Classifiers for sonar target differentiation
In this paper, the processing of sonar signals has been carried out using Minimal Resource Allocation Network (MRAN), Probabilistic Neural Network (PNN) and Fuzzy Artmap (FAM) in differentiation of commonly encountered features in indoor environments. The stability-plasticity behaviors of all three...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://shdl.mmu.edu.my/2499/ |
| Summary: | In this paper, the processing of sonar signals has been carried out using Minimal Resource Allocation Network (MRAN), Probabilistic Neural Network (PNN) and Fuzzy Artmap (FAM) in differentiation of commonly encountered features in indoor environments. The stability-plasticity behaviors of all three networks have been investigated. The experimental result shows that MRAN possesses lower network complexity but experiences higher plasticity in comparison to PNN and FAM. The study also shows that MRAN performance is superior in terms of on-line learning than PNN and FAM. |
|---|