Different regimes for classification of DNA sequences

In this paper we have shown how a Multi-Layered Perceptron (MLP) neural network and a Support Vector Machine (SVM) are used to classify between eukaryotic and prokaryotic cells. The classification is based on their DNA-sequences that is obtained from different databases available on Internet. The sequences are first pre-processed using a sliding window technique to obtain their sub-sequence frequencies, and then normalised to make them comparable. A Particle Swarm Optimization (PSO) technique is finally used to optimize the parameters occurring in both the MLP and SVM regimes which gives good performance.