Performance of Diploid Dominance with Genetically Synthesized Signal Processing Networks

A methodology is described for synthesizing signal processing networks, which are used to solve a low-cost medical signal processing problem. The approach makes use of genetic algorithms and a new approach to diploid/dominance, which is tested using clinical patient data. Two complementary reasons for an observed diploid efficiency increase are proposed: 1) Improvements due to the retention of relatively low-fitness, recessive building blocks and 2) Improvements due to the increased proportion and fast evaluation of non-viable, recessive genotypes.

• Type: Conference
• Year: 1997
• Where: ICGA
• Authors: F. Greene
• Keywords: ICGA 1997, Optimization, Signal Processing, Signal Processing Networks, Signal Processing Problem