SlideShare ist ein Scribd-Unternehmen logo
1 von 60
Downloaden Sie, um offline zu lesen
Knowledge Extraction for the Web of Things
(KE4WoT)
Friday 27 April 2018 (1:40pm-2:20pm), Challenge co-located with The Web
Conference (WWW 2018), 23-27 April, 2018
Ohio Center of Excellence in Knowledge-Enabled Computing
Amelie Gyrard, Manas Gaur,
Swati Padhee, Amit Sheth
Kno.e.sis Research Center
Department of Computer Science and Engineering,
Wright State University, Dayton, Ohio (USA)
Mihaela Juganaru-Mathieu
MINES Saint-Etienne, Institut Henri
Fayol, Saint Etienne, France
Challenge Website:
http://wiki.knoesis.org/index.php/KE4
WoTChallengeWWW2018
KE4WoT Challenge @ WWW 2018 Co-Chairs
3
Dr. Amelie Gyrard
Dr. Amit Sheth
Swati PadheeManas Gaur
Dr. Mihaela Juganaru-Mathieu
Agenda - 40 min Timeslot
• Introduction:
̶ From Internet of Things to Web of Things
̶ Challenge Interest - User feedback
• Challenge Tasks
̶ Tutorials to exploit the datasets
̶ Evaluation of the challenge tasks
• Research Impact
• Conclusion
• Demo and Poster session
4
Agenda - Demo and Poster Session
• Demo (Task 2): Neural Machine Translation Approach for Named Entity Recognition
̶ Philips Kokoh PRASETYO, School of Information Systems Singapore Management
University
̶ http://research.larc.smu.edu.sg/health-sense/s/predict
• Poster (Task 1): Semantic Web of Things
̶ Ruta et al., Poliba, Italy
̶ Also a Demo at WWW 2018: A journey from the Physical Web to the Physical
Semantic Web
5
Towards Semantic Web of Things
6
Connecting the Things to the Web
• Web-based applications are provided to easily monitor
data generated by devices
̶ Example: NetAtmo for smart home, Fitbit for smart
healthcare, Footbot for air quality
7
What is the Web of Things (WoT)?
Who is the pioneer of WoT?
8
Quiz time!
Web of Things (WoT) Overview
• How to send data produced by sensors/devices to the Web?
̶ Connecting the things/objects to the Web = The Web of Things
• Pioneer of the Web of Things: Dominique Guinard
̶ PhD Thesis: A Web of Things Application Architecture [Guinard
2011] and books
• Real-time Demo: http://devices.webofthings.io/
9
Tweet Example
• Tweet Example:
̶ Since taking asthma meds, my Fitbit shows my
heartbeat at >100 even during my nap! I feel like I can
hear my heart in my head #amidying
• How to automatically understand that FitBit and is a
device?
• How to automatically correlate this knowledge with
existing knowledge?
̶ For instance, there is the Fitbit Ontology!
10
Tweet Example 2
• IoT and smart cities ontologies
already describe sensors for air
quality!
• Health ontologies already designed
domain knowledge for Asthma and
allergy, etc.
11
Do you know what is an ontology?
12
Quiz time!
Why this challenge?
• A growing interest within standards to design ontologies for IoT:
̶ W3C Semantic Sensor Networks (SSN)
̶ W3C Web of Things
̶ OneM2M
̶ SAREF for smart building
̶ iot.schema.org
̶ etc.
13
http://wiki.knoesis.org/index.php/KE4WoTChallengeWWW2018#Description_of_the_KE4WoT_Challenge
KE4WoT Research Challenge Introduction
• How to exploit domain knowledge in already
designed in WoT applications?
̶ Frequently, models are designed to structure data
produced by devices
̶ Models referenced within the ontology catalogue for
Internet of Things (LOV4IoT)
• How to exploiting tweets related the healthcare
domain and correlate them with WoT?
14
Overview of the Challenge Tasks
15
KE4WoTChallenge
Task 1: Exploiting the Web of
Things Knowledge Base
Task 2: Creating a System
for extracting named
entities using Healthcare
Knowledge Sources and a
Q/A System over it
Task 1.1: Extracting the most
popular terms
Task 1.2: Ontology Matching
Task 2.1: Named Entity
Recognition in Healthcare
Unstructured Text
Task 2.2: Q/A System
Overall Interest for this Challenge
We design a user feedback form with some of the following questions:
• Q1: Expertise?
• Q2: Challenge task Interests?
• Q3: Why interested in this challenge?
• Q4: IoT applicative domain interest?
• Etc.
You can still fill in the form if you want to stay updated with the future
editions of this challenge: https://goo.gl/forms/iqP22wykRAuamAw43
16
Q1: Expertise? - Results
17
You can still fill in the form if you want to stay updated with the future
editions of this challenge: https://goo.gl/forms/iqP22wykRAuamAw43
Q2: Challenge task Interests? - Results
18
You can still fill in the form if you want to stay updated with the future
editions of this challenge: https://goo.gl/forms/iqP22wykRAuamAw43
Task 1.1: Extracting the most popular terms
Task 1.2: Ontology Matching
Task 2.1: Named Entity Recognition in
Healthcare Unstructured Text
Task 2.2: Q/A System
Q3: Why interested in this challenge? - Results
19
You can still fill in the form if you want to stay updated with the future
editions of this challenge: https://goo.gl/forms/iqP22wykRAuamAw43
Learning new technologies
Solving interesting problems
Compare our systems to other systems
Q4: IoT applicative domain interest? - Results
20
You can still fill in the form if you want to stay updated with the future
editions of this challenge: https://goo.gl/forms/iqP22wykRAuamAw43
Overview of the Challenge Tasks
21
KE4WoTChallenge
Task 1: Exploiting the Web of
Things Knowledge Base
Task 2: Creating a System
for extracting named
entities using Healthcare
Knowledge Sources and a
Q/A System over it
Task 1.1: Extracting the most
popular terms
Task 1.2: Ontology Matching
Task 2.1: Named Entity
Recognition in Healthcare
Unstructured Text
Task 2.2: Q/A System
Google Knowledge Graph
Video: https://www.youtube.com/watch?v=mmQl6VGvX-c
22
How to reuse WoT knowledge already designed?
Linked Open Vocabularies for
Internet of Things (LOV4IoT)
23
How to exploit the domain knowledge already available on
the Web and make it interoperable?
• Domain knowledge already structured and designed
• Ontologies used to share and reuse the domain knowledge
24
Collect InteroperabilityClassify
LOV4IoT in Real-Time - Demo
•
25
LOV4IoT Project: http://lov4iot.appspot.com/
LOV4IoT Demo Embedded
LOV4IoT Video on Youtube: https://youtu.be/a1zsdkzE_oY
26
Task 1: Exploiting the Web of Things Knowledge Base
• Ontology catalogue the Internet of Things and Web of Things
• More than 400 ontology-based projects for IoT, smart cities,
etc.
• Almost 20 domains relevant to IoT referenced such as
healthcare, building, smart grid, smart agriculture, smart
transportation, etc.
• LOV4IoT Project: http://lov4iot.appspot.com/
• We are aware of ontology catalogues such as LOV, BioPortal,
etc.:
̶ State of the art analysis here
27
LOV4IoT - IoT Ontology Web Services or Dumps
Tutorial
• LOV4IoT new functionalities created for the
KE4WoT challenge!
• Creation of web services to get the latest
insertions of ontology-based IoT projects.
• OR dump file of ontologies for a specific
domain
28LOV4IoT Project: http://lov4iot.appspot.com/
LOV4IoT - IoT Web Service & Tutorial - Demo
=> To automatically retrieve
the ontology code
29
LOV4IoT IoT Web Service: http://lov4iot.appspot.com/perfectoOnto/getOntoDomain/?domain=IoT
LOV4IoT - Healthcare Web Service & Tutorial - Demo
=> To automatically retrieve
the ontology code
30
LOV4IoT Healthcare Web Service:
Overview of the Challenge Tasks
31
KE4WoTChallenge
Task 1: Exploiting the Web of
Things Knowledge Base
Task 2: Creating a System
for extracting named
entities using Healthcare
Knowledge Sources and a
Q/A System over it
Task 1.1: Extracting the most
popular terms
Task 1.2: Ontology Matching
Task 2.1: Named Entity
Recognition in Healthcare
Unstructured Text
Task 2.2: Q/A System
Task 1.1: Extracting the Most Popular Terms - Evaluation
• Use case with IoT Ontologies:
• Evaluation online Table:
http://lov4iot.appspot.com/?p=OntologyExtractionKE4WoTChallengeWWW2018
32
Too many concepts:
- Neither aligned
- Nor part of core ontologies
like W3C SSN, W3C time
Overview of the Challenge Tasks
33
KE4WoTChallenge
Task 1: Exploiting the Web of
Things Knowledge Base
Task 2: Creating a System
for extracting named
entities using Healthcare
Knowledge Sources and a
Q/A System over it
Task 1.1: Extracting the most
popular terms
Task 1.2: Ontology Matching
Task 2.1: Named Entity
Recognition in Healthcare
Unstructured Text
Task 2.2: Q/A System
Task 1.2: Ontology Matching
• How to apply ontology matching tools to ontology referenced
with LOV4IoT?
• Why some ontologies cannot be loaded?
