STUDY OF NEURAL NETWORKS FOR CLUSTERING RADAR SIGNALS

PDF

Authors
  1. Savaria, Y.
  2. Blaquiere, Y.
  3. Granger, E.
  4. Cantin, M-A.
Corporate Authors
Ecole Polytechnique, Montreal QUE (CAN) Centre de Developpement Technologique;Defence Research Establishment Ottawa, Ottawa ONT (CAN)
Abstract
Self-organizing neural networks (SONN) are analyzed and compared for automatic deinterleaving of radar pulse streams in electronic support measures (ESM) applications. Theory behind existing SONNs is reviewed, and improvements are proposed for ESM use. Efficient and practical architectures for implementing these SONNs are proposed. This includes the design, simulation, fabriction and testing of proof-of-concept software, reconfigurable hardware, and an application specific integrated circuit (ASIC).
Keywords
Clustering;Self organizing;Unsupervised;Adaptive resonance theory;Reconfigurable hardware;Application Specific Integrated Circuits;ASIC;Deinterleaving
Report Number
C.D.T.-P19601;DREO-CR-98-610 — Contractor Report (Final)
Date of publication
01 Mar 1998
Number of Pages
187
DSTKIM No
98-01925
CANDIS No
508384
Format(s):
Hardcopy;Document Image stored on Optical Disk

Permanent link

Document 1 of 1

Date modified: