Melody Difficulty Classification using Frequent Pattern and Inter-Notes Distance Analysis

Abstract

This research proposes a novel method for melody difficulty classification performed using frequent pattern and inter-notes distance analysis. The Apriori algorithm was used to measure the frequency of the notes in the note sequence, in which the melody length is also included in the calculation. In addition, the inter-notes distance analysis was also used to measure the difficulty level of composition based on the distance between successive notes. The classification was performed for traditional Javanese compositions known as Gamelan music. Symbolic representation, in which the Gamelan compositions music sheets were collected as the dataset, was chosen by asking experts to divide the compositions based on their difficulty level into basic, intermediate and advanced classes. Then, the proposed method was implemented to measure the difficulty value of each composition. The difference in the interpretation of the difficulty level between the experts and the difficulty value of the composition is solved by calculating the mean value to obtain the range of difficulty values in each class. Evaluation was performed using confusion matrix to measure the accuracy, precision and recall value, and the results reaching 82%, 82.1% and 82%, respectively