• How to share lessons learned and encourage best practices for
better semantic interoperability?
34Online Table: http://lov4iot.appspot.com/?p=OntologyAlignmentKE4WoTChallengeWWW2018
Task 1.2: Evaluation
35
Online Table: http://lov4iot.appspot.com/?p=OntologyAlignmentKE4WoTChallengeWWW2018
OAEI: http://oaei.ontologymatching.org/2017.5/
Encouraging to integrate an
IoT track within Ontology
Alignment Evaluation Initiative
(OAEI)
Poster (Task 1): Semantic Web of Things
36
Overview of the Challenge Tasks
37
KE4WoTChallenge
Task 1: Exploiting the Web
of Things Knowledge Base
Task 2: Creating a
System for extracting
named entities using
Healthcare Knowledge
Sources and a Q/A
System over it
Task 1.1: Extracting the
most popular terms
Task 1.2: Ontology
Matching
Task 2.1: Named Entity
Recognition in Healthcare
Unstructured Text
Task 2.2: Q/A System
Task 2: Overview
Named Entity Recognition in Healthcare Unstructured Text
• Definition: Named Entity Recognition (NER) is considered as an important natural
language processing task.
• Focus on health-care domain specific unstructured text obtained from Twitter.
38
Overview of the Challenge Tasks
39
KE4WoTChallenge
Task 1: Exploiting the Web of
Things Knowledge Base
Task 2: Creating a System
for extracting named
entities using Healthcare
Knowledge Sources and a
Q/A System over it
Task 1.1: Extracting the most
popular terms
Task 1.2: Ontology Matching
Task 2.1: Named Entity
Recognition in Healthcare
Unstructured Text
Task 2.2: Q/A System
Task 2.1: Description
We categorise the entities in healthcare text under following entity types:
■ Disease Entity: It is the name of the disease that is being explicitly stated in the text. Identification of this
entity enables discovery of etiological factors of the disease and its historical information.
■ Severity Entity (a severe form of disease entity): It is a disease entity that of etiological origin from a
relatively mild disease entity.
■ Trigger Entity: It is a disease entity/substance/environmental condition that caused/provoked the disease
entity identified in the text. For example, weather, measure cough rate, respiration patterns, heartbeat,
temperature and other body data.
■ Location Entity: Words listed under human anatomy are location entity. For instance, bones, muscles, nose,
lungs, etc.
■ Procedure/Treatment/Device: These are entities that define a procedure, treatment or device used by the
patient or clinician as an act to cure the disease entity stated in the text. For example, an inhaler is a device
to cure asthma.
■ Control: It is a dichotomous variable whose value is given “yes” when the tweet talks about disease control,
reduction in severity or reduced frequency of asthmatic attacks. This category is created for supporting the
question answering task.
40
Tweet Example
Input Tweet Text: Since taking asthma meds, my Fitbit shows my heartbeat at >100 even
during my nap! I feel like I can hear my heart in my head #amidying
Output:
■ Disease Entity: asthma
■ Severity Entity (severity of disease) : Missing
■ Trigger Entity (Findings/Triggers): asthma meds
■ Location Entity: heart
■ Procedure/Treatment/Devices: Fitbit
■ Control (binary variable): (yes/no) : no
41
Sample of Annotated Dataset
42
Task 2.1: Evaluation
• We expect an ensemble based learning system for identification Disease,
Severity, Triggers, Location qualifier, and Procedure entity types.
• Given an input, our evaluation is based on strict and approximate matching
of the entity type.
• Strict evaluation is performed in cases where the text contain single entity
of each entity types.
• Approximate evaluation is performed in cases where the text contain more
than single entity. In such a evaluation, we look for the “presence” of the
entity in our annotated set for each tweet.
43
Task 2.1: Evaluation
44
Demo (Task 2.1): Neural Machine Translation
Approach for Named Entity Recognition
45Demo URL: http://research.larc.smu.edu.sg/health-sense/s/predict
Overview of the Challenge Tasks
46
KE4WoTChallenge
Task 1: Exploiting the Web
of Things Knowledge Base
Task 2: Creating a
System for extracting
named entities using
Healthcare Knowledge
Sources and a Q/A
System over it
Task 1.1: Extracting the
most popular terms
Task 1.2: Ontology
Matching
Task 2.1: Named Entity
Recognition in Healthcare
Unstructured Text
Task 2.2: Q/A System
Task 2.2: Description
• In this Question Answering task, the participant will be required to provide a response
to a natural language question along with the relevant tweet ID and the model that
does the answering.
• In order to complete this task, the participant has to leverage their Named Entity
Recognition (NER) module developed in Task 2.1.
• One can utilize some existing knowledge sources (e.g. SNOMED, DBpedia, etc.) to
enhance the efficiency of their model.
• As a part of this task, the participant will have access to 25 natural language questions
on which they can create their model [1].
47
[1] https://github.com/gyrard/KE4WoT_Challenge_WWW2018/blob/master/Challenge_Dataset/questions.txt
1. Does dust mites causes asthma?
2. Does Prednisone risks obesity?
3. Does Prednisone risks weight gain?
4. Does bronchitis risks pneumonia?
5. Which disease is caused by Exercise-induced Bronchoconstriction?
6. Which drug treats asthma?
7. Which product treats childhood asthma?
8. What is the relation between anxiety and asthma?
9. What is the relation between asthma and COPD?
10. What is the cause of eosinophilic asthma?
11. One procedure for identify bronchitis?
12. Location affected by steroids?
48
13. Location affected by sinus infection?
14. Devices for controlling asthma?
15. Which disease is treated by Vitamin D?
16. Which disease is identified by Lung Bacteria?
17. Which disease is treated by Breastfeeding?
18. Which disease is caused by anabolic steroids?
19. Does eosinophilic pneumonia patients have chronic asthma?
20. What is the cause of sinus venous thrombosis?
21. Which disease is treated by Montelukast?
22. Does Black-mold causes asthma and allergy?
23. Does lung infection causes asthma?
24. Does CBD reduce allergy and asthma?
25. Is the Disease controlled? 49
Question Answering Task Example
■ Input Question: Does dupilumab control asthma ?
■ Answer: Yes
■ Relevant Tweet: Patients with severely uncontrolled asthma derive the most benefit
from dupilumab
50
Task 2.2: Evaluation
• 3 types of questions:
̶ <Entity><Relation><Entity> : Yes/No
• Does Prednisone risks obesity?
̶ <Entity-Type><Relation><Entity> : One or more entities
• Location affected by steroids?
̶ <Entity><?><Entity> : One or more relations
• What is the relation between asthma and COPD?
51
Overall Challenge Research Impact
52
Knowledge
Extraction
Internet of
Things
Natural
Language
Processing
Web of
Things
Medical
Text
Analysis
Semantic
Web
Conclusion & Future Work
• A lot of ontologies to build Web of Things applications
̶ More efforts are needed to extend the existing ones
̶ Common patterns are identified
• Future work:
̶ Ontology alignment initiative (OAEI) with an IoT track
̶ Sharing more semantic web best practices [1]
̶ Sharing more ontology catalogs for IoT
̶ How to find ontologies fitting our needs?
• Ontology ranking, etc.
[1] http://perfectsemanticweb.appspot.com/
53
Acknowledgments
• This work is partially funded by:
̶ A bilateral research convention with ENGIE Research & Development
̶ The National French ANR 14-CE24-0029 OpenSensingCity project
̶ Hazards SEES NSF Award EAR 1520870
̶ KHealth NIH 1 R01 HD087132-01.
54
Questions
55
Knowledge Extraction for the Web of Things
(KE4WoT)
Challenge co-located with The Web Conference (WWW 2018)
23-27 April, 2018
Ohio Center of Excellence in Knowledge-Enabled Computing
Amelie Gyrard, Manas Gaur,
Swati Padhee, Amit Sheth
Kno.e.sis Research Center
Department of Computer Science and Engineering, Wright
State University, Dayton, Ohio (USA)
Mihaela Juganaru-Mathieu
MINES Saint-Etienne, Institut Henri Fayol,
Saint Etienne, France
Appendix
57
Before IoT and WoT
=> Common Goal: Building
smart applications exploiting
sensor data generated by
devices?
=> All domains investigate
semantic web technologies 58
Internet of
Things (IoT)
Web of Things
(WoT)
Ubiquitous
Computing
Pervasive
Computing
Context
Awareness
Mark Weiser,
Kevin Ashton, 1999
Dominique Guinard, 2010
Dey et al., ?
2003
59
60

