Web music emotion recognition based on higher effective gene expression programming

Authors:
Kejun Zhang;Shouqian Sun
Affiliations:
College of Computer Science, Zhejiang University, Hangzhou 310027, China;College of Computer Science, Zhejiang University, Hangzhou 310027, China
Venue:
Neurocomputing
Year:
2013

Citing 9
Cited 0

Support-Vector Networks

Machine Learning
An introduction to genetic algorithms

An introduction to genetic algorithms
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
Study on Music Emotion Cognition Model Based on Applying the Improved Gene Expression Programming

DMAMH '07 Proceedings of the Second Workshop on Digital Media and its Application in Museum & Heritage
Emotion-based music retrieval on a well-reduced audio feature space

ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Backward-chaining evolutionary algorithms

Artificial Intelligence
A Multimedia Retrieval Framework Based on Semi-Supervised Ranking and Relevance Feedback

IEEE Transactions on Pattern Analysis and Machine Intelligence
Harmonizing Hierarchical Manifolds for Multimedia Document Semantics Understanding and Cross-Media Retrieval

IEEE Transactions on Multimedia
An extended one-versus-rest support vector machine for multi-label classification

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

In the study, we present a higher effective algorithm, called revised gene expression programming (RGEP), to construct the model for music emotion recognition. Our main contributions are as follows: firstly, we describe the basic mechanisms of music emotion recognition and introduce gene expression programming (GEP) to deal with the model construction for music emotion recognition. Secondly, we present RGEP based on backward-chaining evolutionary algorithm and use GEP, RGEP, and SVM to construct the models for music emotion recognition separately, the results show that the models obtained by SVM, GEP, and RGEP are satisfactory and well confirm the experimental values. Finally, we report the comparison of these models, and we find that the model obtained by RGEP outperforms classification accuracy of the model by GEP and takes almost 15% less processing time of GEP and even half processing time of SVM, which offers a new efficient way for solving music emotion recognition problems; moreover, because processing time is essential for the problem of large scale music information retrieval, therefore, RGEP might prompt the development of the music information retrieval technology.