Chromosome Classification Using Continuous Hidden Markov Models

Up-to-date results on the application of Markov models to chromosome analysis are presented. On the one hand, this means using continuous Hidden Markov Models (HMMs) instead of discrete models. On the other hand, this also means to conduct empirical tests on the same large chromosome datasets that are currently used to evaluate state-ofthe-art classifiers. It is shown that the use of continuous HMMs allows to obtain error rates that are very close to those provided by the most accurate classifiers.

• Type: Conference
• Year: 2003
• Where: IBPRIA
• Authors: César Martínez, Héctor García, Alfons Juan, Francisco Casacuberta
• Keywords: Continuous Hidden Markov, IBPRIA 2003, Image Analysis, Large Chromosome Datasets, Markov Models