Graph embedded multiple kernel extreme learning machine for music emotion classification

Xixian Zhang; Zhijing Yang; Jinchang Ren; Meilin Wang; Wing-Kuen Ling

doi:10.1007/978-3-030-39431-8_17

Graph embedded multiple kernel extreme learning machine for music emotion classification

Xixian Zhang, Zhijing Yang, Jinchang Ren, Meilin Wang, Wing-Kuen Ling

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

Abstract

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.

Original language	English
Title of host publication	Advances in Brain Inspired Cognitive Systems
Subtitle of host publication	10th International Conference, BICS 2019, Guangzhou, China, July 13–14, 2019, Proceedings
Editors	Jinchang Ren, Amir Hussain, Huimin Zhao, Kaizhu Huang, Jiangbin Zheng, Jun Cai, Rongjun Chen, Yinyin Xiao
Place of Publication	Cham, Switzerland
Publisher	Springer
Pages	180-191
Number of pages	12
ISBN (Electronic)	9783030394318
ISBN (Print)	9783030394301
DOIs	https://doi.org/10.1007/978-3-030-39431-8_17
Publication status	Published - 1 Feb 2020
Event	10th International Conference on Brain Inspired Cognitive Systems, BICS 2019 - Guangzhou, China Duration: 13 Jul 2019 → 14 Jul 2019

Conference

Conference	10th International Conference on Brain Inspired Cognitive Systems, BICS 2019
Country/Territory	China
City	Guangzhou
Period	13/07/19 → 14/07/19

Keywords

music emotion classification
extreme learning machine (ELM)
graph embedded
multiple kernel learning

Access to Document

10.1007/978-3-030-39431-8_17

Cite this

Zhang, X., Yang, Z., Ren, J., Wang, M., & Ling, W-K. (2020). Graph embedded multiple kernel extreme learning machine for music emotion classification. In J. Ren, A. Hussain, H. Zhao, K. Huang, J. Zheng, J. Cai, R. Chen, & Y. Xiao (Eds.), Advances in Brain Inspired Cognitive Systems: 10th International Conference, BICS 2019, Guangzhou, China, July 13–14, 2019, Proceedings (pp. 180-191). Springer. https://doi.org/10.1007/978-3-030-39431-8_17

Zhang, Xixian ; Yang, Zhijing ; Ren, Jinchang ; Wang, Meilin ; Ling, Wing-Kuen. / Graph embedded multiple kernel extreme learning machine for music emotion classification. Advances in Brain Inspired Cognitive Systems: 10th International Conference, BICS 2019, Guangzhou, China, July 13–14, 2019, Proceedings. editor / Jinchang Ren ; Amir Hussain ; Huimin Zhao ; Kaizhu Huang ; Jiangbin Zheng ; Jun Cai ; Rongjun Chen ; Yinyin Xiao. Cham, Switzerland : Springer, 2020. pp. 180-191

@inproceedings{209538a82d8f4a7097ab49c85e4f968b,

title = "Graph embedded multiple kernel extreme learning machine for music emotion classification",

abstract = "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.",

keywords = "music emotion classification, extreme learning machine (ELM), graph embedded, multiple kernel learning",

author = "Xixian Zhang and Zhijing Yang and Jinchang Ren and Meilin Wang and Wing-Kuen Ling",

year = "2020",

month = feb,

day = "1",

doi = "10.1007/978-3-030-39431-8_17",

language = "English",

isbn = "9783030394301",

pages = "180--191",

editor = "Jinchang Ren and Amir Hussain and Huimin Zhao and Kaizhu Huang and Jiangbin Zheng and Jun Cai and Rongjun Chen and Yinyin Xiao",

booktitle = "Advances in Brain Inspired Cognitive Systems",

publisher = "Springer",

note = "10th International Conference on Brain Inspired Cognitive Systems, BICS 2019 ; Conference date: 13-07-2019 Through 14-07-2019",

}

Zhang, X, Yang, Z, Ren, J, Wang, M & Ling, W-K 2020, Graph embedded multiple kernel extreme learning machine for music emotion classification. in J Ren, A Hussain, H Zhao, K Huang, J Zheng, J Cai, R Chen & Y Xiao (eds), Advances in Brain Inspired Cognitive Systems: 10th International Conference, BICS 2019, Guangzhou, China, July 13–14, 2019, Proceedings. Springer, Cham, Switzerland, pp. 180-191, 10th International Conference on Brain Inspired Cognitive Systems, BICS 2019, Guangzhou, China, 13/07/19. https://doi.org/10.1007/978-3-030-39431-8_17

Graph embedded multiple kernel extreme learning machine for music emotion classification. / Zhang, Xixian; Yang, Zhijing; Ren, Jinchang; Wang, Meilin; Ling, Wing-Kuen.

Advances in Brain Inspired Cognitive Systems: 10th International Conference, BICS 2019, Guangzhou, China, July 13–14, 2019, Proceedings. ed. / Jinchang Ren; Amir Hussain; Huimin Zhao; Kaizhu Huang; Jiangbin Zheng; Jun Cai; Rongjun Chen; Yinyin Xiao. Cham, Switzerland : Springer, 2020. p. 180-191.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

TY - GEN

T1 - Graph embedded multiple kernel extreme learning machine for music emotion classification

AU - Zhang, Xixian

AU - Yang, Zhijing

AU - Ren, Jinchang

AU - Wang, Meilin

AU - Ling, Wing-Kuen

PY - 2020/2/1

Y1 - 2020/2/1

N2 - 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.

AB - 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.

KW - music emotion classification

KW - extreme learning machine (ELM)

KW - graph embedded

KW - multiple kernel learning

U2 - 10.1007/978-3-030-39431-8_17

DO - 10.1007/978-3-030-39431-8_17

M3 - Conference contribution book

SN - 9783030394301

SP - 180

EP - 191

BT - Advances in Brain Inspired Cognitive Systems

A2 - Ren, Jinchang

A2 - Hussain, Amir

A2 - Zhao, Huimin

A2 - Huang, Kaizhu

A2 - Zheng, Jiangbin

A2 - Cai, Jun

A2 - Chen, Rongjun

A2 - Xiao, Yinyin

PB - Springer

CY - Cham, Switzerland

T2 - 10th International Conference on Brain Inspired Cognitive Systems, BICS 2019

Y2 - 13 July 2019 through 14 July 2019

ER -

Zhang X, Yang Z, Ren J, Wang M, Ling W-K. Graph embedded multiple kernel extreme learning machine for music emotion classification. In Ren J, Hussain A, Zhao H, Huang K, Zheng J, Cai J, Chen R, Xiao Y, editors, Advances in Brain Inspired Cognitive Systems: 10th International Conference, BICS 2019, Guangzhou, China, July 13–14, 2019, Proceedings. Cham, Switzerland: Springer. 2020. p. 180-191 https://doi.org/10.1007/978-3-030-39431-8_17