Multiclass reduced-set support vector machines
ICML '06 Proceedings of the 23rd international conference on Machine learning
Using SPSS for Windows: Data Analysis and Graphics
Using SPSS for Windows: Data Analysis and Graphics
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
Which is the best multiclass SVM method? an empirical study
MCS'05 Proceedings of the 6th international conference on Multiple Classifier Systems
Hi-index | 0.00 |
The Chinese zither, called guqin, has existed for over 3,000 years and always played an important role in Chinese social history. An interesting but unfortunate fact is that the traditional notation of guqin music does not provide the duration information for each music note which requires the player to learn from his teacher and memorize. As a result, among several thousands of compositions that have been created and recorded with guqin music notation, only around 100 of them are still being played today. In this article we use a machine learning method to study the guqin music recovery problem which tries to use the guqin music notation to recover the duration of each music note. Information provided by the music note is used as features to predict the duration information with a support vector machine. The experimental result shows that our system can predict with fair accuracy, and can be used as a valuable reference for human guqin masters to recover guqin music.