A study on influence of normalization methods on music genre classification results employing kNN algorithm
Aldona Rosner, Marcin Michalak, Bożena Kostek · 2013
This paper presents a comparison of different normalization methods applied to the set of feature vectors of music pieces. Test results show the influence of min-max and Zero-Mean normalization methods, employing different distance functions (Euclidean, Manhattan, Chebyshev, Minkowski) as a pre-processing for genre classification, on k-Nearest Neighbor (kNN) algorithm classification results.