EconPapers    
Economics at your fingertips  
 

Research on Automatic Classification Method of Ethnic Music Emotion Based on Machine Learning

Zijin Wu and Naeem Jan

Journal of Mathematics, 2021, vol. 2021, 1-11

Abstract: With the development of the country’s economy, there is a flourishing situation in the field of culture and art. However, the diversification of artistic expressions has not brought development to folk music. On the contrary, it brought a huge impact, and some national music even fell into the dilemma of being lost. This article is mainly aimed at the recognition and classification of folk music emotions and finds the model that can make the classification accuracy rate as high as possible. The classification model used in this article is mainly after determining the use of Support Vector Machine (SVM) classification method, a variety of attempts have been made to feature extraction, and good results have been achieved. Explore the Deep Belief Network (DBN) pretraining and reverse fine-tuning process, using DBN to learn the fusion characteristics of music. According to the abstract characteristics learned by them, the recognition and classification of folk music emotions are carried out. The DBN is improved by adding “Dropout†to each Restricted Boltzmann Machine (RBM) and adjusting the increase standard of weight and bias. The improved network can avoid the overfitting problem and speed up the training of the network. Through experiments, it is found that using the fusion features proposed in this paper, through classification, the classification accuracy has been improved.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
http://downloads.hindawi.com/journals/jmath/2021/7554404.pdf (application/pdf)
http://downloads.hindawi.com/journals/jmath/2021/7554404.xml (application/xml)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hin:jjmath:7554404

DOI: 10.1155/2021/7554404

Access Statistics for this article

More articles in Journal of Mathematics from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem ().

 
Page updated 2025-03-19
Handle: RePEc:hin:jjmath:7554404