Emo-LSTM: An Emotion Recognition Model of ECG Data Based on Long Short-Term Memory

Zhen Tian; Haoting Liu; De Mi; Dewei Yi; Qing Li

doi:10.1007/978-981-97-7139-4_77

Emo-LSTM: An Emotion Recognition Model of ECG Data Based on Long Short-Term Memory

Zhen Tian, Haoting Liu^*, De Mi, Dewei Yi, Qing Li

^*Corresponding author for this work

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

Abstract

In order to accurately monitor human emotions during work, we develop a deep learning model based on electrocardiogram (ECG) data. First, we set up an ECG data acquisition system and generate standard data set. Second, a model combining convolutional neural network (CNN), Long Short-Term Memory (LSTM) and attention mechanism is used for training and testing. Finally, the recognition results are evaluated using evaluation metrics such as Precision, Recall and F1 Score. Experimental results show that the Precision of the model to identify abnormal emotional states is 85.48%, the Recall is 92.16%, and the F1 score is 88.68%. The development of this technology provides a new tool for emotional monitoring in workplace, which promises to improve productivity and safety through timely interventions.

Original language	English
Title of host publication	Man-Machine-Environment System Engineering - Proceedings of the 24th Conference on MMESE
Editors	Shengzhao Long, Balbir S. Dhillon, Long Ye
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	555-561
Number of pages	7
ISBN (Electronic)	978-981-97-7139-4
ISBN (Print)	9789819771387
DOIs	https://doi.org/10.1007/978-981-97-7139-4_77
Publication status	Published - 29 Sept 2024
Event	24th Conference on Man-Machine-Environment System Engineering, MMESE 2024 - Beijing, China Duration: 18 Oct 2024 → 20 Oct 2024

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	1256 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	24th Conference on Man-Machine-Environment System Engineering, MMESE 2024
Country/Territory	China
City	Beijing
Period	18/10/24 → 20/10/24

Keywords

Attention mechanism
ECG signals
Emotion recognition
LSTM

Access to Document

10.1007/978-981-97-7139-4_77Licence: Unspecified

Cite this

Tian, Z., Liu, H., Mi, D., Yi, D., & Li, Q. (2024). Emo-LSTM: An Emotion Recognition Model of ECG Data Based on Long Short-Term Memory. In S. Long, B. S. Dhillon, & L. Ye (Eds.), Man-Machine-Environment System Engineering - Proceedings of the 24th Conference on MMESE (pp. 555-561). (Lecture Notes in Electrical Engineering; Vol. 1256 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-97-7139-4_77

Emo-LSTM: An Emotion Recognition Model of ECG Data Based on Long Short-Term Memory. / Tian, Zhen; Liu, Haoting; Mi, De et al.
Man-Machine-Environment System Engineering - Proceedings of the 24th Conference on MMESE. ed. / Shengzhao Long; Balbir S. Dhillon; Long Ye. Springer Science and Business Media Deutschland GmbH, 2024. p. 555-561 (Lecture Notes in Electrical Engineering; Vol. 1256 LNEE).

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

Tian, Z, Liu, H, Mi, D, Yi, D & Li, Q 2024, Emo-LSTM: An Emotion Recognition Model of ECG Data Based on Long Short-Term Memory. in S Long, BS Dhillon & L Ye (eds), Man-Machine-Environment System Engineering - Proceedings of the 24th Conference on MMESE. Lecture Notes in Electrical Engineering, vol. 1256 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 555-561, 24th Conference on Man-Machine-Environment System Engineering, MMESE 2024, Beijing, China, 18/10/24. https://doi.org/10.1007/978-981-97-7139-4_77

Tian Z, Liu H, Mi D, Yi D, Li Q. Emo-LSTM: An Emotion Recognition Model of ECG Data Based on Long Short-Term Memory. In Long S, Dhillon BS, Ye L, editors, Man-Machine-Environment System Engineering - Proceedings of the 24th Conference on MMESE. Springer Science and Business Media Deutschland GmbH. 2024. p. 555-561. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-97-7139-4_77

Tian, Zhen ; Liu, Haoting ; Mi, De et al. / Emo-LSTM : An Emotion Recognition Model of ECG Data Based on Long Short-Term Memory. Man-Machine-Environment System Engineering - Proceedings of the 24th Conference on MMESE. editor / Shengzhao Long ; Balbir S. Dhillon ; Long Ye. Springer Science and Business Media Deutschland GmbH, 2024. pp. 555-561 (Lecture Notes in Electrical Engineering).

