LSTM-DNN based approach for pain intensity and protective behaviour prediction

Yi Li; Shreya Ghosh; Jyoti Joshi; Sharon Oviatt

doi:10.1109/FG47880.2020.00061

LSTM-DNN based approach for pain intensity and protective behaviour prediction

Yi Li, Shreya Ghosh, Jyoti Joshi, Sharon Oviatt

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other

4 Citations (Scopus)

Abstract

This paper proposes an approach for pain intensity recognition and protective behaviour prediction task from body movements as a part of the EmoPain challenge. The given dataset consists of body part based sensor data for both the tasks. The proposed network is a lightweight LSTM-DNN model, which takes the angle, angle energy and sEMG features as input and predicts pain intensity level and protective behaviour as output. The performance of LSTM, Bi-LSTM, attention-LSTM and LSTM-DNN models are compared for this problem on the same dataset. In order to enhance the model's discriminating power, joint training of all the models are performed, combining respective task labels with exercise type as an additional label. The experiments show that the proposed approach is effective and outperforms the baseline on the validation set by a margin of 35.00% for pain intensity prediction and 47.72% for protective behaviour prediction, respectively.

Original language	English
Title of host publication	Proceedings of the 15th IEEE International Conference on Automatic Face and Gesture Recognition
Editors	Vitomir Struc, Francisco Gomez-Fernandez
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	819-823
Number of pages	5
ISBN (Electronic)	9781728130798
ISBN (Print)	9781728130804
DOIs	https://doi.org/10.1109/FG47880.2020.00061
Publication status	Published - Nov 2020
Event	IEEE International Conference on Automatic Face and Gesture Recognition 2020 - Buenos Aires, Argentina Duration: 16 Nov 2020 → 20 Nov 2020 Conference number: 15th https://ieeexplore-ieee-org.ezproxy.lib.monash.edu.au/xpl/conhome/9320148/proceeding (Proceedings) https://fg2020.org (Website)

Conference

Conference	IEEE International Conference on Automatic Face and Gesture Recognition 2020
Abbreviated title	FG 2020
Country/Territory	Argentina
City	Buenos Aires
Period	16/11/20 → 20/11/20
Internet address	https://ieeexplore-ieee-org.ezproxy.lib.monash.edu.au/xpl/conhome/9320148/proceeding (Proceedings) https://fg2020.org (Website)

Keywords

Chronic Pain
Emopain challenge
Neural Network
Protective Behavior

Access to Document

10.1109/FG47880.2020.00061

Cite this

Li, Y., Ghosh, S., Joshi, J., & Oviatt, S. (2020). LSTM-DNN based approach for pain intensity and protective behaviour prediction. In V. Struc, & F. Gomez-Fernandez (Eds.), Proceedings of the 15th IEEE International Conference on Automatic Face and Gesture Recognition (pp. 819-823). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/FG47880.2020.00061

Li, Yi ; Ghosh, Shreya ; Joshi, Jyoti et al. / LSTM-DNN based approach for pain intensity and protective behaviour prediction. Proceedings of the 15th IEEE International Conference on Automatic Face and Gesture Recognition. editor / Vitomir Struc ; Francisco Gomez-Fernandez. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2020. pp. 819-823

@inproceedings{39c1cb15b46f4f69b3d0a5139798805d,

title = "LSTM-DNN based approach for pain intensity and protective behaviour prediction",

abstract = "This paper proposes an approach for pain intensity recognition and protective behaviour prediction task from body movements as a part of the EmoPain challenge. The given dataset consists of body part based sensor data for both the tasks. The proposed network is a lightweight LSTM-DNN model, which takes the angle, angle energy and sEMG features as input and predicts pain intensity level and protective behaviour as output. The performance of LSTM, Bi-LSTM, attention-LSTM and LSTM-DNN models are compared for this problem on the same dataset. In order to enhance the model's discriminating power, joint training of all the models are performed, combining respective task labels with exercise type as an additional label. The experiments show that the proposed approach is effective and outperforms the baseline on the validation set by a margin of 35.00% for pain intensity prediction and 47.72% for protective behaviour prediction, respectively.",

keywords = "Chronic Pain, Emopain challenge, Neural Network, Protective Behavior",

author = "Yi Li and Shreya Ghosh and Jyoti Joshi and Sharon Oviatt",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; IEEE International Conference on Automatic Face and Gesture Recognition 2020, FG 2020 ; Conference date: 16-11-2020 Through 20-11-2020",

year = "2020",

month = nov,

doi = "10.1109/FG47880.2020.00061",

language = "English",

isbn = "9781728130804",

pages = "819--823",

editor = "Vitomir Struc and Francisco Gomez-Fernandez",

booktitle = "Proceedings of the 15th IEEE International Conference on Automatic Face and Gesture Recognition",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

url = "https://ieeexplore-ieee-org.ezproxy.lib.monash.edu.au/xpl/conhome/9320148/proceeding, https://fg2020.org",

