Transitioning mine warfare to network-centric sensor analysis: future PMA technologies & capabilities

The purpose of this paper is to outline the requisite technologies and enabling capabilities for network-centric sensor data analysis within the mine warfare community. The focus includes both automated processing and the traditional humancentric post-mission analysis (PMA) of tactical and environmental sensor data. This is motivated by first examining the high-level network-centric guidance and noting the breakdown in the process of distilling actionable requirements from this guidance. Examples are provided that illustrate the intuitive and substantial capability improvement resulting from processing sensor data jointly in a network-centric fashion. Several candidate technologies are introduced including the ability to fully process multi-sensor data given only partial overlap in sensor coverage and the ability to incorporate target identification information in stride. Finally the critical enabling capabilities are outlined including open architecture, open business, and a concept of operations. This ability to process multi-sensor data in a network-centric fashion is a core enabler of the Navy's vision and will become a necessity with the increasing number of manned and unmanned sensor systems and the requirement for their simultaneous use.

[1]  Vern Clark.  Sea Power 21: Projecting Decisive Joint Capabilities , 2002 .

[2]  Lawrence Carin,et al.  Multi-task learning for underwater object classification , 2007, SPIE Defense + Commercial Sensing.

[3]  Hui Li,et al.  Active learning for semi-supervised multi-task learning , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[4]  J. Schafer,et al.  Missing data: our view of the state of the art. , 2002, Psychological methods.

[5]  Jason R. Stack,et al.  In Situ Adaptive Feature Extraction for Underwater Target Classification , 2007, 36th Applied Imagery Pattern Recognition Workshop (aipr 2007).

[6]  Lawrence Carin,et al.  Logistic regression with an auxiliary data source , 2005, ICML.

[7]  David S Alberts,et al.  Network Centric Warfare: Developing and Leveraging Information Superiority , 1999 .

[8]  Mahmood R. Azimi-Sadjdadi,et al.  Target detection from dual disparate sonar platforms using canonical correlations , 2008, SPIE Defense + Commercial Sensing.

[9]  Lawrence Carin,et al.  On Classification with Incomplete Data , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  John P. Stenbit.  Department of Defense Net-Centric Data Strategy , 2003 .

[11]  G.J. Dobeck,et al.  Active learning for detection of mine-like objects in side-scan sonar imagery , 2005, IEEE Journal of Oceanic Engineering.

[12]  David A. Flanigan,et al.  Applying the Systems Engineering Method for the Joint Capabilities Integration and Development System (JCIDS) , 2005 .

[13]  Vernon Eugene Clark,et al.  FORCEnet: A Functional Concept for the 21st Century , 2005 .

[14]  Gerald J. Dobeck.  Algorithm fusion for automated sea mine detection and classification , 2001, MTS/IEEE Oceans 2001. An Ocean Odyssey. Conference Proceedings (IEEE Cat. No.01CH37295).

[15]  M.C. Lohrenz,et al.  The Automated Change Detection and Classification Real-time (ACDC-RT) System , 2007, OCEANS 2007 - Europe.