CONTEXT AWARE INFORMATION DELIVERY FOR MOBILE DEVICES JINHONG K. GUO * , STEPHEN A. KNOTT † , RAY YUAN SHEU ‡ and MARTIN O. HOFMANN § Lockheed Martin Advanced Technology Laborataries 3 Executive Campus, Suite 600, Cherry Hill New Jersey, 08002, USA * kguo@atl.lmco.com † sknott@atl.lmco.com ‡ rsheu@mitre.org § mhofmann@atl.lmco.com Received 6 May 2011 Accepted 23 July 2012 Published 9 January 2013 Delivering the right amount of information to the right person is vital on the tactical battle¯eld. With the increasing use of mobile devices by the military, delivering relevant information instantaneously to the war¯ghter becomes possible. However, large quantities of data are being generated constantly while the human processing power and communication channels are limited. Therefore, data must be processed so it can be evaluated against operational needs. This data is collected in multiple modalities include images, videos and ¯eld reports with multi- sensor data. Providing automated processing of unstructured information promises to e®ec- tively connect information processing with operational decision making, dramatically reducing the time needed to identify relevant information for mission planning and execution. We describe a multi-view learning technique that augments the feature set used by a classi¯er in one modality with entity relationships discovered in other modalities. To accommodate the limited computation power of ¯eld devices, mostly handhelds, the multi-view learning algorithm is low complexity. It applies to multiple modalities, leveraging many-to-many correspondences among di®erent modalities. Experiments on image and text are presented in the paper which show more than 20% improvement over categorizing text or images independently. The categorized information is matched to the mission and task needs. Finally, relevant information needs to be transmitted via limited bandwidth negotiated from limited resources. Keywords : Multi-model information processing; multi-view learning; categorization; informa- tion management; resource management. ‡ Current a±liation: The MITRE Corporation, Defense Enterprise Computing Operations, 300 Sentinel Drive, Suite 600, Annapolis Junction, MD 20701, USA. International Journal of Pattern Recognition and Arti¯cial Intelligence Vol. 26, No. 8 (2012) 1260012 (15 pages) # . c World Scienti¯c Publishing Company DOI: 10.1142/S0218001412600129 1260012-1 Int. J. Patt. Recogn. Artif. Intell. 2012.26. Downloaded from www.worldscientific.com by 192.35.35.35 on 03/01/13. For personal use only.