CERTAIN: Certainty Enrichment via Relational and Temporal Analytical Indexing of Networks

Award Information
Agency:
Department of Defense
Branch
Defense Advanced Research Projects Agency
Amount:
$1,499,989.00
Award Year:
2015
Program:
SBIR
Phase:
Phase II
Contract:
W911NF-14-C-0023
Agency Tracking Number:
D2-1257
Solicitation Year:
2012
Solicitation Topic Code:
SB123-002
Solicitation Number:
2012.3
Small Business Information
Aptima, Inc.
12 Gill Street, Woburn, MA, 01801
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
N
Duns:
967259946
Principal Investigator:
Georgiy Levchuk
Principal Engineer
(781) 935-3966
georgiy@aptima.com
Business Contact:
Thomas McK McKenna
Mr.
(781) 935-3966
mckenna@aptima.com
Research Institution:
n/a
Abstract
Efficient and accurate indexing is fundamental to the Big Data enterprise, but traditional indexing techniques are often foiled by noise and missing information. Aptima proposes Phase II of CERTAIN (Certainty Enrichment via Relational and Temporal Analytical Indexing of Networks), an approach that advances several areas of large dataset indexing and applies them to the domains of cyber and financial analysis. We will extend, implement and integrate the indexing approach prototyped in Phase I that retrieves data that traditional indexers miss. Our enriched indexing approach relies on inference algorithms that extract high level features in temporal and relational datasets. Phase I focused on detecting patterns of temporal behavior by learning categories of records that share qualitatively similar characteristics. Phase II builds upon and enhances that work to now focus on the relational domain, where we will detect subnetwork primitives that highlight regions of a dataset that share similar properties. We will demonstrate how inference-enriched indexing supports query by example and improves the retrieval of relevant data by intelligently managing noisy datasets. Our research and development effort will focus on both cyber and financial datasets, but our approach will extend to other data sources that have temporal or relational components.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government