki
Jump to: navigation, search
(Created page with "=Background and Motivation= '''Knowledge Graph''' (KG) is an encapsulation of structured knowledge in a graphical representation & used for a variety of information processin...")
 
Line 1: Line 1:
−
=Background and Motivation=
+
== Knowledge Graphs (KG) Applications ==
−
'''Knowledge Graph''' (KG) is an encapsulation of structured knowledge in a graphical representation &  used for a variety of information processing and management tasks such as
+
=== EMPWR ===
−
* Data & knowledge integration from diverse sources
+
The '''AIISC [http://wiki.aiisc.ai/index.php/EMPWR:_Knowledge_Graph_Development_Platform EMPWR: Knowledge Graph Development Platform]''' effort involves the development of a comprehensive tool and platform for KG development with the following aims
−
* Improve automation
+
−
* Enabling new generation of applications
+
−
* Empowering machine learning (ML) & NLP techniques with domain knowledge
+
−
and applications such as question answering, summarization, text simplification, and Named Entity Recognition (NER).
+
  
−
Most existing KG platforms & tools are limited in
+
1. Develop a KG development platform capable of instantiating KGs in any domains from '''structured''', '''semi-structured''', and '''unstructured''' data.
−
* Provenance
+
−
* Dynamicity (ie: static schema vs schema generation)
+
−
* Temporal
+
−
* Domain specificity
+
−
* Modularity
+
−
 
+
−
The '''AIISC Knowledge Graph''' (KG) '''EMPWR''' effort involves the development of a comprehensive tool and platform for KG development with the following aims
+
−
 
+
−
1. Develop a KG development platform capable of instantiating KGs in any domains from '''structured''', '''semi-structured''', and '''unstructured''' data:
+
−
** Biomedical & pharmaceutical domain with '''Percuro'''
+
  
 
2. Improve & address the limitations of existing KG platforms
 
2. Improve & address the limitations of existing KG platforms
Line 25: Line 11:
 
** Construct a Knowledge Graph out of given entities '''(Bottom-up data driven)'''
 
** Construct a Knowledge Graph out of given entities '''(Bottom-up data driven)'''
  
−
=Goals & Use-Cases=
+
=== Scooner ===
−
The goals of KGs are to provide
+
[http://wiki.aiisc.ai/index.php/Scooner Scooner]
−
* Contextualization
+
Scooner is a knowledge-based literature search and exploration system where recently published results are computationally extracted and used a background KB to guide the search process. The key here is that the knowledge base that guides the search is extracted from the same universe of literature that is being explored.
−
** [https://www.google.com/url?q=https://www.semanticscholar.org/paper/Context-Enriched-Learning-Models-for-Aligning-in/650e79de9f4a4a123d559240387db0e3c3d1f867&sa=D&source=editors&ust=1654007896106276&usg=AOvVaw2iUUH6T-CCQl6mV6oNlmMN Context-Enriched Learning Models for Aligning Biomedical Vocabularies in the UMLS Metathesaurus]
+
−
* Personalization
+
−
* Abstraction
+
−
* Explainability
+
  
−
=Collaborations=
+
=== Human Performance and Cognition Ontology ===
−
'''Percuro''' is a collaborative research project involving WIPRO, The AI Institute at University of South Carolina (AIISC), and IIT-Patna
+
[http://wiki.aiisc.ai/index.php/Human_Performance_and_Cognition_Ontology HPCO] The human performance and cognition ontology (HPCO) project aims to achieve the following two major objectives
−
(IIT-P). It involves development of semantic (i.e., knowledge graph enhanced) approach to natural language processing (NLP), natural language generation (NLG) and natural language understanding (NLU) targeted at the pharmaceutical domain. It will involve techniques for NLP/NLG/NLU on biomedical and clinical documents relevant to pharmaceutical markets.
+
  
−
'''Percuro''' aims to solve tasks such as (a) text simplification, (b) summarization and (c) question answering. These are tasks that are not straightforward and require more information that what the text provides.  
+
# Build a knowledge base using semi-automatic domain hierarchy construction and relationship extraction from PubMed citations;
 +
# Build a tool to browse and explore scientific literature with the help of the knowledge base created in 1.
  
−
'''An example:''' Which hormone reduces blood sugar level?
+
The project involves extending our work in focused knowledge (entity-relationship) extraction from scientific literature, automatic taxonomy extraction from selected community authored content (eg Wikipedia), and semi-automatic ontology development with limited expert guidance.
  