Weitere ähnliche Inhalte

Was ist angesagt?

Smart Cloud Engine and Solution based on Knowledge Base
Smart Cloud Engine and Solution based on Knowledge BaseSmart Cloud Engine and Solution based on Knowledge Base
Smart Cloud Engine and Solution based on Knowledge BasePaolo Nesi
 
From Data Platforms to Dataspaces: Enabling Data Ecosystems for Intelligent S...
From Data Platforms to Dataspaces: Enabling Data Ecosystems for Intelligent S...From Data Platforms to Dataspaces: Enabling Data Ecosystems for Intelligent S...
From Data Platforms to Dataspaces: Enabling Data Ecosystems for Intelligent S...Edward Curry
 
Km4City Smart City API: an integrated support for mobility services
Km4City Smart City API: an integrated support for mobility servicesKm4City Smart City API: an integrated support for mobility services
Km4City Smart City API: an integrated support for mobility servicesPaolo Nesi
 
Creating a Data Science Ecosystem for Scientific, Societal and Educational Im...
Creating a Data Science Ecosystem for Scientific, Societal and Educational Im...Creating a Data Science Ecosystem for Scientific, Societal and Educational Im...
Creating a Data Science Ecosystem for Scientific, Societal and Educational Im...Ilkay Altintas, Ph.D.
 
Data science presentation 2nd CI day
Data science presentation 2nd CI dayData science presentation 2nd CI day
Data science presentation 2nd CI dayMohammed Barakat
 
OntoSoft: A Distributed Semantic Registry for Scientific Software
OntoSoft: A Distributed Semantic Registry for Scientific SoftwareOntoSoft: A Distributed Semantic Registry for Scientific Software
OntoSoft: A Distributed Semantic Registry for Scientific Softwaredgarijo
 
AI & ML in Cyber Security - Why Algorithms Are Dangerous
AI & ML in Cyber Security - Why Algorithms Are DangerousAI & ML in Cyber Security - Why Algorithms Are Dangerous
AI & ML in Cyber Security - Why Algorithms Are DangerousRaffael Marty
 
Open Data, Big Data and Machine Learning
Open Data, Big Data and Machine LearningOpen Data, Big Data and Machine Learning
Open Data, Big Data and Machine LearningSteven Van Vaerenbergh
 
Lessons from Data Science Program at Indiana University: Curriculum, Students...
Lessons from Data Science Program at Indiana University: Curriculum, Students...Lessons from Data Science Program at Indiana University: Curriculum, Students...
Lessons from Data Science Program at Indiana University: Curriculum, Students...Geoffrey Fox
 
Data Science Curriculum at Indiana University
Data Science Curriculum at Indiana UniversityData Science Curriculum at Indiana University
Data Science Curriculum at Indiana UniversityGeoffrey Fox
 
Introduction on Data Science
Introduction on Data ScienceIntroduction on Data Science
Introduction on Data ScienceEdureka!
 
Machine Learning Introduction for Digital Business Leaders
Machine Learning Introduction for Digital Business LeadersMachine Learning Introduction for Digital Business Leaders
Machine Learning Introduction for Digital Business LeadersSudha Jamthe
 
Data Science: Not Just For Big Data
Data Science: Not Just For Big DataData Science: Not Just For Big Data
Data Science: Not Just For Big DataRevolution Analytics
 
How it works- Data Science
How it works- Data ScienceHow it works- Data Science
How it works- Data ScienceEdureka!
 
Search, Exploration and Analytics of Evolving Data
Search, Exploration and Analytics of Evolving DataSearch, Exploration and Analytics of Evolving Data
Search, Exploration and Analytics of Evolving DataNattiya Kanhabua
 
Introduction to Data Science
Introduction to Data ScienceIntroduction to Data Science
Introduction to Data ScienceEdureka!
 
Machine Learning using Big data
Machine Learning using Big data Machine Learning using Big data
Machine Learning using Big data Vaibhav Kurkute
 

Was ist angesagt? (19)

Smart Cloud Engine and Solution based on Knowledge Base
Smart Cloud Engine and Solution based on Knowledge BaseSmart Cloud Engine and Solution based on Knowledge Base
Smart Cloud Engine and Solution based on Knowledge Base
 
From Data Platforms to Dataspaces: Enabling Data Ecosystems for Intelligent S...
From Data Platforms to Dataspaces: Enabling Data Ecosystems for Intelligent S...From Data Platforms to Dataspaces: Enabling Data Ecosystems for Intelligent S...
From Data Platforms to Dataspaces: Enabling Data Ecosystems for Intelligent S...
 
