Detection of mood disorder using modulation spectrum of facial action unit profiles

Tsung Hsien Yang, Chung Hsien Wu, Ming Hsiang Su, Chia Cheng Chang

研究成果: Conference contribution

摘要

In mood disorder diagnosis, bipolar disorder (BD) patients are often misdiagnosed as unipolar depression (UD) on initial presentation. It is crucial to establish an accurate distinction between BD and UD to make an accurate and early diagnosis, leading to improvements in treatment. In this work, facial expressions of the subjects are collected when they were watching the eliciting emotional video clips. In mood disorder detection, first, facial features extracted from the DISFA database are used to train a support vector machine (SVM) for generating facial action unit (AU) profiles. The modulation spectrum characterizing the fluctuation of AU profile sequence over a video segment are further extracted and then used for mood disorder detection using an ANN model. Comparative experiments clearly show the promising advantage of the modulation spectrum features for mood disorder detection.

原文English
主出版物標題2016 International Conference on Orange Technologies, ICOT 2016
發行者Institute of Electrical and Electronics Engineers Inc.
頁面5-8
頁數4
2018-January
ISBN(電子)9781538648315
DOIs
出版狀態Published - 2018 二月 1
事件2016 International Conference on Orange Technologies, ICOT 2016 - Melbourne, Australia
持續時間: 2016 十二月 182016 十二月 20

Other

Other2016 International Conference on Orange Technologies, ICOT 2016
國家Australia
城市Melbourne
期間16-12-1816-12-20

指紋

Mood Disorders
Bipolar Disorder
Modulation
Depressive Disorder
Support vector machines
Facial Expression
Diagnostic Errors
Surgical Instruments
Early Diagnosis
Experiments
Databases
Action Spectrum
Therapeutics

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Behavioral Neuroscience
  • Cognitive Neuroscience

引用此文

Yang, T. H., Wu, C. H., Su, M. H., & Chang, C. C. (2018). Detection of mood disorder using modulation spectrum of facial action unit profiles. 於 2016 International Conference on Orange Technologies, ICOT 2016 (卷 2018-January, 頁 5-8). [8278966] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICOT.2016.8278966
Yang, Tsung Hsien ; Wu, Chung Hsien ; Su, Ming Hsiang ; Chang, Chia Cheng. / Detection of mood disorder using modulation spectrum of facial action unit profiles. 2016 International Conference on Orange Technologies, ICOT 2016. 卷 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. 頁 5-8
@inproceedings{9e490adc97124236b1d574414b0dd715,
title = "Detection of mood disorder using modulation spectrum of facial action unit profiles",
abstract = "In mood disorder diagnosis, bipolar disorder (BD) patients are often misdiagnosed as unipolar depression (UD) on initial presentation. It is crucial to establish an accurate distinction between BD and UD to make an accurate and early diagnosis, leading to improvements in treatment. In this work, facial expressions of the subjects are collected when they were watching the eliciting emotional video clips. In mood disorder detection, first, facial features extracted from the DISFA database are used to train a support vector machine (SVM) for generating facial action unit (AU) profiles. The modulation spectrum characterizing the fluctuation of AU profile sequence over a video segment are further extracted and then used for mood disorder detection using an ANN model. Comparative experiments clearly show the promising advantage of the modulation spectrum features for mood disorder detection.",
author = "Yang, {Tsung Hsien} and Wu, {Chung Hsien} and Su, {Ming Hsiang} and Chang, {Chia Cheng}",
year = "2018",
month = "2",
day = "1",
doi = "10.1109/ICOT.2016.8278966",
language = "English",
volume = "2018-January",
pages = "5--8",
booktitle = "2016 International Conference on Orange Technologies, ICOT 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Yang, TH, Wu, CH, Su, MH & Chang, CC 2018, Detection of mood disorder using modulation spectrum of facial action unit profiles. 於 2016 International Conference on Orange Technologies, ICOT 2016. 卷 2018-January, 8278966, Institute of Electrical and Electronics Engineers Inc., 頁 5-8, 2016 International Conference on Orange Technologies, ICOT 2016, Melbourne, Australia, 16-12-18. https://doi.org/10.1109/ICOT.2016.8278966

Detection of mood disorder using modulation spectrum of facial action unit profiles. / Yang, Tsung Hsien; Wu, Chung Hsien; Su, Ming Hsiang; Chang, Chia Cheng.

2016 International Conference on Orange Technologies, ICOT 2016. 卷 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 5-8 8278966.

研究成果: Conference contribution

TY - GEN

T1 - Detection of mood disorder using modulation spectrum of facial action unit profiles

AU - Yang, Tsung Hsien

AU - Wu, Chung Hsien

AU - Su, Ming Hsiang

AU - Chang, Chia Cheng

PY - 2018/2/1

Y1 - 2018/2/1

N2 - In mood disorder diagnosis, bipolar disorder (BD) patients are often misdiagnosed as unipolar depression (UD) on initial presentation. It is crucial to establish an accurate distinction between BD and UD to make an accurate and early diagnosis, leading to improvements in treatment. In this work, facial expressions of the subjects are collected when they were watching the eliciting emotional video clips. In mood disorder detection, first, facial features extracted from the DISFA database are used to train a support vector machine (SVM) for generating facial action unit (AU) profiles. The modulation spectrum characterizing the fluctuation of AU profile sequence over a video segment are further extracted and then used for mood disorder detection using an ANN model. Comparative experiments clearly show the promising advantage of the modulation spectrum features for mood disorder detection.

AB - In mood disorder diagnosis, bipolar disorder (BD) patients are often misdiagnosed as unipolar depression (UD) on initial presentation. It is crucial to establish an accurate distinction between BD and UD to make an accurate and early diagnosis, leading to improvements in treatment. In this work, facial expressions of the subjects are collected when they were watching the eliciting emotional video clips. In mood disorder detection, first, facial features extracted from the DISFA database are used to train a support vector machine (SVM) for generating facial action unit (AU) profiles. The modulation spectrum characterizing the fluctuation of AU profile sequence over a video segment are further extracted and then used for mood disorder detection using an ANN model. Comparative experiments clearly show the promising advantage of the modulation spectrum features for mood disorder detection.

UR - http://www.scopus.com/inward/record.url?scp=85051012172&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051012172&partnerID=8YFLogxK

U2 - 10.1109/ICOT.2016.8278966

DO - 10.1109/ICOT.2016.8278966

M3 - Conference contribution

AN - SCOPUS:85051012172

VL - 2018-January

SP - 5

EP - 8

BT - 2016 International Conference on Orange Technologies, ICOT 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Yang TH, Wu CH, Su MH, Chang CC. Detection of mood disorder using modulation spectrum of facial action unit profiles. 於 2016 International Conference on Orange Technologies, ICOT 2016. 卷 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 5-8. 8278966 https://doi.org/10.1109/ICOT.2016.8278966