Transcript Infofusion highlights 2006

Information Fusion
Requirements on Databases
Ronnie Johansson
www.infofusion.se
Principles of data fusion automation
Richard T. Antony (JDL DFG member)
Artech House, 1995
470 pages
It’s like a thesis on data fusion algorithms,
problem-solving and database support
 There is reason to believe that the book is
focused on target tracking type defense
applications (spatial and hierarchical reasoning)
 Focusing on Ch 6 ”Database requirements” in
this discussion.




infofusion
Algorithm knowledge incorporation
 Declarative
 Short-term: signals, sensor data, images
 Medium-term: clusters, tracks, situations
 Long-term: doctrine, soil type
 Procedural
(long-term declarative knowledge w. control)
 Knowledge about how to reason: rules, patternbased classification
 Declarative and Procedural makes up 16
classes of fusion algorithms
(e.g., class I only relies on short-term knowledge, class VIII is general
machine learning)
infofusion
Infrastructure consideration
 Higher-level fusion algorithms (i.e., relying on
long-term and procedural knowledge) may be:
 Robust, Context-sensitive, and Efficient (in
computational requirements)
 However:
 Requires more complex algorithms and may
place heavy demands on DBMS
infofusion
Dependence on infrastructure
 Ex: Problems with ordinary DBMS
 A road network stored as a vector of
vertices
 Target tracking alg that depends on
the distance between the target and
the closest road – might require an
exhaustive search of all vertices.
 This might be too slow for real-time
tracking
infofusion
Storing declarative and procedural
knowledge
 Databases must support storage,
maintenance and query of both types
of knowledge.
 Declarative know. datastruct: tables,
semantic networks, decision trees,
lists, etc.
 Procedural know. datastruct:
pattern/action rules
infofusion
Claim
1. Lack of efficient database support for
spatial, temporal and hierarchical
reasoning is an obstacle to
sophisticated fusion algorithms.
2. Linear indexing not sufficient for data
search and manipulation.
infofusion
Database models: Relational
 Pros:
 More general than older models (hierarchical and
network models)
 Physical and logical data independence
 Standardized query interface
 Runs on numerous hardware platforms
 Cons:
 Table the only representation structure
 Joins can computationally expensive
 Spatial or combined spatial and temporal data may
be inefficient to both search and manipulate.
 Table-based data model cannot preserve complex
semantic relationships among data.
infofusion
Geographical information systems
(GIS)
 Pros:
 Supports storage and retrieval of spatially
organized information.
 Supports spatial search and 2-D set
operations.
 Cons:
 Does not support temporal reasoning
infofusion
Object-orient databases
 ”While OODBs conceptually supports
sophisticated [higher-order] problem
solving approaches, current [OODBs]
provides limited support for the
maintentance, query or manipulation
of spatial objects [and especially not
for real-time applications].”
infofusion
Algorithm requirements
1. Human problem-solving metaphor
2. Algorithmic issues
infofusion
Human problem-solving metaphor
 ”Biological systems maintain a
dynamic situation awareness wrt 3-D
space by fusing sensory-derived
information with a priori using
multiple level of abstraction analysis.”
infofusion
Algorithmic issues
 Spatial reasoning – entities of interest
are often spatially distributed
 Hierarchical reasoning – abstract
concepts, e.g., situations composed
of simpler elements
 Temporal reasoning – states and
situations typically change over time
infofusion
Temporal reasoning
 Implicit – time-stamped data, filtering
 Explicit – causality of events
infofusion
Algorithmic issues
 Support for retrieval from database
that is dependent on both spatial and
temporal aspects.
infofusion
Conclusions
 ”… the effectiveness and efficiency of
data fusion systems can be enhanced
by the development of highly robust,
context-sensitive and fusion
algorithms that in turn are supported
by database systems that both
facilitate alg. development and
enhance alg. efficency.”
infofusion