News

Spectral-based Features Ranking for Gamelan Instruments Identification using Filter Techniques

Thu, 25 Oct 2018
8:41 am
Research Database

Sorry, no posts matched your criteria.

Share :
Oleh : Admin-Komputer   |

Kategori  

Penelitian

Judul Spectral-based Features Ranking for Gamelan Instruments Identification using Filter Techniques
Peneliti
  1. Prof Dr. Ir. Yoyon Kusnendar Suprapto, M.Sc.
  2. Dr. Diah Puspito Wulandari, S.T.,M.Sc.
  3. Aris Tjahyanto

In this paper, we describe an approach of spectral-based features ranking for Javanese gamelan instruments identification using filter techniques. The model extracted spectral-based features set of the signal using Short Time Fourier Transform (STFT). The rank of the features was determined using the five algorithms; namely ReliefF, Chi-Squared, Information Gain, Gain Ratio, and Symmetric Uncertainty. Then, we tested the ranked features by cross validation using Support Vector Machine (SVM). The experiment showed that Gain Ratio algorithm gave the best result, it yielded accuracy of 98.93%.

Latest News

Sorry, no posts matched your criteria.