Graph Embedded Multiple Kernel Extreme Learning Machine for Music Emotion Classification

Music emotion classification is one of the most importance parts of music information retrieval (MIR) because of its potential commercial value and cultural value. However, music emotion classification is still a tough challenge, due to the low representation of music features. In this paper, a novel Extreme Learning Machine (ELM), combining graph regularization term and multiple kernel, is proposed to enhance the accuracy of music emotion classification. We use nonnegative matrix factorization (NMF) to find the optimal weights of combining multiple kernels. Furthermore, the graph regularization term is added to increase the relevance between predictions from the same class. The proposed Graph embedded Multiple Kernel Extreme Learning Machine (GMK-ELM) is tested on three music emotion datasets. Experiment results show that the proposed GMK-ELM outperforms several well-known ELM methods.

[1]  Ye Zhang,et al.  Multiple Kernel Learning via Low-Rank Nonnegative Matrix Factorization for Classification of Hyperspectral Imagery , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[2]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[3]  Alexandros Iosifidis,et al.  Graph Embedded Extreme Learning Machine , 2016, IEEE Transactions on Cybernetics.

[4]  Yu Zhang,et al.  Multi-kernel extreme learning machine for EEG classification in brain-computer interfaces , 2018, Expert Syst. Appl..

[5]  Wei Feng,et al.  Class imbalance ensemble learning based on the margin theory , 2018 .

[6]  Kun-Ming Yu,et al.  Automatic Music Genre Classification Based on Modulation Spectral Analysis of Spectral and Cepstral Features , 2009, IEEE Transactions on Multimedia.

[7]  Zhijing Yang,et al.  Extreme Sparse Multinomial Logistic Regression: A Fast and Robust Framework for Hyperspectral Image Classification , 2017, Remote. Sens..

[8]  Les E. Atlas,et al.  Modulation-scale analysis for content identification , 2004, IEEE Transactions on Signal Processing.

[9]  Xianzhong Long,et al.  Discriminative graph regularized extreme learning machine and its application to face recognition , 2015, Neurocomputing.

[10]  Jyh-Shing Roger Jang,et al.  Automatic Music Mood Classification Based on Timbre and Modulation Features , 2015, IEEE Transactions on Affective Computing.

[11]  Yading Song,et al.  Evaluation of Musical Features for Emotion Classification , 2012, ISMIR.

[12]  Seiji Inokuchi,et al.  Sentiment extraction in music , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[13]  Jon Atli Benediktsson,et al.  Classification of Hyperspectral Images by Exploiting Spectral–Spatial Information of Superpixel via Multiple Kernels , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Danilo Comminiello,et al.  Music classification using extreme learning machines , 2013, 2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA).

[15]  Jocelyn Chanussot,et al.  Multiple Kernel Learning for Hyperspectral Image Classification: A Review , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Zhijing Yang,et al.  Spectral and Spatial Kernel Extreme Learning Machine for Hyperspectral Image Classification , 2018, BICS.

[17]  Yueting Zhuang,et al.  Popular music retrieval by detecting mood , 2003, SIGIR.

[18]  T. Eerola,et al.  A comparison of the discrete and dimensional models of emotion in music , 2011 .

[19]  Aleix M. Martínez,et al.  Subclass discriminant analysis , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Zhijing Yang,et al.  Sparse Representation-Based Augmented Multinomial Logistic Extreme Learning Machine With Weighted Composite Features for Spectral–Spatial Classification of Hyperspectral Images , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[21]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[22]  Gokhan Bilgin,et al.  MCK-ELM: multiple composite kernel extreme learning machine for hyperspectral images , 2019, Neural Computing and Applications.