Open AccessFinal report for LDRD project 11-0029 : high-interest event detection in large-scale multi-modal data sets : proof of concept.
Author(s) -
Brandon R. Rohrer
Publication year - 2011
Language(s) - English
Resource type - Reports
DOI - 10.2172/1029755
Subject(s) - modal , anomaly detection , feature (linguistics) , computer science , event (particle physics) , focus (optics) , proof of concept , anomaly (physics) , scale (ratio) , data mining , artificial intelligence , geography , linguistics , chemistry , philosophy , physics , cartography , quantum mechanics , polymer chemistry , optics , condensed matter physics , operating system
Events of interest to data analysts are sometimes difficult to characterize in detail. Rather, they consist of anomalies, events that are unpredicted, unusual, or otherwise incongruent. The purpose of this LDRD was to test the hypothesis that a biologically-inspired anomaly detection algorithm could be used to detect contextual, multi-modal anomalies. There currently is no other solution to this problem, but the existence of a solution would have a great national security impact. The technical focus of this research was the application of a brain-emulating cognition and control architecture (BECCA) to the problem of anomaly detection. One aspect of BECCA in particular was discovered to be critical to improved anomaly detection capabilities: it's feature creator. During the course of this project the feature creator was developed and tested against multiple data types. Development direction was drawn from psychological and neurophysiological measurements. Major technical achievements include the creation of hierarchical feature sets created from both audio and imagery data