TY - JOUR
T1 - Spectral-based features ranking for gamelan instruments identification using filter techniques
AU - Tjahyanto, Aris
AU - Suprapto, Yoyon K.
AU - Wulandari, Diah P.
PY - 2013/3
Y1 - 2013/3
N2 - 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%.
AB - 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%.
KW - Automatic transcription
KW - Features extraction
KW - Gain ratio
KW - Support vector machine
UR - http://www.scopus.com/inward/record.url?scp=84888868728&partnerID=8YFLogxK
U2 - 10.12928/telkomnika.v11i1.895
DO - 10.12928/telkomnika.v11i1.895
M3 - Article
AN - SCOPUS:84888868728
SN - 1693-6930
VL - 11
SP - 95
EP - 106
JO - Telkomnika (Telecommunication Computing Electronics and Control)
JF - Telkomnika (Telecommunication Computing Electronics and Control)
IS - 1
ER -