| EPSRC Reference: |
GR/J48597/01 |
| Title: |
EVOLUTIONARY ALGORITHMS IN NON-LINEAR SIGNAL PROCESSING PROBLEMS |
| Principal Investigator: |
Flockton, Dr S |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Physics |
| Organisation: |
Royal Holloway, Univ of London |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
25 February 1994 |
Ends: |
24 August 1997 |
Value (£): |
117,279
|
| EPSRC Research Topic Classifications: |
| Digital Signal Processing |
|
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
The aim of the project is to investigate and develop evolutionary algorithms for solving non-linear signal processing problems. The tasks of the project include a) characterising the performance of existing evolutionary algorithms for solving non-linear signal processing problems, and b) developing evolutionary algorithms in the signal processing context in order to provide better theoretical understanding and achieve better algorithmic performance.Progress:The behaviour of evolutionary algorithms in solving the problem of estimating parameters of superimposed signals from noisy measurements has been studied. The estimation of the direction of arrival (DOA) of narrow-band signal sources impinging on a multi-sensor array was considered. Conventional evolutionary programming in which mutation and selection operators are used to seek the optimal solution has been implemented and evaluated. It has been shown that the evolutionary algorithm outperforms the gradient-based methods currently used in signal processing field. The ability of the evolutionary algorithm to find the global optimum in a multimodal error surface has been investigated and a characterisation of premature convergence has been made. A new evolutionary algorithm has been proposed which utilises the niche concept. This is a mechanism to group the individuals in the population in terms of their proximities in solution space. The niche is used to maintain a population capable of exploring the search space while preserving the diversity to prevent the premature convergence. The former is achieved by a niche-based adaptive mutation scheme while the latter by a niche-based local selection scheme. Preliminary simulation results show that the proposed method has better performance than the conventional method in terms of the success of achieving the desired global optimal solution. Ongoing work concerned with the proposed method focuses on the following components:a) to pursue further performance analysis for the justification and the comparison with other methods;b) to develop the methodology for specifying the niche size by using prior knowledge of the problem at hand rather than on heuristic manner; and c) to investigate the general applicability of the proposed method to other non-linear signal processing problems.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
|