{"298491":{"#nid":"298491","#data":{"type":"news","title":"MINT Program Helps Pinpoint Threats Contained in Intelligence Data","body":[{"value":"\u003Cp\u003EEvery day, U.S. military and security units receive vast amounts of data collected by intelligence, surveillance and reconnaissance (ISR) sensors. Human analysts constantly review this data, searching for possible threats.\u003C\/p\u003E\u003Cp\u003ETo aid this effort, researchers from the \u003Ca href=\u0022http:\/\/www.gtri.gatech.edu\/\u0022\u003EGeorgia Tech Research Institute\u003C\/a\u003E (GTRI) are helping to improve the capabilities of the nation\u2019s Multi-Disciplinary Intelligence (Multi-INT) system, which monitors incoming data.\u003C\/p\u003E\u003Cp\u003EA key to improving the U.S. Multi-INT system involves bringing \u0022actionable intelligence\u0022 \u2013 information that could require immediate response \u2013 to the attention of human analysts as quickly as possible, explained Chris Kennedy, a research program analyst who leads the MINT effort in GTRI. But finding actionable intelligence is a challenge; it must be identified from myriad raw data gathered by intelligence sources, which include optical and radar sensors, communications sensors, measurements and signatures intelligence (MASINT) and others.\u003C\/p\u003E\u003Cp\u003E\u0022The number of analysts is limited, and they can only perform a certain number of actions,\u0022 said Kennedy. \u0022So out of a huge set of information \u2013 which could involve millions of data points \u2013 you need to find the most valuable pieces to prioritize for investigation and possible action.\u0022\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAccelerating the System\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EGTRI\u0027s work addresses two related Multi-INT challenges:\u003C\/p\u003E\u003Cul\u003E\u003Cli\u003ENetwork bandwidth and workstation processing power sometimes can\u0027t keep up with incoming data sets that contain terabytes or even petabytes of raw information.\u003C\/li\u003E\u003Cli\u003EHuman analysts need to stay on top of incoming data by concentrating on the most significant information.\u003C\/li\u003E\u003C\/ul\u003E\u003Cp\u003EMetadata are small amounts of information that contain the key elements of a data point, which is an individual piece of data. For example, in the case of a car moving down a road, its metadata might consist of the make\/model\/color, location, speed and number of passengers. Those attributes are highly informative, yet much easier to transmit and process than, say, a video of the car, which would involve large amounts of data.\u003C\/p\u003E\u003Cp\u003EThe GTRI approach creates metadata fields, or utilizes existing ones, thereby characterizing each data point with minimal overhead. Then only the metadata is transmitted to the main system for immediate processing; the rest of the raw data is retained in an archive in case it\u0027s needed later.\u003C\/p\u003E\u003Cp\u003EThe metadata technique results in much smaller amounts of information being relayed from ISR sources to computers. That reduces processing loads, helping computers and networks keep up with incoming data. The raw data is also stored and can be examined if necessary.\u003C\/p\u003E\u003Cp\u003E\u0022Obviously under this data-reduction approach there are information losses that could affect how our program makes decisions, which is why our system is only a tool for \u2013 and not a replacement for \u2013 the human analyst,\u0022 Kennedy said.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EInforming the Analyst\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EThe second challenge \u2013 supporting human analysts \u2013 is addressed by methods that improve the system\u0027s ability to identify, compare and prioritize different types of information.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EFirst, the gathered metadata is converted into a single uniform format. By creating one format for all incoming metadata, data points from many different sources can be more readily identified and manipulated. This uniform format is independent of the data source, so different types of ISR data can be processed together.\u003C\/p\u003E\u003Cp\u003EThen, utilizing the identity-bearing metadata tags, GTRI researchers use complex machine-learning algorithms to find and compare related pieces of information. Powerful concurrent-computing techniques allow problems to be divided up and computed on multiple processors. That helps the system perform the complex task of determining which data points have been previously associated with other data points.\u003C\/p\u003E\u003Cp\u003EMetadata approaches have been used in the past, Kennedy explained, but only for a single intelligence technology \u2013 such as a text-recognition program that identifies keywords in voice-to-text data. The GTRI approach differs because it integrates metadata from a variety of intelligence disciplines into a single technology that prioritizes corroborative relationships from multiple sources.\u003C\/p\u003E\u003Cp\u003EUnder GTRI\u0027s integrated approach, one set of potentially significant signals could be quickly compared to others in the same vicinity to form an in-depth picture. For example, in a disaster relief scenario, one aircraft-mounted ISR sensor might detect information indicating abandoned vehicles. But if another sensor detected a functioning communications device in one of the vehicles, that would indicate a higher likelihood of finding a survivor, prompting a rescue reconnaissance.