EEG Recognition with Adaptive Noise Reduction Based on Convolutional LSTM Network

Hengxing Lv; Xuemei Ren; Yongfeng Lv

doi:10.1007/978-981-15-0474-7_22

EEG Recognition with Adaptive Noise Reduction Based on Convolutional LSTM Network

Hengxing Lv, Xuemei Ren^*, Yongfeng Lv

^*Corresponding author for this work

School of Automation

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

In this paper, a new EMD adaptive decomposition algorithm is designed to denoise the original EEG signals, and a deep neural network model ConvLSTM is used to extract the features of the denoised signals. First, EEG signals are collected by a brain equipment. Then we use the proposed method to denoise the collected signals. Finally, the needed features are extracted with the convLSTM. Compared with previous methods, this proposed algorithm can extract the temporal and spatial characteristics of EEG more effectively. The proposed method is implemented on the actual moving EEG dataset, which verifies the validity and practicability of the proposed model.

Original language	English
Title of host publication	Proceedings of the 11th International Conference on Modelling, Identification and Control, ICMIC 2019
Editors	Rui Wang, Zengqiang Chen, Weicun Zhang, Quanmin Zhu
Publisher	Springer
Pages	227-237
Number of pages	11
ISBN (Print)	9789811504730
DOIs	https://doi.org/10.1007/978-981-15-0474-7_22
Publication status	Published - 2020
Event	11th International Conference on Modelling, Identification and Control, ICMIC 2019 - Tianjin, China Duration: 13 Jul 2019 → 15 Jul 2019

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	582
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	11th International Conference on Modelling, Identification and Control, ICMIC 2019
Country/Territory	China
City	Tianjin
Period	13/07/19 → 15/07/19

Keywords

ConvLSTM
Deep learning
Electroencephalogram
Empirical mode decomposition

Access to Document

10.1007/978-981-15-0474-7_22

Cite this

Lv, H., Ren, X., & Lv, Y. (2020). EEG Recognition with Adaptive Noise Reduction Based on Convolutional LSTM Network. In R. Wang, Z. Chen, W. Zhang, & Q. Zhu (Eds.), Proceedings of the 11th International Conference on Modelling, Identification and Control, ICMIC 2019 (pp. 227-237). (Lecture Notes in Electrical Engineering; Vol. 582). Springer. https://doi.org/10.1007/978-981-15-0474-7_22

@inproceedings{25a3af15297548c19f4820bc28126301,

title = "EEG Recognition with Adaptive Noise Reduction Based on Convolutional LSTM Network",

abstract = "In this paper, a new EMD adaptive decomposition algorithm is designed to denoise the original EEG signals, and a deep neural network model ConvLSTM is used to extract the features of the denoised signals. First, EEG signals are collected by a brain equipment. Then we use the proposed method to denoise the collected signals. Finally, the needed features are extracted with the convLSTM. Compared with previous methods, this proposed algorithm can extract the temporal and spatial characteristics of EEG more effectively. The proposed method is implemented on the actual moving EEG dataset, which verifies the validity and practicability of the proposed model.",

keywords = "ConvLSTM, Deep learning, Electroencephalogram, Empirical mode decomposition",

author = "Hengxing Lv and Xuemei Ren and Yongfeng Lv",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Singapore Pte Ltd.; 11th International Conference on Modelling, Identification and Control, ICMIC 2019 ; Conference date: 13-07-2019 Through 15-07-2019",

year = "2020",

doi = "10.1007/978-981-15-0474-7_22",

language = "English",

isbn = "9789811504730",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer",

pages = "227--237",

editor = "Rui Wang and Zengqiang Chen and Weicun Zhang and Quanmin Zhu",

booktitle = "Proceedings of the 11th International Conference on Modelling, Identification and Control, ICMIC 2019",

address = "Germany",

}

Lv, H, Ren, X & Lv, Y 2020, EEG Recognition with Adaptive Noise Reduction Based on Convolutional LSTM Network. in R Wang, Z Chen, W Zhang & Q Zhu (eds), Proceedings of the 11th International Conference on Modelling, Identification and Control, ICMIC 2019. Lecture Notes in Electrical Engineering, vol. 582, Springer, pp. 227-237, 11th International Conference on Modelling, Identification and Control, ICMIC 2019, Tianjin, China, 13/07/19. https://doi.org/10.1007/978-981-15-0474-7_22

EEG Recognition with Adaptive Noise Reduction Based on Convolutional LSTM Network. / Lv, Hengxing; Ren, Xuemei; Lv, Yongfeng.
Proceedings of the 11th International Conference on Modelling, Identification and Control, ICMIC 2019. ed. / Rui Wang; Zengqiang Chen; Weicun Zhang; Quanmin Zhu. Springer, 2020. p. 227-237 (Lecture Notes in Electrical Engineering; Vol. 582).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - EEG Recognition with Adaptive Noise Reduction Based on Convolutional LSTM Network

AU - Lv, Hengxing

AU - Ren, Xuemei

AU - Lv, Yongfeng

PY - 2020

Y1 - 2020

N2 - In this paper, a new EMD adaptive decomposition algorithm is designed to denoise the original EEG signals, and a deep neural network model ConvLSTM is used to extract the features of the denoised signals. First, EEG signals are collected by a brain equipment. Then we use the proposed method to denoise the collected signals. Finally, the needed features are extracted with the convLSTM. Compared with previous methods, this proposed algorithm can extract the temporal and spatial characteristics of EEG more effectively. The proposed method is implemented on the actual moving EEG dataset, which verifies the validity and practicability of the proposed model.

AB - In this paper, a new EMD adaptive decomposition algorithm is designed to denoise the original EEG signals, and a deep neural network model ConvLSTM is used to extract the features of the denoised signals. First, EEG signals are collected by a brain equipment. Then we use the proposed method to denoise the collected signals. Finally, the needed features are extracted with the convLSTM. Compared with previous methods, this proposed algorithm can extract the temporal and spatial characteristics of EEG more effectively. The proposed method is implemented on the actual moving EEG dataset, which verifies the validity and practicability of the proposed model.

KW - ConvLSTM

KW - Deep learning

KW - Electroencephalogram

KW - Empirical mode decomposition

UR - http://www.scopus.com/inward/record.url?scp=85076864072&partnerID=8YFLogxK

U2 - 10.1007/978-981-15-0474-7_22

DO - 10.1007/978-981-15-0474-7_22

M3 - Conference contribution

AN - SCOPUS:85076864072

SN - 9789811504730

T3 - Lecture Notes in Electrical Engineering

SP - 227

EP - 237

BT - Proceedings of the 11th International Conference on Modelling, Identification and Control, ICMIC 2019

A2 - Wang, Rui

A2 - Chen, Zengqiang

A2 - Zhang, Weicun

A2 - Zhu, Quanmin

PB - Springer

T2 - 11th International Conference on Modelling, Identification and Control, ICMIC 2019

Y2 - 13 July 2019 through 15 July 2019

ER -

EEG Recognition with Adaptive Noise Reduction Based on Convolutional LSTM Network

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this