−
This question requires additional context on what the word hormone means before finding an answer.
+
=== Healthcare KG ===
 +
Leaders: [http://knoesis.org/researchers/saeedeh/ Dr. Saeedeh Shekarpour], [http://wiki.knoesis.org/index.php/AmelieGyrard Dr. Amelie Gyrard]
  
−
=Overview=
 
−
<html>
 
 
<center>
 
<center>
−
<iframe src="https://docs.google.com/presentation/d/1EOqyl5fK6tUecrjOpslcd9IY8US3fGqKgRZQIttGD3A/embed?start=false&loop=false&delayms=3000" frameborder="0" width="600" height="375" allowfullscreen="true" mozallowfullscreen="true" webkitallowfullscreen="true"></iframe>
+
{{#widget:SlideShare|id=118908850&doc=personalizedhealthknowledgegraph-ckgworkshop-iswc20182-181009191259|width=500|border=0}}
 
</center>
 
</center>
 +
 +
=== Internet of Things (IoT) KG ===
 +
Leader: [http://wiki.knoesis.org/index.php/AmelieGyrard Dr. Amelie Gyrard]
  
 
<center>
 
<center>
−
<iframe src="https://docs.google.com/presentation/d/1SFLzGCcTM8oYP0VsiWkvzclJ3zHKTGgY8VWeFw5kqtc/embed?start=false&loop=false&delayms=3000" frameborder="0" width="600" height="375" allowfullscreen="true" mozallowfullscreen="true" webkitallowfullscreen="true"></iframe>
+
{{#widget:SlideShare|id=123120441&doc=copyofiot-181115182215|width=500|border=0}}
 
</center>
 
</center>
−
</html>
 
  
−
=Toolkit=
 
  
−
The Knowledge Graph Toolkit (EMPWR) V1.0 currently supports knowledge sources from:
+
<Strong>[http://lov4iot.appspot.com/ Linked Open Vocabularies for Internet of Things (LOV4IoT)]</Strong>, an ontology catalog for Internet of Things, references ontology-based IoT projects:<br/>
−
* PharmKG (base)
+
- Almost 500 ontology-based projects for IoT, smart cities, etc. <br/>
−
* Open-domain: '''DBpedia''' & '''Wikidata'''
+
- More than 20 domains relevant to IoT referenced such as building, smart grid, smart agriculture, robotics, smart transportation, healthcare, etc. <br/>
−
* Biomedical & pharmaceutical domain: '''Drugbank''' & '''UMLS'''
+
- We provide the LOV4IoT ontology catalog as an HTML view. <br/>
 +
- We also provide the LOV4IoT RDF dataset. <br/>
 +
LOV4IoT is an extension of the LOV (Linked Open Vocabulary) catalog. <br/>
 +
* <Strong>Project Demonstrator</Strong>: [http://lov4iot.appspot.com/ Linked Open Vocabularies for Internet of Things (LOV4IoT)]
 +
* <Strong>LOV4IoT refering almost 400 ontology based IoT projects</Strong>: [http://lov4iot.appspot.com/?p=ontologies http://lov4iot.appspot.com/?p=ontologies]
 +
* <Strong>LOV4IoT RDF Dataset</Strong>: [http://purl.org/lov4iot-dataset http://purl.org/lov4iot-dataset]
 +
* <Strong>Publications</Strong>: [http://lov4iot.appspot.com/?p=publication Here]
 +
* <Strong>Presentation</Strong>:
 +
<center>
 +
{{#widget:SlideShare|id=65309629&doc=ficloud2016presentationgyrardlov4iotsecondlife-160824090311|width=500|border=0}}
 +
{{#widget:SlideShare|id=65309859&doc=ficloud2016presentationgyrardlov4iotunifyingknowledge-160824091023|width=500|border=0}}
 +
</center>
 +
* <Strong>Demo</Strong>:
 +
{{#ev:youtube|https://www.youtube.com/watch?v=a1zsdkzE_oY&feature=youtu.be|500|center}}
 +
<br/>
  
−
and has an extensive coverage over the domains of '''Drugs''', '''Chemicals''', '''Diseases''' entities and their associated relations:
 
−
* '''Chemical''': Drug interactions, diseases cured, etc.
 
−
* '''Physical''': Lethal dosage, boiling point, pressure, solubility, etc
 
−
* '''Disease''': Symptoms, treatments, differential diagnosis, etc.
 
