<![CDATA[Music consists of various genres and emotions, therefore it is important to group the music according to what the listener wants both based on the genre and the emotions they feel. As an example of an online music application that can automatically group music that makes it easy for listeners to play the desired music, music grouping is seen based on the similarity of certain characteristics. Another example is the Radio music player, where a common problem with radio broadcasters is to play and choose what songs to play. With the grouping of music automatically this will certainly be very helpful and more efficient for playing these songs automatically. Then this research will cluster songs based on the emotions of Broken Heart and Happy with feature extraction using the Haar Wavelet transformation method, then clustering using K-Means. The results of clustering will be evaluated using purity. The test is based on the song structure, a combination of statistical features, and the Haar Wavelet coefficient. Based on the results of all tests carried out obtained clustering with the highest purity value of 0.62.]]>
Copyrights © 2019