Km4City Smart City API: an integrated support for mobility services
Km4City Smart City API: an integrated support for mobility servicesKm4City Smart City API: an integrated support for mobility services
Km4City Smart City API: an integrated support for mobility services
 
Creating a Data Science Ecosystem for Scientific, Societal and Educational Im...
Creating a Data Science Ecosystem for Scientific, Societal and Educational Im...Creating a Data Science Ecosystem for Scientific, Societal and Educational Im...
Creating a Data Science Ecosystem for Scientific, Societal and Educational Im...
 
Data science presentation 2nd CI day
Data science presentation 2nd CI dayData science presentation 2nd CI day
Data science presentation 2nd CI day
 
OntoSoft: A Distributed Semantic Registry for Scientific Software
OntoSoft: A Distributed Semantic Registry for Scientific SoftwareOntoSoft: A Distributed Semantic Registry for Scientific Software
OntoSoft: A Distributed Semantic Registry for Scientific Software
 
AI & ML in Cyber Security - Why Algorithms Are Dangerous
AI & ML in Cyber Security - Why Algorithms Are DangerousAI & ML in Cyber Security - Why Algorithms Are Dangerous
AI & ML in Cyber Security - Why Algorithms Are Dangerous
 
Open Data, Big Data and Machine Learning
Open Data, Big Data and Machine LearningOpen Data, Big Data and Machine Learning
Open Data, Big Data and Machine Learning
 
Lessons from Data Science Program at Indiana University: Curriculum, Students...
Lessons from Data Science Program at Indiana University: Curriculum, Students...Lessons from Data Science Program at Indiana University: Curriculum, Students...
Lessons from Data Science Program at Indiana University: Curriculum, Students...
 
Data Science using Python
Data Science using PythonData Science using Python
Data Science using Python
 
Data Science Curriculum at Indiana University
Data Science Curriculum at Indiana UniversityData Science Curriculum at Indiana University
Data Science Curriculum at Indiana University
 
Introduction on Data Science
Introduction on Data ScienceIntroduction on Data Science
Introduction on Data Science
 
Machine Learning Introduction for Digital Business Leaders
Machine Learning Introduction for Digital Business LeadersMachine Learning Introduction for Digital Business Leaders
Machine Learning Introduction for Digital Business Leaders
 
Intro to Data Science by DatalentTeam at Data Science Clinic#11
Intro to Data Science by DatalentTeam at Data Science Clinic#11Intro to Data Science by DatalentTeam at Data Science Clinic#11
Intro to Data Science by DatalentTeam at Data Science Clinic#11
 
Data Science: Not Just For Big Data
Data Science: Not Just For Big DataData Science: Not Just For Big Data
Data Science: Not Just For Big Data
 
How it works- Data Science
How it works- Data ScienceHow it works- Data Science
How it works- Data Science
 
Search, Exploration and Analytics of Evolving Data
Search, Exploration and Analytics of Evolving DataSearch, Exploration and Analytics of Evolving Data
Search, Exploration and Analytics of Evolving Data
 
Introduction to Data Science
Introduction to Data ScienceIntroduction to Data Science
Introduction to Data Science
 
Machine Learning using Big data
Machine Learning using Big data Machine Learning using Big data
Machine Learning using Big data
 

Ähnlich wie Knowledge Extraction for the Web of Things (KE4WoT) Challenge: Co-located with The Web Conference 2018 (WWW 2018)

Reusing and Unifying Background Knowledge for Internet of Things with LOV4IoT
Reusing and Unifying Background Knowledge for Internet of Things with LOV4IoTReusing and Unifying Background Knowledge for Internet of Things with LOV4IoT
Reusing and Unifying Background Knowledge for Internet of Things with LOV4IoTFIESTA-IoT
 
EADTU Conference - UKOER Technology Challenges
EADTU Conference - UKOER Technology ChallengesEADTU Conference - UKOER Technology Challenges
EADTU Conference - UKOER Technology ChallengesLorna Campbell
 
Exploiting Wikipedia for Information Retrieval Tasks, SIGIR Tutorial
Exploiting Wikipedia for Information Retrieval Tasks, SIGIR TutorialExploiting Wikipedia for Information Retrieval Tasks, SIGIR Tutorial
Exploiting Wikipedia for Information Retrieval Tasks, SIGIR TutorialVictor Makarenkov
 
Oerri briefing dec11
Oerri briefing dec11Oerri briefing dec11
Oerri briefing dec11Jisc
 
Semantic Web in the Plateau of Productivity
Semantic Web in the Plateau of ProductivitySemantic Web in the Plateau of Productivity
Semantic Web in the Plateau of ProductivityIoannis Stavrakantonakis
 
Semantic Web: In Quest for the Next Generation Killer Apps
Semantic Web: In Quest for the Next Generation Killer AppsSemantic Web: In Quest for the Next Generation Killer Apps
Semantic Web: In Quest for the Next Generation Killer AppsJie Bao
 
Internet of Things - Call presentations and hints from presenters
Internet of Things - Call presentations and hints from presentersInternet of Things - Call presentations and hints from presenters
Internet of Things - Call presentations and hints from presentersOpen & Agile Smart Cities
 
Challenges and Opportunities of the IoT Data and Service Interoperability
Challenges and Opportunities of the IoT Data and Service InteroperabilityChallenges and Opportunities of the IoT Data and Service Interoperability
Challenges and Opportunities of the IoT Data and Service InteroperabilitySensorUp
 
347 wk01 2013 copy
347 wk01 2013 copy347 wk01 2013 copy
347 wk01 2013 copyGuy Richards
 
NTCIR-12 MobileClick-2 Overview
NTCIR-12 MobileClick-2 OverviewNTCIR-12 MobileClick-2 Overview
NTCIR-12 MobileClick-2 Overviewkt.mako
 
TFI2014 Conference Opening - ISOC Deployment & Operationalization
TFI2014 Conference Opening - ISOC Deployment & OperationalizationTFI2014 Conference Opening - ISOC Deployment & Operationalization
TFI2014 Conference Opening - ISOC Deployment & OperationalizationColorado Internet Society (CO ISOC)
 
Wesleyan2.0
Wesleyan2.0Wesleyan2.0
Wesleyan2.0sbclapp
 
Grand Challenges Learning Analytics
Grand Challenges Learning AnalyticsGrand Challenges Learning Analytics
Grand Challenges Learning Analyticsamberg
 
OpenAIRE Infrastructure & Services: we need your input!
OpenAIRE Infrastructure & Services: we need your input!OpenAIRE Infrastructure & Services: we need your input!
OpenAIRE Infrastructure & Services: we need your input!OpenAIRE
 

Ähnlich wie Knowledge Extraction for the Web of Things (KE4WoT) Challenge: Co-located with The Web Conference 2018 (WWW 2018) (20)

Ioe orientation
Ioe orientationIoe orientation
Ioe orientation
 
Reusing and Unifying Background Knowledge for Internet of Things with LOV4IoT
Reusing and Unifying Background Knowledge for Internet of Things with LOV4IoTReusing and Unifying Background Knowledge for Internet of Things with LOV4IoT
Reusing and Unifying Background Knowledge for Internet of Things with LOV4IoT
 
