Year
1999
Abstract
The use of unattended monitoring systems for monitoring the status of high value assets and processes has proven to be less costly and less intrusive than the on-site inspections which they are intended to replace. However, these systems present a classic information overload problem to anyone trying to analyze the resulting sensor data. These data are typically so voluminous and contain information at such a low level that the significance of any single reading (e.g., a door open event) is not obvious. Sophisticated, automated techniques are needed to extract expected patterns in the data and isolate and characterize the remaining patterns that are due to undeclared activities. This paper describes a data analysis engine that runs a state machine model of each facility and its sensor suite. It analyzes the raw sensor data, converting and combining the inputs from many sensors into operator domain level information. It compares the resulting activities against a set of activities declared by an inspector or operator, and then presents the differences in a form comprehensible to an inspector. Although the current analysis engine was written with international nuclear material safeguards, nonproliferation, and transparency in mind, since there is no information about any particular facility in the software, there is no reason why it cannot be applied anywhere it is important to verify proccesses are occurring as expected, to detect intrusion into a secured area, or to detect the diversion of valuable assets.