The joint publication of the Faculty of Computational Statistics and Chair of the Algorithm Engineering (TU Dortmund) [1] was recently presented as poster at the PPSN conference in Krakow. Evolutionary strategy driven by asymmetric mutation and several hybridization methods were developed and compared for the feature selection task for selected music classification problems.
[1] B. Bischl, I. Vatolkin and M. Preuss: Selecting Small Audio Feature Sets in Music Classification by Means of Asymmetric Mutation. In: Proceedings of the 11th International Conference on Parallel Problem Solving From Nature (PPSN), Krakow
2010