ABSTRACT
Expert System ............................................................................................ 13
2.2.1. Introduction ..................................................................................... 13
2.2.2. Classification of the Test Cells ....................................................... 14
2.2.2.1. Mapping of the Space........................................................ 14
2.2.2.2. Indexing of the Cells ......................................................... 15
2.2.3. Target Detection .............................................................................. 16
2.3. Signal Understanding and Detection Using a Feedback
Expert System ............................................................................................ 20
2.3.1. Introduction ..................................................................................... 20
2.3.2. IPUS Architecture ........................................................................... 20
2.3.2.1. Introduction........................................................................ 20
2.3.2.3. Diagnosis and Reprocessing.............................................. 25
2.3.2.4. Interpretation Process ........................................................ 26
2.3.2.5. SOU and Resolving Control Structure.............................. 26
2.3.3. Application of IPUS to Radar Signal Understanding..................... 29
2.4. Proposed Radar Signal Processing System Using a Feedback
Expert System............................................................................................ 29
2.4.1. Data Collection and Preprocessing ................................................. 29
2.4.2. Mapping........................................................................................... 32
2.5. Mapping Procedure.................................................................................... 36
2.5.1. Introduction ..................................................................................... 36
2.5.2. Observations on BN and CL Cells.................................................. 37
2.5.2.1. Observations on BN Cells ................................................. 37
2.5.2.2. Observations on CL Cells ................................................. 38
2.5.3. Mapping Procedure ......................................................................... 39
2.5.3.1. Separation of CL Patches from
Background Noise ............................................................. 39
2.5.3.2. Detection of CL Patch Edges and Edge
Enhancement...................................................................... 44
2.5.3.3. Conclusion ......................................................................... 46
2.5.4. Examples of the Mapping Procedure.............................................. 47
2.5.4.1. Introduction........................................................................ 47
2.5.4.2. Examples............................................................................ 49
2.5.5. Convergence of the Mapping Procedure ........................................ 70
2.5.5.1. Introduction........................................................................ 70
2.5.5.2. Separation between BN and CL Patches .......................... 73
2.5.6. Extension of the Mapping Procedure to
Range-Azimuth-Doppler Cells ..................................................... 79
2.5.7. Conclusion ....................................................................................... 81
2.6. Indexing Procedure .................................................................................... 82
2.6.1. Introduction ..................................................................................... 82
2.6.2. Assessment Stage ............................................................................ 83
2.6.2.1. Identification of the BN and CL Patches .......................... 83
2.6.2.2. Computation of CL-to-Noise Ratios ................................. 85
2.6.2.3. Classification of CL Patches ............................................. 85
2.6.3. CL Subpatch Investigation Stage.................................................... 86
2.6.4. PDF Approximation of WSC CL Patches ...................................... 87
2.6.4.1. Test Cell Selection............................................................. 88
2.6.4.2. PDF Approximation........................................................... 89
2.6.4.3. PDF Approximation Metric............................................... 91
2.6.4.4. Outliers............................................................................... 93
2.6.4.5. PDF Approximation Strategy ............................................ 96
2.6.5. Examples ......................................................................................... 97
2.6.5.1. Example 1 .......................................................................... 97
2.6.6. Extension of the Indexing Procedure
to Range-Azimuth-Doppler Cells............................................... 111
2.6.7. Conclusion ..................................................................................... 113
2.7. Application of IPUS to the Radar Detection Problem............................ 114
2.7.1. Summary of IPUS Concepts ......................................................... 114
2.7.2. Role of IPUS in the Mapping Procedure...................................... 115
2.7.2.1. IPUS Stages Included in the Mapping Procedure........... 115
2.7.2.2. Observations on the Setting of NCC............................... 117
2.7.3. Examples of Mapping ................................................................... 125
2.7.3.1. Example 1 ........................................................................ 125
2.7.3.2. Example 2 ........................................................................ 125
2.7.3.3. Example 3 ........................................................................ 125
2.7.4. Role of IPUS in the Indexing Procedure ...................................... 126
2.7.4.1. IPUS Stages Included in the Assessment Stage ............. 127
2.7.4.2. IPUS Stages Included in the CL Subpatch
Investigation Stage .......................................................... 127
2.7.4.3. Examples.......................................................................... 131
2.7.4.4. IPUS Stages Included in the PDF
Approximation Stage ....................................................... 133
2.7.5. Examples of Indexing.................................................................... 147
2.7.5.1. Example 1 ........................................................................ 148
2.7.5.2. Example 2 ........................................................................ 152
2.7.5.3. Example 3 ........................................................................ 163
2.7.6. Conclusion ..................................................................................... 170
2.8. Conclusion and Future Research............................................................. 172
2.8.1. Conclusion ..................................................................................... 172
2.8.2. Future Research ............................................................................. 173
In signal processing applications it is common to assume a Gaussian process in
the design of optimal signal processors. However, non-Gaussian processes do
arise in many situations. For example, measurements reveal that radar clutter
may be approximated by either Weibull, K-distributed, Lognormal, or Gaussian
distributions depending upon the scenario.
