- Title
- Protein structure prediction with a new composite measure of diversity and memory-based diversification strategy
- Creator
- Nazmul, Rumana; Chetty, Madhu
- Date
- 2013
- Type
- Text; Conference paper
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/157266
- Identifier
- vital:11553
- Identifier
-
https://doi.org/10.1007/978-3-642-42042-9_80
- Identifier
- ISBN:978-3-642-42041-2
- Abstract
- Protein structure prediction (PSP) problem is a multimodal problem that can be tackled efficiently by evolutionary algorithms. However, evolutionary algorithms often fail to find the global optima due to genetic drift while solving the complex problems with a lot of peaks in the fitness landscape. Therefore, the need to efficiently measure as well as maintaining population diversity has significant effects in performance of evolutionary algorithms. In this paper, we introduce a composite measure of population diversity by hybridizing the phenotypic properties along with the distribution of individuals in a population over the fitness landscape. We further propose a memory-based diversification technique for the maintenance and promotion of diversity to prevent occurrence of stuck condition in multimodal problems such as PSP. Experiments conducted on protein structure prediction with HP benchmark sequences for 3D cubic lattice model illustrate that the proposed techniques are useful in improving the optimization process in terms of convergence as well as for achieving the optimal energy
- Publisher
- Springer
- Relation
- 20th International Conference, ICONIP 2013 Daegu, Korea, November 3-7 th 2013;In Neural Information Processing. ( Lecture Notes in Computer Science), vol 8227. pg 649-656
- Rights
- Copyright Springer
- Rights
- This metadata is freely available under a CCO license
- Subject
- Protein structure prediction; Diversity phenotype
- Reviewed
- Hits: 499
- Visitors: 489
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|