Design guidelines for a rule-based passive surveillance system
Jennings, Kirk Edward
Rowe, Neil C.
Dunlap, Calvin R.
MetadataShow full item record
This paper addresses the application of artificial intelligence to passive surveillance systems that use waveform analysis as their primary means of detecting, classifying and locating a specific target. Discussion is further limited to those passive surveillance systems which must deal with considerable noise in the data. Present methods, which use visual examination of the waveform data for the detection of target waveforms, is complicated, time consuming, and requires considerable expertise. The lack of prior knowledge of the nature of the noise, (e.g., frequency spectra, amplitude, or dynamics), means that the majority of signal analysis must be done by experts. This study discusses and recommends a rule-based system which uses the following artificial intelligence structures: the blackboard architecture, and the frames data structure. Sources of uncertainty are also discussed and methods of dealing with it are suggested. This study recommends that the symbolic representation language be carefully selected for conciseness, efficiency, and a vocabulary rich enough to express everything desired by the experts. A learning knowledge source is also recommended.
Approved for public release; distribution is unlimited