@inproceedings{ba09a215bdd34dde8f648d895ed3d4bd,

title = "Emo-LSTM: An Emotion Recognition Model of ECG Data Based on Long Short-Term Memory",

abstract = "In order to accurately monitor human emotions during work, we develop a deep learning model based on electrocardiogram (ECG) data. First, we set up an ECG data acquisition system and generate standard data set. Second, a model combining convolutional neural network (CNN), Long Short-Term Memory (LSTM) and attention mechanism is used for training and testing. Finally, the recognition results are evaluated using evaluation metrics such as Precision, Recall and F1 Score. Experimental results show that the Precision of the model to identify abnormal emotional states is 85.48%, the Recall is 92.16%, and the F1 score is 88.68%. The development of this technology provides a new tool for emotional monitoring in workplace, which promises to improve productivity and safety through timely interventions.",

keywords = "Attention mechanism, ECG signals, Emotion recognition, LSTM",

author = "Zhen Tian and Haoting Liu and De Mi and Dewei Yi and Qing Li",

year = "2024",

month = sep,

day = "29",

doi = "10.1007/978-981-97-7139-4_77",

language = "English",

isbn = "9789819771387",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "555--561",

editor = "Shengzhao Long and Dhillon, {Balbir S.} and Long Ye",

booktitle = "Man-Machine-Environment System Engineering - Proceedings of the 24th Conference on MMESE",

address = "Germany",

note = "24th Conference on Man-Machine-Environment System Engineering, MMESE 2024 ; Conference date: 18-10-2024 Through 20-10-2024",

}

TY - GEN

T1 - Emo-LSTM

T2 - 24th Conference on Man-Machine-Environment System Engineering, MMESE 2024

AU - Tian, Zhen

AU - Liu, Haoting

AU - Mi, De

AU - Yi, Dewei

AU - Li, Qing

PY - 2024/9/29

Y1 - 2024/9/29

N2 - In order to accurately monitor human emotions during work, we develop a deep learning model based on electrocardiogram (ECG) data. First, we set up an ECG data acquisition system and generate standard data set. Second, a model combining convolutional neural network (CNN), Long Short-Term Memory (LSTM) and attention mechanism is used for training and testing. Finally, the recognition results are evaluated using evaluation metrics such as Precision, Recall and F1 Score. Experimental results show that the Precision of the model to identify abnormal emotional states is 85.48%, the Recall is 92.16%, and the F1 score is 88.68%. The development of this technology provides a new tool for emotional monitoring in workplace, which promises to improve productivity and safety through timely interventions.

AB - In order to accurately monitor human emotions during work, we develop a deep learning model based on electrocardiogram (ECG) data. First, we set up an ECG data acquisition system and generate standard data set. Second, a model combining convolutional neural network (CNN), Long Short-Term Memory (LSTM) and attention mechanism is used for training and testing. Finally, the recognition results are evaluated using evaluation metrics such as Precision, Recall and F1 Score. Experimental results show that the Precision of the model to identify abnormal emotional states is 85.48%, the Recall is 92.16%, and the F1 score is 88.68%. The development of this technology provides a new tool for emotional monitoring in workplace, which promises to improve productivity and safety through timely interventions.

KW - Attention mechanism

KW - ECG signals

KW - Emotion recognition

KW - LSTM

UR - http://www.scopus.com/inward/record.url?scp=85206193178&partnerID=8YFLogxK

U2 - 10.1007/978-981-97-7139-4_77

DO - 10.1007/978-981-97-7139-4_77

M3 - Published conference contribution

AN - SCOPUS:85206193178

SN - 9789819771387

T3 - Lecture Notes in Electrical Engineering

SP - 555

EP - 561

BT - Man-Machine-Environment System Engineering - Proceedings of the 24th Conference on MMESE

A2 - Long, Shengzhao

A2 - Dhillon, Balbir S.

A2 - Ye, Long

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 18 October 2024 through 20 October 2024

ER -

Emo-LSTM: An Emotion Recognition Model of ECG Data Based on Long Short-Term Memory

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this