AFRL releases BAA for Multi-Source Information Extraction & Network Analysis program
August 18, 2015
AFRL 112On August 18, the Air Force Research Laboratory (AFRL 112On - Rome, NY, USA) posted a broad agency announcement (BAA) for Multi-Source Information Extraction & Network Analysis (MUSIENA) (Solicitation Number: BAA-AFRL-RIK-2015-0019).
To maximize the possibility of award, AFRL recommends that white papers for FY16 funding be received by September 18, 2015.
A WHITE PAPER gives the AGENCIES free information, brain power, from potential contractors, or research scientists who want to achieve GRANT AWARDS. FREE information to the AGENCIES also comes from solicitations to HIGH SCHOOL and COLLEGE KIDS in guise of "science fairs" or "project challenges" (driverless vehicles was one of the award programs).
What that means, is that the AFRL group wants tools that can take a good look at SOCIAL MEDIA, and sort through it for anything interesting, data-mine it, find out who is talking to whom, and what subjects are of interest to the "public" or special interest groups. WHENCE the subjects of interest are determined, then various groups can be targeted to find out "more".The Air Force Research Laboratory is soliciting white papers for various research and development analytics, analytical tools, algorithm developments, projects, and experiments focused on developing Multi-Source Information Extraction and Network Analysis (MUSIENA) capabilities that will provide the Air Force the means to better conduct analytical operations in support of their Intelligence, Surveillance, and Reconnaissance mission.
This announcement is comprised of two projects, (1) Global Threat Discovery and Identification (GTD-ID) and (2) Emerging Threat Analytics (ETA) where each has research areas that taken together comprise the focus of MUSIENA research and development. (DTRA for instance is a specialty group in the Department of Defence who is very interested in mitigating any upcoming threats from any sources, from NBC (nuclear biological and chemical), and 'otherwise').
BACKGROUND:
Past research in text analysis has led to the automated capabilities that are now in use to extract relevant information from large volumes of textual data. (i.e. PRISM)
The development of this technology has reduced textual data overload, increased the accuracy of analysis, and decreased the cycle time and manpower requirements needed to assess threats and vulnerabilities.
However, this is a situation that has not remained static from either the perspective of the anticipated number of data sources or projected analytical needs.
Further development is required to not just keep pace but to move beyond current performance levels, to overcome limitations in moving to new data types and domains, and to achieve new, more sophisticated capabilities.
NEW DATA TYPES - multiple forms of encryption - layered encryption and dynamic encryption. Embedding images within MP3 audio files, where the images are encrypted with multi-layered passphrases.
Fundamentally the analysis of textual content must produce higher levels of comprehension and understanding than presently exists.
COMPREHENSION and SIGNIFICANCE - keywords example: doctor, bug, car, nuclear - "the doctor was driving a car which had bugs in it, and he went nuclear when it broke down on the side of the road" - was that a message about a biological attack or did something bother the doctor about his lemon of a car? Keyword analysis is overwhelmed with the old techniques.
As textual information has increased in both quantity and complexity the demands for greater analytical capabilities have also grown dramatically. While basic documents still comprise a large portion of textual information, valuable content can now be extracted from a range of other sources including a variety of social media material (chat, email, blogs, etc), many open source materials and the metadata descriptors that relate back to additional media forms (video, imagery, speech, etc).
The value of (con)textual analysis going forward will now be gauged by the ability to work effectively in and across these and other components of a complex data environment while advancing the capabilities in exploiting traditional sources.
Current network discovery and analysis science has focused on static relationship or event based networks of interest.
This occurs primarily on one or two particular data sources.
These capabilities are adept at enabling an analyst to effectively analyze network data within a single data source, but the analyst is then left to make mental correlations of observations and conclusions drawn from one data source to other data sources. Furthermore, current input methods do not account for semantic equivalences during the ingestion of the data, making the analyst’s job even more difficult.
(In computer metadata, semantic equivalence is a declaration that two data elements from different vocabularies contain data that has similar meaning. )
One of the greatest technical challenges facing all decision support systems is the heterogeneous aspect of the data that is collected by millions of sensors and the different stovepipe architectures used to store this data.
(Stovepipes are systems procured and developed to solve a specific problem, characterized by a limited focus and functionality, and containing data that cannot be easily shared with other systems.)
With the idea of CLOUD COMPUTING data needs to be shared between analytics systems and not be throttled - in other words a gargantuan intelligence analysis system needs to get data easily, have ways to sort through it to determine "significant content" and then distribute the analysis to the appropriate followup agency for action.
IN THE MINIMUM, in order to perform useful analytics, a composite picture of thehave to be pieced together from the original disparate data sources. That shows the "network".
- key entities,
- events, and
- locations
The ingesting and integrating of information from disparate data sources remains a difficult and unresolved problem. (PRISM, CARNIVORE fail in these situations).
OBJECTIVES:
THEREFORE - The Information Directorate, Activity Based Analysis Branch, is soliciting white papers under this announcement for unique and innovative technologies to explore and develop Multi-Source Information Extraction and Network Analysis (MUSIENA) capabilities.
The two projects under this MUSIENA program are:
(1) Global Threat Discovery and Identification (GTD-ID) and
(2) Emerging Threat Analytics (ETA) with each containing the key focus areas for development.
REF: http://www.afrl.af.mil/
Bookmarks