−
* '''Aliases''': Common names, chemical names and external identifiers.
 
  
−
=GitHub=
 
−
* [https://github.com/Anirudh-Sundar/APGC AIISC Knowledge Graph (EMPWR) Development Tool]
 
  
−
=Demo=
+
[http://wiki.knoesis.org/index.php/KE4WoTChallengeWWW2018 Knowledge Extraction for the Web of Things (KE4WoT) Challenge] co-located with The Web Conference 2018 (WWW 2018)
−
<embedvideo service="youtube">https://www.youtube.com/watch?v=ggvfAo-yp5g</embedvideo>
+
  
−
<embedvideo service="youtube">https://www.youtube.com/watch?v=fUf8A48r8G0</embedvideo>
+
=== Disaster Management KG ===
 +
Leader: [http://knoesis.org/resources/researchers/hussein/ Hussein Al-Olimat], Shruti Kar
  
−
=People=
+
NSF Project: [http://wiki.knoesis.org/index.php?title=Social_and_Physical_Sensing_Enabled_Decision_Support&redirect=no Hazards SEES: Social and Physical Sensing Enabled Decision Support for Disaster Management and Response]
−
*'''Artificial Intelligence Institute, University of South Carolina'''
+
−
**[https://www.linkedin.com/in/joeyyip/ Hong Yung (Joey) Yip]
+
−
**[https://www.linkedin.com/in/thilini-w/ Thilini Wijesiriwardene]
+
−
**[https://sc.edu/study/colleges_schools/engineering_and_computing/faculty-staff/amitsheth.php Dr. Amit P. Sheth]
+
  
−
*'''Development Team'''
+
[http://lov4iot.appspot.com/?p=lov4iot-disaster LOV4IoT-Disaster]
−
**[https://www.linkedin.com/in/joeyyip/ Hong Yung (Joey) Yip]
+
 
−
**[https://github.com/Anirudh-Sundar/APGC Anirudh Sundar]
+
Some publications:
 +
# Shruti Kar, Hussein S. Al-Olimat, Krishnaprasad Thirunarayan, Valerie Shalin, Amit Sheth, and Srinivasan Parthasarathy. [http://knoesis.org/node/2915 "D-record: Disaster Response and Relief Coordination Pipeline"]. In Proceedings of the ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities (ARIC 2018). ACM, 2018.
 +
 
 +
=== Security KG ===
 +
Security Toolbox: Attacks and Countermeasures (STAC)
 +
is a project to assist developers in:
 +
1) Designing secured applications or architectures.
 +
2) Being aware of main security threats.
 +
3) Exploring security in various technologies such as: Sensor Networks, Cellular Networks (2G, 3G, 4G), Wireless Networks (Wi-Fi, Wimax, Zigbee, Bluetooth), Mesh/M2M/MANET, Network Management, Web Applications, Cryptography, Attacks & Countermeasures, Security Properties (e.g., authentication, integrity), Etc.
 +
 
 +
* <Strong>Project Demonstrator</Strong>: [http://securitytoolbox.appspot.com/ Security Toolbox: Attacks and Countermeasures (STAC) ]
 +
* <Strong>Presentation</Strong>:
 +
<center>
 +
{{#widget:SlideShare|id=141841124&doc=keynote-wfiot2019-datagraphontologiesinternetofthingsiotcyber-physicial-systemscps-monday15april1-190424003458|width=500|border=0}}
 +
</center>
 +
* <Strong>Demo</Strong>:
 +
{{#ev:youtube|https://www.youtube.com/watch?v=vXYYbwM0xvY&feature=youtu.be|500|center}}
 +
<br/>
 +
 
 +
=== Robotics KG ===
 +
Leader: [http://wiki.knoesis.org/index.php/AmelieGyrard Dr. Amelie Gyrard]
 +
 
 +
<center>
 +
{{#widget:SlideShare|id=157318770&doc=july182019weeklyontologiesfortheinternetofroboticthingsontologycatalogknowledgeextractionieeep1872-190723173028|width=500|border=0}}
 +
</center>
 +
 
 +
=== Affective Science (Well-Being and Happiness) KG ===
 +
Leader: [http://wiki.knoesis.org/index.php/AmelieGyrard Dr. Amelie Gyrard]
 +
 
 +
<center>
 +
{{#widget:SlideShare|id=179792888&doc=slideschase2019-connectedhealthconference-thursday26september2019-iamhappytowardsaniotknowledge-base-191007160923|width=500|border=0}}
 +
</center>
  
