A Coincidence Filtering-based Approach for CNNs in EEG-based Recognition

Zhongke Gao, Yanli Li, Yuxuan Yang, Na Dong*, Xiong Yang, Celso Grebogi

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

Electroencephalogram (EEG), obtained by wearable devices, can realize effective human health monitoring. Traditional methods based on artificially-designed features have achieved valid results in EEG-based recognition, and numerous
studies start to apply deep learning techniques in this area. In this paper, we propose a coincidence filtering-based method to build a connection between artificial features-based methods and convolutional neural networks (CNNs), and design CNNs through simulating the information extraction pattern of artificial
features-based methods. Based on this method, we propose a novel, simple, and effective CNNs structure for EEG-based classification. We implement two experiments to obtain EEG data, and perform experiments based on the two health monitoring tasks. The results illustrate that the proposed network can achieve a prominent average accuracy on the emotion recognition and fatigue driving detection task. Due to its generality, the proposed framework design of CNNs is expected to be useful for broader applications in health monitoring areas.
Original languageEnglish
Number of pages8
JournalIEEE Transactions on Industrial Informatics
Early online date25 Nov 2019
DOIs
Publication statusE-pub ahead of print - 25 Nov 2019

Fingerprint

Electroencephalography
Neural networks
Health
Monitoring
Experiments
Fatigue of materials

Keywords

  • convolutional neural networks
  • electroencephalography (EEG)
  • emotion recognition
  • fatigue driving detection

Cite this

A Coincidence Filtering-based Approach for CNNs in EEG-based Recognition. / Gao, Zhongke; Li, Yanli; Yang, Yuxuan; Dong, Na; Yang, Xiong; Grebogi, Celso.

In: IEEE Transactions on Industrial Informatics, 25.11.2019.

Research output: Contribution to journalArticle

@article{4806878bc15d45d4a3123216459f6d64,
title = "A Coincidence Filtering-based Approach for CNNs in EEG-based Recognition",
abstract = "Electroencephalogram (EEG), obtained by wearable devices, can realize effective human health monitoring. Traditional methods based on artificially-designed features have achieved valid results in EEG-based recognition, and numerousstudies start to apply deep learning techniques in this area. In this paper, we propose a coincidence filtering-based method to build a connection between artificial features-based methods and convolutional neural networks (CNNs), and design CNNs through simulating the information extraction pattern of artificialfeatures-based methods. Based on this method, we propose a novel, simple, and effective CNNs structure for EEG-based classification. We implement two experiments to obtain EEG data, and perform experiments based on the two health monitoring tasks. The results illustrate that the proposed network can achieve a prominent average accuracy on the emotion recognition and fatigue driving detection task. Due to its generality, the proposed framework design of CNNs is expected to be useful for broader applications in health monitoring areas.",
keywords = "convolutional neural networks, electroencephalography (EEG), emotion recognition, fatigue driving detection",
author = "Zhongke Gao and Yanli Li and Yuxuan Yang and Na Dong and Xiong Yang and Celso Grebogi",
note = "This work was supported by National Natural Science Foundation of China under Grant N os. 61873181, 61922062 and 61773282",
year = "2019",
month = "11",
day = "25",
doi = "10.1109/TII.2019.2955447",
language = "English",
journal = "IEEE Transactions on Industrial Informatics",
issn = "1551-3203",
publisher = "IEEE Press",

}

TY - JOUR

T1 - A Coincidence Filtering-based Approach for CNNs in EEG-based Recognition

AU - Gao, Zhongke

AU - Li, Yanli

AU - Yang, Yuxuan

AU - Dong, Na

AU - Yang, Xiong

AU - Grebogi, Celso

N1 - This work was supported by National Natural Science Foundation of China under Grant N os. 61873181, 61922062 and 61773282

PY - 2019/11/25

Y1 - 2019/11/25

N2 - Electroencephalogram (EEG), obtained by wearable devices, can realize effective human health monitoring. Traditional methods based on artificially-designed features have achieved valid results in EEG-based recognition, and numerousstudies start to apply deep learning techniques in this area. In this paper, we propose a coincidence filtering-based method to build a connection between artificial features-based methods and convolutional neural networks (CNNs), and design CNNs through simulating the information extraction pattern of artificialfeatures-based methods. Based on this method, we propose a novel, simple, and effective CNNs structure for EEG-based classification. We implement two experiments to obtain EEG data, and perform experiments based on the two health monitoring tasks. The results illustrate that the proposed network can achieve a prominent average accuracy on the emotion recognition and fatigue driving detection task. Due to its generality, the proposed framework design of CNNs is expected to be useful for broader applications in health monitoring areas.

AB - Electroencephalogram (EEG), obtained by wearable devices, can realize effective human health monitoring. Traditional methods based on artificially-designed features have achieved valid results in EEG-based recognition, and numerousstudies start to apply deep learning techniques in this area. In this paper, we propose a coincidence filtering-based method to build a connection between artificial features-based methods and convolutional neural networks (CNNs), and design CNNs through simulating the information extraction pattern of artificialfeatures-based methods. Based on this method, we propose a novel, simple, and effective CNNs structure for EEG-based classification. We implement two experiments to obtain EEG data, and perform experiments based on the two health monitoring tasks. The results illustrate that the proposed network can achieve a prominent average accuracy on the emotion recognition and fatigue driving detection task. Due to its generality, the proposed framework design of CNNs is expected to be useful for broader applications in health monitoring areas.

KW - convolutional neural networks

KW - electroencephalography (EEG)

KW - emotion recognition

KW - fatigue driving detection

U2 - 10.1109/TII.2019.2955447

DO - 10.1109/TII.2019.2955447

M3 - Article

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

SN - 1551-3203

ER -