EADTU Conference - UKOER Technology Challenges
EADTU Conference - UKOER Technology ChallengesEADTU Conference - UKOER Technology Challenges
EADTU Conference - UKOER Technology Challenges
 
Semantic Discovery in the Web of Things
Semantic Discovery in the Web of ThingsSemantic Discovery in the Web of Things
Semantic Discovery in the Web of Things
 
Exploiting Wikipedia for Information Retrieval Tasks, SIGIR Tutorial
Exploiting Wikipedia for Information Retrieval Tasks, SIGIR TutorialExploiting Wikipedia for Information Retrieval Tasks, SIGIR Tutorial
Exploiting Wikipedia for Information Retrieval Tasks, SIGIR Tutorial
 
Oerri briefing dec11
Oerri briefing dec11Oerri briefing dec11
Oerri briefing dec11
 
Semantic Web in the Plateau of Productivity
Semantic Web in the Plateau of ProductivitySemantic Web in the Plateau of Productivity
Semantic Web in the Plateau of Productivity
 
ION Belfast - Opening Slides - Chris Grundemann
ION Belfast - Opening Slides - Chris GrundemannION Belfast - Opening Slides - Chris Grundemann
ION Belfast - Opening Slides - Chris Grundemann
 
Social Media Dataset
Social Media DatasetSocial Media Dataset
Social Media Dataset
 
Semantic Web: In Quest for the Next Generation Killer Apps
Semantic Web: In Quest for the Next Generation Killer AppsSemantic Web: In Quest for the Next Generation Killer Apps
Semantic Web: In Quest for the Next Generation Killer Apps
 
Internet of Things - Call presentations and hints from presenters
Internet of Things - Call presentations and hints from presentersInternet of Things - Call presentations and hints from presenters
Internet of Things - Call presentations and hints from presenters
 
Data-X-v3.1
Data-X-v3.1Data-X-v3.1
Data-X-v3.1
 
Challenges and Opportunities of the IoT Data and Service Interoperability
Challenges and Opportunities of the IoT Data and Service InteroperabilityChallenges and Opportunities of the IoT Data and Service Interoperability
Challenges and Opportunities of the IoT Data and Service Interoperability
 
347 wk01 2013 copy
347 wk01 2013 copy347 wk01 2013 copy
347 wk01 2013 copy
 
NTCIR-12 MobileClick-2 Overview
NTCIR-12 MobileClick-2 OverviewNTCIR-12 MobileClick-2 Overview
NTCIR-12 MobileClick-2 Overview
 
Data-X-Sparse-v2
Data-X-Sparse-v2Data-X-Sparse-v2
Data-X-Sparse-v2
 
TFI2014 Conference Opening - ISOC Deployment & Operationalization
TFI2014 Conference Opening - ISOC Deployment & OperationalizationTFI2014 Conference Opening - ISOC Deployment & Operationalization
TFI2014 Conference Opening - ISOC Deployment & Operationalization
 
Wesleyan2.0
Wesleyan2.0Wesleyan2.0
Wesleyan2.0
 
Grand Challenges Learning Analytics
Grand Challenges Learning AnalyticsGrand Challenges Learning Analytics
Grand Challenges Learning Analytics
 
OpenAIRE Infrastructure & Services: we need your input!
OpenAIRE Infrastructure & Services: we need your input!OpenAIRE Infrastructure & Services: we need your input!
OpenAIRE Infrastructure & Services: we need your input!
 

Mehr von Amélie Gyrard

Toward a Semantic Web of Vehicles
Toward a Semantic Web of VehiclesToward a Semantic Web of Vehicles
Toward a Semantic Web of VehiclesAmélie Gyrard
 
Presentation aina2016 seg3.0_methodology_v2
Presentation aina2016 seg3.0_methodology_v2Presentation aina2016 seg3.0_methodology_v2
Presentation aina2016 seg3.0_methodology_v2Amélie Gyrard
 
Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...
Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...
Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...Amélie Gyrard
 
A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...
A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...
A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...Amélie Gyrard
 
Fi cloudpresentationgyrardaugust2015 v2
Fi cloudpresentationgyrardaugust2015 v2Fi cloudpresentationgyrardaugust2015 v2
Fi cloudpresentationgyrardaugust2015 v2Amélie Gyrard
 
Designing Cross-Domain Semantic Web of Things Applications
Designing Cross-Domain Semantic Web of Things ApplicationsDesigning Cross-Domain Semantic Web of Things Applications
Designing Cross-Domain Semantic Web of Things ApplicationsAmélie Gyrard
 
Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...
Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...
Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...Amélie Gyrard
 
An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...
An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...
An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...Amélie Gyrard
 
Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...
Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...
Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...Amélie Gyrard
 
An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...
An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...
An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...Amélie Gyrard
 

Mehr von Amélie Gyrard (10)

Toward a Semantic Web of Vehicles
Toward a Semantic Web of VehiclesToward a Semantic Web of Vehicles
Toward a Semantic Web of Vehicles
 
Presentation aina2016 seg3.0_methodology_v2
Presentation aina2016 seg3.0_methodology_v2Presentation aina2016 seg3.0_methodology_v2
Presentation aina2016 seg3.0_methodology_v2
 
Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...
Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...
Assisting IoT Projects and Developers in Designing Interoperable Semantic Web...
 
A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...
A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...
A Unified Semantic Engine for Internet of Things and Smart Cities: From Senso...
 
Fi cloudpresentationgyrardaugust2015 v2
Fi cloudpresentationgyrardaugust2015 v2Fi cloudpresentationgyrardaugust2015 v2
Fi cloudpresentationgyrardaugust2015 v2
 
Designing Cross-Domain Semantic Web of Things Applications
Designing Cross-Domain Semantic Web of Things ApplicationsDesigning Cross-Domain Semantic Web of Things Applications
Designing Cross-Domain Semantic Web of Things Applications
 
Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...
Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...
Gyrard ssn2014 Helping IoT Application Developers with Sensor-based Linked Op...
 
An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...
An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...
An ontology-based approach for helping to secure the ETSI Machine-to-Machine ...
 
Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...
Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...
Enrich Machine-to-Machine Data with Semantic Web Technologies for Cross-Domai...
 
An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...
An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...
An Ontology to Semantically Annotate the Machine-to-Machine (M2M) Device Meas...
 

