A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors
One of the main objectives of Active and Assisted Living (AAL) environments is to ensure that elderly and/or disabled people perform/live well in their immediate environments; this can be monitored by among others the recognition of emotions based on non-highly intrusive sensors such as Electroderma...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/7/1659 |
id |
doaj-e431ad9b586944e6bbe710cc68bda919 |
---|---|
record_format |
Article |
spelling |
doaj-e431ad9b586944e6bbe710cc68bda9192020-11-25T01:06:04ZengMDPI AGSensors1424-82202019-04-01197165910.3390/s19071659s19071659A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity SensorsFadi Al Machot0Ali Elmachot1Mouhannad Ali2Elyan Al Machot3Kyandoghere Kyamakya4Research Center Borstel—Leibniz Lung Center, 23845 Borstel, GermanyFaculty of Mechanical and Electrical Engineering, University of Damascus, Damascus, SyriaInstitute for Smart Systems Technologies, Alpen-Adira University, 9020 Klagenfurt, AustriaCarl Gustav Carus Faculty of Medicine, Dresden University of Technology, 01069 Dresden, GermanyInstitute for Smart Systems Technologies, Alpen-Adira University, 9020 Klagenfurt, AustriaOne of the main objectives of Active and Assisted Living (AAL) environments is to ensure that elderly and/or disabled people perform/live well in their immediate environments; this can be monitored by among others the recognition of emotions based on non-highly intrusive sensors such as Electrodermal Activity (EDA) sensors. However, designing a learning system or building a machine-learning model to recognize human emotions while training the system on a specific group of persons and testing the system on a totally a new group of persons is still a serious challenge in the field, as it is possible that the second testing group of persons may have different emotion patterns. Accordingly, the purpose of this paper is to contribute to the field of human emotion recognition by proposing a Convolutional Neural Network (CNN) architecture which ensures promising robustness-related results for both subject-dependent and subject-independent human emotion recognition. The CNN model has been trained using a grid search technique which is a model hyperparameter optimization technique to fine-tune the parameters of the proposed CNN architecture. The overall concept’s performance is validated and stress-tested by using MAHNOB and DEAP datasets. The results demonstrate a promising robustness improvement regarding various evaluation metrics. We could increase the accuracy for subject-independent classification to 78% and 82% for MAHNOB and DEAP respectively and to 81% and 85% subject-dependent classification for MAHNOB and DEAP respectively (4 classes/labels). The work shows clearly that while using solely the non-intrusive EDA sensors a robust classification of human emotion is possible even without involving additional/other physiological signals.https://www.mdpi.com/1424-8220/19/7/1659subject-dependent emotion recognitionsubject-independent emotion recognitionelectrodermal activity (EDA)deep learningconvolutional neural networks |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Fadi Al Machot Ali Elmachot Mouhannad Ali Elyan Al Machot Kyandoghere Kyamakya |
spellingShingle |
Fadi Al Machot Ali Elmachot Mouhannad Ali Elyan Al Machot Kyandoghere Kyamakya A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors Sensors subject-dependent emotion recognition subject-independent emotion recognition electrodermal activity (EDA) deep learning convolutional neural networks |
author_facet |
Fadi Al Machot Ali Elmachot Mouhannad Ali Elyan Al Machot Kyandoghere Kyamakya |
author_sort |
Fadi Al Machot |
title |
A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors |
title_short |
A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors |
title_full |
A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors |
title_fullStr |
A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors |
title_full_unstemmed |
A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors |
title_sort |
deep-learning model for subject-independent human emotion recognition using electrodermal activity sensors |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2019-04-01 |
description |
One of the main objectives of Active and Assisted Living (AAL) environments is to ensure that elderly and/or disabled people perform/live well in their immediate environments; this can be monitored by among others the recognition of emotions based on non-highly intrusive sensors such as Electrodermal Activity (EDA) sensors. However, designing a learning system or building a machine-learning model to recognize human emotions while training the system on a specific group of persons and testing the system on a totally a new group of persons is still a serious challenge in the field, as it is possible that the second testing group of persons may have different emotion patterns. Accordingly, the purpose of this paper is to contribute to the field of human emotion recognition by proposing a Convolutional Neural Network (CNN) architecture which ensures promising robustness-related results for both subject-dependent and subject-independent human emotion recognition. The CNN model has been trained using a grid search technique which is a model hyperparameter optimization technique to fine-tune the parameters of the proposed CNN architecture. The overall concept’s performance is validated and stress-tested by using MAHNOB and DEAP datasets. The results demonstrate a promising robustness improvement regarding various evaluation metrics. We could increase the accuracy for subject-independent classification to 78% and 82% for MAHNOB and DEAP respectively and to 81% and 85% subject-dependent classification for MAHNOB and DEAP respectively (4 classes/labels). The work shows clearly that while using solely the non-intrusive EDA sensors a robust classification of human emotion is possible even without involving additional/other physiological signals. |
topic |
subject-dependent emotion recognition subject-independent emotion recognition electrodermal activity (EDA) deep learning convolutional neural networks |
url |
https://www.mdpi.com/1424-8220/19/7/1659 |
work_keys_str_mv |
AT fadialmachot adeeplearningmodelforsubjectindependenthumanemotionrecognitionusingelectrodermalactivitysensors AT alielmachot adeeplearningmodelforsubjectindependenthumanemotionrecognitionusingelectrodermalactivitysensors AT mouhannadali adeeplearningmodelforsubjectindependenthumanemotionrecognitionusingelectrodermalactivitysensors AT elyanalmachot adeeplearningmodelforsubjectindependenthumanemotionrecognitionusingelectrodermalactivitysensors AT kyandogherekyamakya adeeplearningmodelforsubjectindependenthumanemotionrecognitionusingelectrodermalactivitysensors AT fadialmachot deeplearningmodelforsubjectindependenthumanemotionrecognitionusingelectrodermalactivitysensors AT alielmachot deeplearningmodelforsubjectindependenthumanemotionrecognitionusingelectrodermalactivitysensors AT mouhannadali deeplearningmodelforsubjectindependenthumanemotionrecognitionusingelectrodermalactivitysensors AT elyanalmachot deeplearningmodelforsubjectindependenthumanemotionrecognitionusingelectrodermalactivitysensors AT kyandogherekyamakya deeplearningmodelforsubjectindependenthumanemotionrecognitionusingelectrodermalactivitysensors |
_version_ |
1725191682876506112 |