data science for joint doctrine dr. brand niemann director and senior data scientist/data journalist...
TRANSCRIPT
1
Data Science for Joint Doctrine
Dr. Brand NiemannDirector and Senior Data Scientist/Data Journalist
Semantic CommunitySemantic Community
Data ScienceData Science for Joint Doctrine
September 16-17, 2015
2
Overview
• August 31st Federal Big Data Working Group Meetup: Yosemite Project for Healthcare Information Interoperability & New Ontology Book• September 16-17th Information Meeting on Joint Doctrine Ontology
Invitation• Data Mine the Joint Electronic Library• Data Science for Joint Doctrine:• Knowledge Base• Spreadsheet Index• Spotfire Visualizations
3
http://www.meetup.com/Federal-Big-Data-Working-Group/events/224437815/
4
Building Ontologies with Basic Formal Ontology
• How to build an ontology• import BFO into ontology editor such as
Protégé• work with domain experts to create an
initial midlevel classification• find ~50 most commonly used terms
corresponding to types in reality• arrange these terms into an informal is_a
hierarchy• according to this universality principle
• A is_a B every instance of A is an instance of B• fill in missing terms to give a complete
hierarchy• (leave it to domain experts to populate the
lower levels of the hierarchy)
• BFO• A simple, small top-level ontology
to support information integration in scientific research
• Thoroughly tested in over 150 ontology development projects
• Large cadre of ontology development experts trained to use it
• No abstracta (numbers, propositions, …)
• No overlap with domain ontologiesBarry Smith, Federal Big Data Working Group, August 31, 2015
5
http://ncorwiki.buffalo.edu/index.php/Information_Meeting_on_Joint_Doctrine_Ontology
6
http://www.dtic.mil/doctrine/new_pubs/jointpub.htm
7
Data Mining - Science - Questions - Publication Process
• Data Mining Process:• Business Understanding• Data Understanding• Data Preparation• Modeling• Evaluation• Deployment
• Data Science Process:• Data Preparation• Data Ecosystem• Data Story
• Data Science Questions:• How was the data collected?• Where is the data stored?• What are the data results? and• Why should we believe the data results?
• Data Science Data Publication:• Knowledge Base• Spreadsheet Index• Web & PDF Tables to Spreadsheet• Data Browser• Dynamically Linked Adjacent
Visualizations
8
Semantic CommunityData ScienceData Science for Joint Doctrine
9
DoDJointDoctrineKnowledgeBase.xlsx
12
Conclusions and Recommendations
• Barry Smith has brought science to ontology with his new book: Building Ontologies with Basic Formal Ontology, just like science has come to data in Data Science.• The Federal Big Data Working Group Meetup follows a Data Mining -
Science - Questions - Publication Process which is being used on the Joint Doctrine Publications to support the Information Meeting on Joint Doctrine Ontology.• Ultimately, the nearly 70 Joint Doctrine PDF files could be converted to
Word and imported into MindTouch to create a Semantic Knowledge Base and Spreadsheet Index that could be visualized in Spotfire.