Kürzlich hochgeladen

Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...
Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...
Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...OnePlan Solutions
 
SpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at RuntimeSpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at Runtimeandrehoraa
 
Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...
Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...
Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...OnePlan Solutions
 
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Cizo Technology Services
 
Post Quantum Cryptography – The Impact on Identity
Post Quantum Cryptography – The Impact on IdentityPost Quantum Cryptography – The Impact on Identity
Post Quantum Cryptography – The Impact on Identityteam-WIBU
 
Powering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsPowering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsSafe Software
 
Automate your Kamailio Test Calls - Kamailio World 2024
Automate your Kamailio Test Calls - Kamailio World 2024Automate your Kamailio Test Calls - Kamailio World 2024
Automate your Kamailio Test Calls - Kamailio World 2024Andreas Granig
 
Cyber security and its impact on E commerce
Cyber security and its impact on E commerceCyber security and its impact on E commerce
Cyber security and its impact on E commercemanigoyal112
 
Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Mater
 
Implementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureImplementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureDinusha Kumarasiri
 
SuccessFactors 1H 2024 Release - Sneak-Peek by Deloitte Germany
SuccessFactors 1H 2024 Release - Sneak-Peek by Deloitte GermanySuccessFactors 1H 2024 Release - Sneak-Peek by Deloitte Germany
SuccessFactors 1H 2024 Release - Sneak-Peek by Deloitte GermanyChristoph Pohl
 
Precise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalPrecise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalLionel Briand
 
Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)
Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)
Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)jennyeacort
 
What is Advanced Excel and what are some best practices for designing and cre...
What is Advanced Excel and what are some best practices for designing and cre...What is Advanced Excel and what are some best practices for designing and cre...
What is Advanced Excel and what are some best practices for designing and cre...Technogeeks
 
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...confluent
 
Simplifying Microservices & Apps - The art of effortless development - Meetup...
Simplifying Microservices & Apps - The art of effortless development - Meetup...Simplifying Microservices & Apps - The art of effortless development - Meetup...
Simplifying Microservices & Apps - The art of effortless development - Meetup...Rob Geurden
 
Xen Safety Embedded OSS Summit April 2024 v4.pdf
Xen Safety Embedded OSS Summit April 2024 v4.pdfXen Safety Embedded OSS Summit April 2024 v4.pdf
Xen Safety Embedded OSS Summit April 2024 v4.pdfStefano Stabellini
 
20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...
20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...
20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...Akihiro Suda
 
Salesforce Implementation Services PPT By ABSYZ
Salesforce Implementation Services PPT By ABSYZSalesforce Implementation Services PPT By ABSYZ
Salesforce Implementation Services PPT By ABSYZABSYZ Inc
 
Folding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesFolding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesPhilip Schwarz
 

Kürzlich hochgeladen (20)

Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...
Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...
Tech Tuesday - Mastering Time Management Unlock the Power of OnePlan's Timesh...
 
SpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at RuntimeSpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at Runtime
 
Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...
Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...
Maximizing Efficiency and Profitability with OnePlan’s Professional Service A...
 
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
Global Identity Enrolment and Verification Pro Solution - Cizo Technology Ser...
 
Post Quantum Cryptography – The Impact on Identity
Post Quantum Cryptography – The Impact on IdentityPost Quantum Cryptography – The Impact on Identity
Post Quantum Cryptography – The Impact on Identity
 
Powering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsPowering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data Streams
 
Automate your Kamailio Test Calls - Kamailio World 2024
Automate your Kamailio Test Calls - Kamailio World 2024Automate your Kamailio Test Calls - Kamailio World 2024
Automate your Kamailio Test Calls - Kamailio World 2024
 
Cyber security and its impact on E commerce
Cyber security and its impact on E commerceCyber security and its impact on E commerce
Cyber security and its impact on E commerce
 
Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)
 
Implementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with AzureImplementing Zero Trust strategy with Azure
Implementing Zero Trust strategy with Azure
 
SuccessFactors 1H 2024 Release - Sneak-Peek by Deloitte Germany
SuccessFactors 1H 2024 Release - Sneak-Peek by Deloitte GermanySuccessFactors 1H 2024 Release - Sneak-Peek by Deloitte Germany
SuccessFactors 1H 2024 Release - Sneak-Peek by Deloitte Germany
 
Precise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive GoalPrecise and Complete Requirements? An Elusive Goal
Precise and Complete Requirements? An Elusive Goal
 
Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)
Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)
Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)
 
What is Advanced Excel and what are some best practices for designing and cre...
What is Advanced Excel and what are some best practices for designing and cre...What is Advanced Excel and what are some best practices for designing and cre...
What is Advanced Excel and what are some best practices for designing and cre...
 
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
Catch the Wave: SAP Event-Driven and Data Streaming for the Intelligence Ente...
 
Simplifying Microservices & Apps - The art of effortless development - Meetup...
Simplifying Microservices & Apps - The art of effortless development - Meetup...Simplifying Microservices & Apps - The art of effortless development - Meetup...
Simplifying Microservices & Apps - The art of effortless development - Meetup...
 
Xen Safety Embedded OSS Summit April 2024 v4.pdf
Xen Safety Embedded OSS Summit April 2024 v4.pdfXen Safety Embedded OSS Summit April 2024 v4.pdf
Xen Safety Embedded OSS Summit April 2024 v4.pdf
 
20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...
20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...
20240415 [Container Plumbing Days] Usernetes Gen2 - Kubernetes in Rootless Do...
 
Salesforce Implementation Services PPT By ABSYZ
Salesforce Implementation Services PPT By ABSYZSalesforce Implementation Services PPT By ABSYZ
Salesforce Implementation Services PPT By ABSYZ
 
Folding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesFolding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a series
 

