Partitioning around medoids (PAM) in clustering genre music

Dine Tiara Kusuma, Yessy Fitriani, M. Yoga Distra Sudirman

Abstract


Music consists of many genres, so it is difficult to make a standard protocol system to standardize or grouping a music genre if the assessment is only subjective. PAM (Partitioning Around Medoids) is a clustering technique used in troubleshooting Genre of music's clustering process in this research. The parameters used are Average Energy (AE), Tempo, and Music Bar which it is produce a "Muster" (Music Clustering).  “Muster” is a application that makes up 5 clusters with PAM. 5 clusters are Genre Music with medium Tempo, music with Slow and quiet tempo, music with a less calm feel, music that tends to be loud, strong and fast. Sample data used in this research were 50 data testing, namely from the types of music categories of classical music, jazz, blues, rock, and pop which produced an accuracy rate of 72.66%.

Keywords


Average energy (AE); Clustering; Music; Music bar; PAM (Partitioning around medoids); Tempo



DOI: http://doi.org/10.11591/ijeecs.v22.i3.pp%25p

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

shopify stats IJEECS visitor statistics