\u003C\/p\u003E\u003Cp\u003EThe relationship found between the communications device\u2019s signal information and the vehicle\u2019s imagery information would be prioritized against other found relationships and displayed to the analyst on mapping software, such as GTRI\u2019s FalconView program.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EOngoing Improvement\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003ERecently, the MINT team began working with a GTRI group that\u2019s involved in the ongoing development of Stinger, a Georgia Tech-produced graph-analysis software. Stinger\u2019s capabilities could aid MINT in recording and analyzing information about long-term patterns of observed relationships \u2013 that, for instance, a type of vehicle and a specific communications device are frequently observed together by independent sensors.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThis information would then be sent to an analyst through a web-based portal, giving the analyst access to alerts regarding specific kinds of relationships identified by MINT.\u003C\/p\u003E\u003Cp\u003EThe MINT team is presently focused on improving the program\u2019s capacity to process many data points quickly. They\u0027re using three primary sets of testing data involving thousands or millions of data points over lengthy time spans. The researchers\u0027 goal is to achieve real-time or near-real-time processing capability, so analysts can be alerted to abnormal information almost instantly.\u003C\/p\u003E\u003Cp\u003E\u0022We want to get to the point where, as the latest data is coming in, it\u0027s being correlated against the data we already have,\u0022 Kennedy said. \u0022We need to able to say to the analyst, \u0027OK you\u2019ve got a million data points, but look at these 10 first.\u0027 \u0022\u003Cbr \/\u003E\u003Cbr \/\u003E\u003Cstrong\u003EResearch News\u003C\/strong\u003E\u003Cbr \/\u003E\u003Cstrong\u003EGeorgia Institute of Technology\u003C\/strong\u003E\u003Cbr \/\u003E\u003Cstrong\u003E177 North Avenue\u003C\/strong\u003E\u003Cbr \/\u003E\u003Cstrong\u003EAtlanta, Georgia 30332-0181\u003C\/strong\u003E\u003Cbr \/\u003E\u003Cbr \/\u003E\u003Cstrong\u003EMedia Relations Contacts\u003C\/strong\u003E: Lance Wallace (404-407-7280) (\u003Ca href=\u0022mailto:lance.wallace@gtri.gatech.edu\u0022\u003Elance.wallace@gtri.gatech.edu\u003C\/a\u003E) or John Toon (404-894-6986) (\u003Ca href=\u0022mailto:jtoon@gatech.edu\u0022\u003Ejtoon@gatech.edu\u003C\/a\u003E).\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EWriter\u003C\/strong\u003E: Rick Robinson\u003Cbr \/\u003E\u003Cbr \/\u003E\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EEvery day U.S. military and security units receive vast amounts of data collected by intelligence, surveillance and reconnaissance (ISR) sensors. Researchers from the Georgia Tech Research Institute (GTRI) are helping to improve the capabilities of the nation\u2019s Multi-Disciplinary Intelligence (Multi-INT) system, which monitors this incoming data. \u003Cbr \/\u003E\u003Cbr \/\u003E\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Researchers are helping improve the capabilities of the nation\u2019s Multi-Disciplinary Intelligence (Multi-INT) system."}],"uid":"27303","created_gmt":"2014-05-20 20:25:21","changed_gmt":"2016-10-08 03:16:26","author":"John Toon","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2014-05-21T00:00:00-04:00","iso_date":"2014-05-21T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"298471":{"id":"298471","type":"image","title":"MINT Program","body":null,"created":"1449244552","gmt_created":"2015-12-04 15:55:52","changed":"1475895000","gmt_changed":"2016-10-08 02:50:00","alt":"MINT Program","file":{"fid":"199471","name":"mint1.jpg","image_path":"\/sites\/default\/files\/images\/mint1_0.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/images\/mint1_0.jpg","mime":"image\/jpeg","size":1623069,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/mint1_0.jpg?itok=78-_IntS"}},"298481":{"id":"298481","type":"image","title":"MINT Program4","body":null,"created":"1449244552","gmt_created":"2015-12-04 15:55:52","changed":"1475895000","gmt_changed":"2016-10-08 02:50:00","alt":"MINT Program4","file":{"fid":"199472","name":"mint4.jpg","image_path":"\/sites\/default\/files\/images\/mint4_0.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/images\/mint4_0.jpg","mime":"image\/jpeg","size":1530297,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/mint4_0.jpg?itok=dMG9jz8c"}}},"media_ids":["298471","298481"],"groups":[{"id":"1188","name":"Research Horizons"}],"categories":[{"id":"147","name":"Military Technology"},{"id":"135","name":"Research"}],"keywords":[{"id":"416","name":"GTRI"},{"id":"856","name":"Intelligence"},{"id":"525","name":"military"},{"id":"93551","name":"MINT"},{"id":"93561","name":"Multi-INT"},{"id":"93571","name":"reconaissance"},{"id":"167055","name":"security"},{"id":"167617","name":"surveillance"}],"core_research_areas":[{"id":"39431","name":"Data Engineering and Science"},{"id":"39481","name":"National Security"}],"news_room_topics":[{"id":"71881","name":"Science and Technology"}],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EJohn Toon\u003C\/p\u003E\u003Cp\u003EResearch News\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022mailto:jtoon@gatech.edu\u0022\u003Ejtoon@gatech.edu\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E(404) 894-6986\u003C\/p\u003E","format":"limited_html"}],"email":["jtoon@gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}