• Aucun résultat trouvé

Importance of Semantic Ontologies in Information Fusion

N/A
N/A
Protected

Academic year: 2022

Partager "Importance of Semantic Ontologies in Information Fusion"

Copied!
1
0
0

Texte intégral

(1)

STIDS 2016 Proceedings Page x

STIDS 2016 Invited Talk:

Importance of Semantic Ontologies in Information Fusion

Dr. Erik Blasch

Abstract

The use of semantic technologies has essential implications for information fusion systems solutions. An emerging development in high-level information fusion (HLIF) is the importance of the user for mission management, com- mand and control, as well as process refinement. The ability of the user to be part of the systems solution supports low-level information fusion (LLIF) functions of object, situation, and impact assessment. Future technology de- signs will require coordinating the LLIF physics-based big data measurements with the HLIF human-derived in- formation content. A semantic ontology is necessary for physics-based and human-derived information fusion (PHIF). The fusion of measurements and content should augment contextual understanding, refine uncertainty es- timates, and provide robust decision support. This talk will provide trends in high-level information fusion, address developments in an uncertainty ontology, and provide examples of PHIF. Examples include unmanned aerial vehi- cle (UAV), multi-intelligence, and space situation awareness.

Biography: Dr. Erik Blasch

Dr. Erik Blasch is a principal scientist at the the United States Air Force Research Laboratory (AFRL) in the In- formation Directorate at Rome, NY, USA. From 2009-2012, he was an exchange scientist to Defence Research and Development Canada (DRDC) at Valcartier, Quebec. From 2000-2009, Dr. Blasch was the Information Fusion Evaluation Tech Lead for the AFRL Sensors Directorate - COMprehensive Performance Assessment of Sensor Exploitation (COMPASE) Center supporting design evaluations in Dayton, OH. Dr. Blasch has been an Adjunct Electrical Engineering Professor at Wright State University teaching signal processing, target tracking, and infor- mation fusion.

He is a member of the International Society of Information Fusion (ISIF) Evaluation of Technologies for Uncer- tainty Reasoning Working Group (ETURWG) Automatic Target Recognition Working Group (ATRWG), and the Dynamic Data Driven Applications System (DDDAS) community. He served as a member of IEEE Aerospace and Electronics Systems Society (AESS) Board of Governors (BoG), was a founding member of the International Soci- ety of Information Fusion (ISIF) (www.isif.org), and the 2007 ISIF President. Recently, he was the Chairman for the AIAA/IEEE AESS Digital Avionics Systems Confernce focusing on the future for Unmanned Aerical Vehicle (UAV) traffic management (UTM).

He has focused on information fusion, target tracking, pattern recognition, and robitcs research compiling 600+

scientific papers and book chapters. He holds 10 patents, presented over 30 tutorials, and is an associate editor of three academic journals. He was a recipent of the Military Sensing Symposium Ledaership in Data Fusion Award, Fellow of SPIE, Associate Fellow of AIAA, and a senior member of IEEE.

Références

Documents relatifs

/ La version de cette publication peut être l’une des suivantes : la version prépublication de l’auteur, la version acceptée du manuscrit ou la version de l’éditeur. Access and

Keywords Information fusion · Driving scene understanding · Theory of belief functions · Dempster-Shafer theory · Object detection · Semantic seg-

In the preceding section, meta-knowledge concerned the relevance and the crudest form of lack of truthfulness of sources of information. However, in some applica- tions, the lack

L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des

Information Elaborée conjointement par l’équipe du Centre MITIC interjurassien et des enseignant-e-s des deux cantons, cette publication est destinée à mieux faire connaître

A modified weight vector of the category will be used to create the input vector for the SFAM, while the input itself can be generated by different sensors or just different

In our context, an Information Fusion Process (IFP) is defined as a discrete data-flow graph the nodes of which are fusion functions and the edges of which are links between

Cette seconde etape iterative consiste a predire la po- sition dans l'image du motif (en position, echelle et orientation), a calculer la di erence du motif observe a