Smart Assistant for Mining (SAM)

To
 facilitate
 exploitation
 of

 data mining
 techniques
 by
 the
 increasingly
 IT‐ sophisticated
 NASA
 Earth
 science
 community,
 the
 University
 of
 Alabama
 in
 Huntsville
 led
 a
 collaborative
 team
 to
 leverage
 Semantic
 Web
 technologies
 to
 build
 a
 Smart
 Assistant
 for
 Mining
 (SAM)
 and
 to
 deploy
 it
 for
 use.
 This
 project

 reused
 an
 existing
 toolkit
 of
 data
 mining
 web
 services
 designed
 specifically
 for
 the
 analysis
 of
 NASA
 data
 in
 a
 web‐based,
 service‐oriented
 architecture.
 It

 also
 leverage
d and 
extend
ed an 
initial
 ontology 
describing
 data
 mining 
services 
with
 links 
to
 other
 ontologies
 describing
 the
 Earth
 science
 problem
 domain
 and
 relevant
 data
 sets.
 The
 new
 SAM
 user
 interface
 tool,
 which
 integrates
 semantic
 reasoning
 into
 a
 traditional
 workflow
 composer,

 allows
 users
 to
 discover
 available
 data
 and
 services,
 assists
 users
 in
 composing
 mining
 workflows,
 and
 invoke
s them
 to
 perform
 the 
desired 
analysis.