Applying Knowledge-Based Reasoning for Information Fusion in Intelligence, Surveillance, and Reconnaissance

In this study, an information fusion component is presented, designed for fusing information acquired by a distributed surveillance system with prior information contained in intelligence databases. The fusion component is part of a larger system supporting the situational awareness of operators and decision makers in military and civil security domains based on concepts and processes in ISR (Intelligence, Surveillance and Reconnaissance). The distributed surveillance system is composed of unmanned aircraft systems, acquiring sensor data which has to be integrated with background information for providing useful input to a situational picture. To this end, the information fusion component includes mechanisms for information integration and conclusion drawing, based on an expressive knowledge model and on employing different reasoning techniques. This paper constitutes an extended version of [1], including further details on knowledge modeling, information extraction and model transformations as well as a first concept for an agent-based realization of the fusion system.

[1]  Jürgen Beyerer,et al.  Decision theoretic approaches for focussed Bayesian fusion , 2011, GI-Jahrestagung.

[2]  Serge Chaumette,et al.  Using heterogeneous multilevel swarms of UAVs and high-level data fusion to support situation management in surveillance scenarios , 2016, 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI).

[3]  Boris Motik,et al.  Optimising Ontology Classification , 2010, International Semantic Web Conference.

[4]  Achim Kuwertz,et al.  High-Level information management in joint ISR based on an object-oriented approach , 2017, 2017 Sensor Data Fusion: Trends, Solutions, Applications (SDF).

[5]  Christopher Ré,et al.  Tuffy: Scaling up Statistical Inference in Markov Logic Networks using an RDBMS , 2011, Proc. VLDB Endow..

[6]  Jürgen Beyerer,et al.  A local approach for Bayesian fusion: Mathematical analysis and agent based conception , 2009, Robotics Auton. Syst..

[7]  Gerd Schneider,et al.  ISR analytics: Architectural and methodic concepts , 2012, 2012 Workshop on Sensor Data Fusion: Trends, Solutions, Applications (SDF).

[8]  Kathryn B. Laskey MEBN: A language for first-order Bayesian knowledge bases , 2008, Artif. Intell..

[9]  Jürgen Beyerer,et al.  Fuselets: an agent based architecture for fusion of heterogeneous information and data , 2006, SPIE Defense + Commercial Sensing.

[10]  Jürgen Beyerer,et al.  Extending adaptive world modeling by identifying and handling insufficient knowledge models , 2016, J. Appl. Log..

[11]  Wilmuth Müller,et al.  Semantic information fusion to enhance situational awareness in surveillance scenarios , 2017, 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI).

[12]  Matthew Richardson,et al.  Just Add Weights: Markov Logic for the Semantic Web , 2008, URSW.

[13]  Subrata Das High-Level Data Fusion , 2008 .

[14]  Jürgen Beyerer,et al.  A local approach for focussed Bayesian fusion , 2009, Defense + Commercial Sensing.

[15]  Paulo Gomes,et al.  Instance-based probabilistic reasoning in the semantic web , 2009, WWW '09.

[16]  Yarden Katz,et al.  Pellet: A practical OWL-DL reasoner , 2007, J. Web Semant..

[17]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[18]  George J. Vachtsevanos,et al.  Handbook of Unmanned Aerial Vehicles , 2014 .