−
*'''WiPRO'''
+
Scientific paper: [http://knoesis.org/sites/default/files/CHASE_2019_Well_being_IoT_Cross_Domain_Recommender_System_for_Everyday_Happiness_Emotion_Stress_Depression_Ontologies.pdf IAMHAPPY: Towards An IoT Knowledge-Based Cross-Domain Well-Being Recommendation System for Everyday Happiness. IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) Conference 2019. Elsevier Smart Health Journal]
−
**[http://www.amitavadas.com/ Amitava Das]
+

Revision as of 14:18, 21 March 2023

Knowledge Graphs (KG) Applications

EMPWR

The AIISC EMPWR: Knowledge Graph Development Platform effort involves the development of a comprehensive tool and platform for KG development with the following aims

1. Develop a KG development platform capable of instantiating KGs in any domains from structured, semi-structured, and unstructured data.

2. Improve & address the limitations of existing KG platforms

3. Constructs a Knowledge Graph (based on a combination of)

    • Enrich an existing Knowledge Graph (Top-down declarative)
    • Construct a Knowledge Graph out of given entities (Bottom-up data driven)

Scooner

Scooner Scooner is a knowledge-based literature search and exploration system where recently published results are computationally extracted and used a background KB to guide the search process. The key here is that the knowledge base that guides the search is extracted from the same universe of literature that is being explored.

Human Performance and Cognition Ontology

HPCO The human performance and cognition ontology (HPCO) project aims to achieve the following two major objectives

  1. Build a knowledge base using semi-automatic domain hierarchy construction and relationship extraction from PubMed citations;
  2. Build a tool to browse and explore scientific literature with the help of the knowledge base created in 1.

The project involves extending our work in focused knowledge (entity-relationship) extraction from scientific literature, automatic taxonomy extraction from selected community authored content (eg Wikipedia), and semi-automatic ontology development with limited expert guidance.

Healthcare KG

Leaders: Dr. Saeedeh Shekarpour, Dr. Amelie Gyrard

Internet of Things (IoT) KG

Leader: Dr. Amelie Gyrard


Linked Open Vocabularies for Internet of Things (LOV4IoT), an ontology catalog for Internet of Things, references ontology-based IoT projects:
- Almost 500 ontology-based projects for IoT, smart cities, etc.
- More than 20 domains relevant to IoT referenced such as building, smart grid, smart agriculture, robotics, smart transportation, healthcare, etc.
- We provide the LOV4IoT ontology catalog as an HTML view.
- We also provide the LOV4IoT RDF dataset.
LOV4IoT is an extension of the LOV (Linked Open Vocabulary) catalog.

  • Demo:



Knowledge Extraction for the Web of Things (KE4WoT) Challenge co-located with The Web Conference 2018 (WWW 2018)

Disaster Management KG

Leader: Hussein Al-Olimat, Shruti Kar

NSF Project: Hazards SEES: Social and Physical Sensing Enabled Decision Support for Disaster Management and Response

LOV4IoT-Disaster

Some publications:

  1. Shruti Kar, Hussein S. Al-Olimat, Krishnaprasad Thirunarayan, Valerie Shalin, Amit Sheth, and Srinivasan Parthasarathy. "D-record: Disaster Response and Relief Coordination Pipeline". In Proceedings of the ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities (ARIC 2018). ACM, 2018.

Security KG

Security Toolbox: Attacks and Countermeasures (STAC) is a project to assist developers in: 1) Designing secured applications or architectures. 2) Being aware of main security threats. 3) Exploring security in various technologies such as: Sensor Networks, Cellular Networks (2G, 3G, 4G), Wireless Networks (Wi-Fi, Wimax, Zigbee, Bluetooth), Mesh/M2M/MANET, Network Management, Web Applications, Cryptography, Attacks & Countermeasures, Security Properties (e.g., authentication, integrity), Etc.

  • Demo:


Robotics KG

Leader: Dr. Amelie Gyrard

Affective Science (Well-Being and Happiness) KG

Leader: Dr. Amelie Gyrard

Scientific paper: IAMHAPPY: Towards An IoT Knowledge-Based Cross-Domain Well-Being Recommendation System for Everyday Happiness. IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) Conference 2019. Elsevier Smart Health Journal

Retrieved from "https://wiki.aiisc.ai/index.php?title=EMPWR:_Knowledge_Graph_Development_Platform&oldid=13329"