}

Li, Y, Ghosh, S, Joshi, J & Oviatt, S 2020, LSTM-DNN based approach for pain intensity and protective behaviour prediction. in V Struc & F Gomez-Fernandez (eds), Proceedings of the 15th IEEE International Conference on Automatic Face and Gesture Recognition. IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 819-823, IEEE International Conference on Automatic Face and Gesture Recognition 2020, Buenos Aires, Argentina, 16/11/20. https://doi.org/10.1109/FG47880.2020.00061

LSTM-DNN based approach for pain intensity and protective behaviour prediction. / Li, Yi; Ghosh, Shreya; Joshi, Jyoti et al.
Proceedings of the 15th IEEE International Conference on Automatic Face and Gesture Recognition. ed. / Vitomir Struc; Francisco Gomez-Fernandez. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2020. p. 819-823.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other

TY - GEN

T1 - LSTM-DNN based approach for pain intensity and protective behaviour prediction

AU - Li, Yi

AU - Ghosh, Shreya

AU - Joshi, Jyoti

AU - Oviatt, Sharon

N1 - Conference code: 15th

PY - 2020/11

Y1 - 2020/11

N2 - This paper proposes an approach for pain intensity recognition and protective behaviour prediction task from body movements as a part of the EmoPain challenge. The given dataset consists of body part based sensor data for both the tasks. The proposed network is a lightweight LSTM-DNN model, which takes the angle, angle energy and sEMG features as input and predicts pain intensity level and protective behaviour as output. The performance of LSTM, Bi-LSTM, attention-LSTM and LSTM-DNN models are compared for this problem on the same dataset. In order to enhance the model's discriminating power, joint training of all the models are performed, combining respective task labels with exercise type as an additional label. The experiments show that the proposed approach is effective and outperforms the baseline on the validation set by a margin of 35.00% for pain intensity prediction and 47.72% for protective behaviour prediction, respectively.

AB - This paper proposes an approach for pain intensity recognition and protective behaviour prediction task from body movements as a part of the EmoPain challenge. The given dataset consists of body part based sensor data for both the tasks. The proposed network is a lightweight LSTM-DNN model, which takes the angle, angle energy and sEMG features as input and predicts pain intensity level and protective behaviour as output. The performance of LSTM, Bi-LSTM, attention-LSTM and LSTM-DNN models are compared for this problem on the same dataset. In order to enhance the model's discriminating power, joint training of all the models are performed, combining respective task labels with exercise type as an additional label. The experiments show that the proposed approach is effective and outperforms the baseline on the validation set by a margin of 35.00% for pain intensity prediction and 47.72% for protective behaviour prediction, respectively.

KW - Chronic Pain

KW - Emopain challenge

KW - Neural Network

KW - Protective Behavior

UR - http://www.scopus.com/inward/record.url?scp=85099021258&partnerID=8YFLogxK

U2 - 10.1109/FG47880.2020.00061

DO - 10.1109/FG47880.2020.00061

M3 - Conference Paper

AN - SCOPUS:85099021258

SN - 9781728130804

SP - 819

EP - 823

BT - Proceedings of the 15th IEEE International Conference on Automatic Face and Gesture Recognition

A2 - Struc, Vitomir

A2 - Gomez-Fernandez, Francisco

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - IEEE International Conference on Automatic Face and Gesture Recognition 2020

Y2 - 16 November 2020 through 20 November 2020

ER -

Li Y, Ghosh S, Joshi J, Oviatt S. LSTM-DNN based approach for pain intensity and protective behaviour prediction. In Struc V, Gomez-Fernandez F, editors, Proceedings of the 15th IEEE International Conference on Automatic Face and Gesture Recognition. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2020. p. 819-823 doi: 10.1109/FG47880.2020.00061

LSTM-DNN based approach for pain intensity and protective behaviour prediction

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this