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

  • 1. Knowledge Extraction for the Web of Things (KE4WoT) Friday 27 April 2018 (1:40pm-2:20pm), Challenge co-located with The Web Conference (WWW 2018), 23-27 April, 2018 Ohio Center of Excellence in Knowledge-Enabled Computing Amelie Gyrard, Manas Gaur, Swati Padhee, Amit Sheth Kno.e.sis Research Center Department of Computer Science and Engineering, Wright State University, Dayton, Ohio (USA) Mihaela Juganaru-Mathieu MINES Saint-Etienne, Institut Henri Fayol, Saint Etienne, France
  • 3. KE4WoT Challenge @ WWW 2018 Co-Chairs 3 Dr. Amelie Gyrard Dr. Amit Sheth Swati PadheeManas Gaur Dr. Mihaela Juganaru-Mathieu
  • 4. Agenda - 40 min Timeslot • Introduction: ̶ From Internet of Things to Web of Things ̶ Challenge Interest - User feedback • Challenge Tasks ̶ Tutorials to exploit the datasets ̶ Evaluation of the challenge tasks • Research Impact • Conclusion • Demo and Poster session 4
  • 5. Agenda - Demo and Poster Session • Demo (Task 2): Neural Machine Translation Approach for Named Entity Recognition ̶ Philips Kokoh PRASETYO, School of Information Systems Singapore Management University ̶ http://research.larc.smu.edu.sg/health-sense/s/predict • Poster (Task 1): Semantic Web of Things ̶ Ruta et al., Poliba, Italy ̶ Also a Demo at WWW 2018: A journey from the Physical Web to the Physical Semantic Web 5
  • 6. Towards Semantic Web of Things 6
  • 7. Connecting the Things to the Web • Web-based applications are provided to easily monitor data generated by devices ̶ Example: NetAtmo for smart home, Fitbit for smart healthcare, Footbot for air quality 7
  • 8. What is the Web of Things (WoT)? Who is the pioneer of WoT? 8 Quiz time!
  • 9. Web of Things (WoT) Overview • How to send data produced by sensors/devices to the Web? ̶ Connecting the things/objects to the Web = The Web of Things • Pioneer of the Web of Things: Dominique Guinard ̶ PhD Thesis: A Web of Things Application Architecture [Guinard 2011] and books • Real-time Demo: http://devices.webofthings.io/ 9
  • 10. Tweet Example • Tweet Example: ̶ Since taking asthma meds, my Fitbit shows my heartbeat at >100 even during my nap! I feel like I can hear my heart in my head #amidying • How to automatically understand that FitBit and is a device? • How to automatically correlate this knowledge with existing knowledge? ̶ For instance, there is the Fitbit Ontology! 10
  • 11. Tweet Example 2 • IoT and smart cities ontologies already describe sensors for air quality! • Health ontologies already designed domain knowledge for Asthma and allergy, etc. 11
  • 12. Do you know what is an ontology? 12 Quiz time!
  • 13. Why this challenge? • A growing interest within standards to design ontologies for IoT: ̶ W3C Semantic Sensor Networks (SSN) ̶ W3C Web of Things ̶ OneM2M ̶ SAREF for smart building ̶ iot.schema.org ̶ etc. 13 http://wiki.knoesis.org/index.php/KE4WoTChallengeWWW2018#Description_of_the_KE4WoT_Challenge
  • 14. KE4WoT Research Challenge Introduction • How to exploit domain knowledge in already designed in WoT applications? ̶ Frequently, models are designed to structure data produced by devices ̶ Models referenced within the ontology catalogue for Internet of Things (LOV4IoT) • How to exploiting tweets related the healthcare domain and correlate them with WoT? 14
  • 15. Overview of the Challenge Tasks 15 KE4WoTChallenge Task 1: Exploiting the Web of Things Knowledge Base Task 2: Creating a System for extracting named entities using Healthcare Knowledge Sources and a Q/A System over it Task 1.1: Extracting the most popular terms Task 1.2: Ontology Matching Task 2.1: Named Entity Recognition in Healthcare Unstructured Text Task 2.2: Q/A System
  • 16. Overall Interest for this Challenge We design a user feedback form with some of the following questions: • Q1: Expertise? • Q2: Challenge task Interests? • Q3: Why interested in this challenge? • Q4: IoT applicative domain interest? • Etc. You can still fill in the form if you want to stay updated with the future editions of this challenge: https://goo.gl/forms/iqP22wykRAuamAw43 16
  • 17. Q1: Expertise? - Results 17 You can still fill in the form if you want to stay updated with the future editions of this challenge: https://goo.gl/forms/iqP22wykRAuamAw43
  • 18. Q2: Challenge task Interests? - Results 18 You can still fill in the form if you want to stay updated with the future editions of this challenge: https://goo.gl/forms/iqP22wykRAuamAw43 Task 1.1: Extracting the most popular terms Task 1.2: Ontology Matching Task 2.1: Named Entity Recognition in Healthcare Unstructured Text Task 2.2: Q/A System
  • 19. Q3: Why interested in this challenge? - Results 19 You can still fill in the form if you want to stay updated with the future editions of this challenge: https://goo.gl/forms/iqP22wykRAuamAw43 Learning new technologies Solving interesting problems Compare our systems to other systems
  • 20. Q4: IoT applicative domain interest? - Results 20 You can still fill in the form if you want to stay updated with the future editions of this challenge: https://goo.gl/forms/iqP22wykRAuamAw43
  • 21. Overview of the Challenge Tasks 21 KE4WoTChallenge Task 1: Exploiting the Web of Things Knowledge Base Task 2: Creating a System for extracting named entities using Healthcare Knowledge Sources and a Q/A System over it Task 1.1: Extracting the most popular terms Task 1.2: Ontology Matching Task 2.1: Named Entity Recognition in Healthcare Unstructured Text Task 2.2: Q/A System
  • 22. Google Knowledge Graph Video: https://www.youtube.com/watch?v=mmQl6VGvX-c 22
  • 23. How to reuse WoT knowledge already designed? Linked Open Vocabularies for Internet of Things (LOV4IoT) 23
  • 24. How to exploit the domain knowledge already available on the Web and make it interoperable? • Domain knowledge already structured and designed • Ontologies used to share and reuse the domain knowledge 24 Collect InteroperabilityClassify
  • 25. LOV4IoT in Real-Time - Demo • 25 LOV4IoT Project: http://lov4iot.appspot.com/
  • 26. LOV4IoT Demo Embedded LOV4IoT Video on Youtube: https://youtu.be/a1zsdkzE_oY 26
  • 27. Task 1: Exploiting the Web of Things Knowledge Base • Ontology catalogue the Internet of Things and Web of Things • More than 400 ontology-based projects for IoT, smart cities, etc. • Almost 20 domains relevant to IoT referenced such as healthcare, building, smart grid, smart agriculture, smart transportation, etc. • LOV4IoT Project: http://lov4iot.appspot.com/ • We are aware of ontology catalogues such as LOV, BioPortal, etc.: ̶ State of the art analysis here 27
  • 28. LOV4IoT - IoT Ontology Web Services or Dumps Tutorial • LOV4IoT new functionalities created for the KE4WoT challenge! • Creation of web services to get the latest insertions of ontology-based IoT projects. • OR dump file of ontologies for a specific domain 28LOV4IoT Project: http://lov4iot.appspot.com/
  • 29. LOV4IoT - IoT Web Service & Tutorial - Demo => To automatically retrieve the ontology code 29 LOV4IoT IoT Web Service: http://lov4iot.appspot.com/perfectoOnto/getOntoDomain/?domain=IoT
  • 30. LOV4IoT - Healthcare Web Service & Tutorial - Demo => To automatically retrieve the ontology code 30 LOV4IoT Healthcare Web Service:
  • 31. Overview of the Challenge Tasks 31 KE4WoTChallenge Task 1: Exploiting the Web of Things Knowledge Base Task 2: Creating a System for extracting named entities using Healthcare Knowledge Sources and a Q/A System over it Task 1.1: Extracting the most popular terms Task 1.2: Ontology Matching Task 2.1: Named Entity Recognition in Healthcare Unstructured Text Task 2.2: Q/A System
  • 32. Task 1.1: Extracting the Most Popular Terms - Evaluation • Use case with IoT Ontologies: • Evaluation online Table: http://lov4iot.appspot.com/?p=OntologyExtractionKE4WoTChallengeWWW2018 32 Too many concepts: - Neither aligned - Nor part of core ontologies like W3C SSN, W3C time
  • 33. Overview of the Challenge Tasks 33 KE4WoTChallenge Task 1: Exploiting the Web of Things Knowledge Base Task 2: Creating a System for extracting named entities using Healthcare Knowledge Sources and a Q/A System over it Task 1.1: Extracting the most popular terms Task 1.2: Ontology Matching Task 2.1: Named Entity Recognition in Healthcare Unstructured Text Task 2.2: Q/A System
