Applied Mathematics & Information Sciences

Author Country (or Countries)



The interest in the music classification has increased due to its wide applicability and discoveries obtained from researches. However, efficient methods for systemic organization of digital libraries are required, since users need to classify the available music files. When an automatic classification is desired, the extraction of input attributes and an efficient system, able to process them, are needed. In this context, the use of decision trees as a tool to predict musical genres classes allows the monitoring of the ramification, since nodes and branches of the tree can be accessed in this process. Decision tree is a technique very useful in data mining to extract information of a data set, normally using a TDIDT (Top-Down Induction Decision Tree) algorithm. Therefore, the goal of this paper is to propose an automatic classification method for Latin musical genres, by applying decision tree approach. The real database used is named Latin Music Database [20]. Two algorithms are executed: CART (Classification and Regression Tree) [2] and C4.5 [18], which have constructive criteria distinguished. The obtained results are compared and discussed in order to evaluate the classification performance.

Digital Object Identifier (DOI)