  • 34. Task 1.2: Ontology Matching • How to apply ontology matching tools to ontology referenced with LOV4IoT? • Why some ontologies cannot be loaded? • How to share lessons learned and encourage best practices for better semantic interoperability? 34Online Table: http://lov4iot.appspot.com/?p=OntologyAlignmentKE4WoTChallengeWWW2018
  • 35. Task 1.2: Evaluation 35 Online Table: http://lov4iot.appspot.com/?p=OntologyAlignmentKE4WoTChallengeWWW2018 OAEI: http://oaei.ontologymatching.org/2017.5/ Encouraging to integrate an IoT track within Ontology Alignment Evaluation Initiative (OAEI)
  • 36. Poster (Task 1): Semantic Web of Things 36
  • 37. Overview of the Challenge Tasks 37 KE4WoTChallenge Task 1: Exploiting the Web of Things Knowledge Base Task 2: Creating a System for extracting named entities using Healthcare Knowledge Sources and a Q/A System over it Task 1.1: Extracting the most popular terms Task 1.2: Ontology Matching Task 2.1: Named Entity Recognition in Healthcare Unstructured Text Task 2.2: Q/A System
  • 38. Task 2: Overview Named Entity Recognition in Healthcare Unstructured Text • Definition: Named Entity Recognition (NER) is considered as an important natural language processing task. • Focus on health-care domain specific unstructured text obtained from Twitter. 38
  • 39. Overview of the Challenge Tasks 39 KE4WoTChallenge Task 1: Exploiting the Web of Things Knowledge Base Task 2: Creating a System for extracting named entities using Healthcare Knowledge Sources and a Q/A System over it Task 1.1: Extracting the most popular terms Task 1.2: Ontology Matching Task 2.1: Named Entity Recognition in Healthcare Unstructured Text Task 2.2: Q/A System
  • 40. Task 2.1: Description We categorise the entities in healthcare text under following entity types: ■ Disease Entity: It is the name of the disease that is being explicitly stated in the text. Identification of this entity enables discovery of etiological factors of the disease and its historical information. ■ Severity Entity (a severe form of disease entity): It is a disease entity that of etiological origin from a relatively mild disease entity. ■ Trigger Entity: It is a disease entity/substance/environmental condition that caused/provoked the disease entity identified in the text. For example, weather, measure cough rate, respiration patterns, heartbeat, temperature and other body data. ■ Location Entity: Words listed under human anatomy are location entity. For instance, bones, muscles, nose, lungs, etc. ■ Procedure/Treatment/Device: These are entities that define a procedure, treatment or device used by the patient or clinician as an act to cure the disease entity stated in the text. For example, an inhaler is a device to cure asthma. ■ Control: It is a dichotomous variable whose value is given “yes” when the tweet talks about disease control, reduction in severity or reduced frequency of asthmatic attacks. This category is created for supporting the question answering task. 40
  • 41. Tweet Example Input Tweet Text: Since taking asthma meds, my Fitbit shows my heartbeat at >100 even during my nap! I feel like I can hear my heart in my head #amidying Output: ■ Disease Entity: asthma ■ Severity Entity (severity of disease) : Missing ■ Trigger Entity (Findings/Triggers): asthma meds ■ Location Entity: heart ■ Procedure/Treatment/Devices: Fitbit ■ Control (binary variable): (yes/no) : no 41
  • 42. Sample of Annotated Dataset 42
  • 43. Task 2.1: Evaluation • We expect an ensemble based learning system for identification Disease, Severity, Triggers, Location qualifier, and Procedure entity types. • Given an input, our evaluation is based on strict and approximate matching of the entity type. • Strict evaluation is performed in cases where the text contain single entity of each entity types. • Approximate evaluation is performed in cases where the text contain more than single entity. In such a evaluation, we look for the “presence” of the entity in our annotated set for each tweet. 43
  • 45. Demo (Task 2.1): Neural Machine Translation Approach for Named Entity Recognition 45Demo URL: http://research.larc.smu.edu.sg/health-sense/s/predict
  • 46. Overview of the Challenge Tasks 46 KE4WoTChallenge Task 1: Exploiting the Web of Things Knowledge Base Task 2: Creating a System for extracting named entities using Healthcare Knowledge Sources and a Q/A System over it Task 1.1: Extracting the most popular terms Task 1.2: Ontology Matching Task 2.1: Named Entity Recognition in Healthcare Unstructured Text Task 2.2: Q/A System
  • 47. Task 2.2: Description • In this Question Answering task, the participant will be required to provide a response to a natural language question along with the relevant tweet ID and the model that does the answering. • In order to complete this task, the participant has to leverage their Named Entity Recognition (NER) module developed in Task 2.1. • One can utilize some existing knowledge sources (e.g. SNOMED, DBpedia, etc.) to enhance the efficiency of their model. • As a part of this task, the participant will have access to 25 natural language questions on which they can create their model [1]. 47 [1] https://github.com/gyrard/KE4WoT_Challenge_WWW2018/blob/master/Challenge_Dataset/questions.txt
  • 48. 1. Does dust mites causes asthma? 2. Does Prednisone risks obesity? 3. Does Prednisone risks weight gain? 4. Does bronchitis risks pneumonia? 5. Which disease is caused by Exercise-induced Bronchoconstriction? 6. Which drug treats asthma? 7. Which product treats childhood asthma? 8. What is the relation between anxiety and asthma? 9. What is the relation between asthma and COPD? 10. What is the cause of eosinophilic asthma? 11. One procedure for identify bronchitis? 12. Location affected by steroids? 48
  • 49. 13. Location affected by sinus infection? 14. Devices for controlling asthma? 15. Which disease is treated by Vitamin D? 16. Which disease is identified by Lung Bacteria? 17. Which disease is treated by Breastfeeding? 18. Which disease is caused by anabolic steroids? 19. Does eosinophilic pneumonia patients have chronic asthma? 20. What is the cause of sinus venous thrombosis? 21. Which disease is treated by Montelukast? 22. Does Black-mold causes asthma and allergy? 23. Does lung infection causes asthma? 24. Does CBD reduce allergy and asthma? 25. Is the Disease controlled? 49
  • 50. Question Answering Task Example ■ Input Question: Does dupilumab control asthma ? ■ Answer: Yes ■ Relevant Tweet: Patients with severely uncontrolled asthma derive the most benefit from dupilumab 50
  • 51. Task 2.2: Evaluation • 3 types of questions: ̶ <Entity><Relation><Entity> : Yes/No • Does Prednisone risks obesity? ̶ <Entity-Type><Relation><Entity> : One or more entities • Location affected by steroids? ̶ <Entity><?><Entity> : One or more relations • What is the relation between asthma and COPD? 51
  • 52. Overall Challenge Research Impact 52 Knowledge Extraction Internet of Things Natural Language Processing Web of Things Medical Text Analysis Semantic Web
  • 53. Conclusion & Future Work • A lot of ontologies to build Web of Things applications ̶ More efforts are needed to extend the existing ones ̶ Common patterns are identified • Future work: ̶ Ontology alignment initiative (OAEI) with an IoT track ̶ Sharing more semantic web best practices [1] ̶ Sharing more ontology catalogs for IoT ̶ How to find ontologies fitting our needs? • Ontology ranking, etc. [1] http://perfectsemanticweb.appspot.com/ 53
  • 54. Acknowledgments • This work is partially funded by: ̶ A bilateral research convention with ENGIE Research & Development ̶ The National French ANR 14-CE24-0029 OpenSensingCity project ̶ Hazards SEES NSF Award EAR 1520870 ̶ KHealth NIH 1 R01 HD087132-01. 54
  • 56. Knowledge Extraction for the Web of Things (KE4WoT) Challenge co-located with The Web Conference (WWW 2018) 23-27 April, 2018 Ohio Center of Excellence in Knowledge-Enabled Computing Amelie Gyrard, Manas Gaur, Swati Padhee, Amit Sheth Kno.e.sis Research Center Department of Computer Science and Engineering, Wright State University, Dayton, Ohio (USA) Mihaela Juganaru-Mathieu MINES Saint-Etienne, Institut Henri Fayol, Saint Etienne, France
  • 58. Before IoT and WoT => Common Goal: Building smart applications exploiting sensor data generated by devices? => All domains investigate semantic web technologies 58 Internet of Things (IoT) Web of Things (WoT) Ubiquitous Computing Pervasive Computing Context Awareness Mark Weiser, Kevin Ashton, 1999 Dominique Guinard, 2010 Dey et al., ? 2003
  • 59. 59
  • 60. 60