Combining Facial Expressions and Electroencephalography to Enhance Emotion Recognition
Emotion recognition plays an essential role in human−computer interaction. Previous studies have investigated the use of facial expression and electroencephalogram (EEG) signals from single modal for emotion recognition separately, but few have paid attention to a fusion between them. In t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/11/5/105 |
| _version_ | 1828762732189450240 |
|---|---|
| author | Yongrui Huang Jianhao Yang Siyu Liu Jiahui Pan |
| author_facet | Yongrui Huang Jianhao Yang Siyu Liu Jiahui Pan |
| author_sort | Yongrui Huang |
| collection | DOAJ |
| description | Emotion recognition plays an essential role in human−computer interaction. Previous studies have investigated the use of facial expression and electroencephalogram (EEG) signals from single modal for emotion recognition separately, but few have paid attention to a fusion between them. In this paper, we adopted a multimodal emotion recognition framework by combining facial expression and EEG, based on a valence-arousal emotional model. For facial expression detection, we followed a transfer learning approach for multi-task convolutional neural network (CNN) architectures to detect the state of valence and arousal. For EEG detection, two learning targets (valence and arousal) were detected by different support vector machine (SVM) classifiers, separately. Finally, two decision-level fusion methods based on the enumerate weight rule or an adaptive boosting technique were used to combine facial expression and EEG. In the experiment, the subjects were instructed to watch clips designed to elicit an emotional response and then reported their emotional state. We used two emotion datasets—a Database for Emotion Analysis using Physiological Signals (DEAP) and MAHNOB-human computer interface (MAHNOB-HCI)—to evaluate our method. In addition, we also performed an online experiment to make our method more robust. We experimentally demonstrated that our method produces state-of-the-art results in terms of binary valence/arousal classification, based on DEAP and MAHNOB-HCI data sets. Besides this, for the online experiment, we achieved 69.75% accuracy for the valence space and 70.00% accuracy for the arousal space after fusion, each of which has surpassed the highest performing single modality (69.28% for the valence space and 64.00% for the arousal space). The results suggest that the combination of facial expressions and EEG information for emotion recognition compensates for their defects as single information sources. The novelty of this work is as follows. To begin with, we combined facial expression and EEG to improve the performance of emotion recognition. Furthermore, we used transfer learning techniques to tackle the problem of lacking data and achieve higher accuracy for facial expression. Finally, in addition to implementing the widely used fusion method based on enumerating different weights between two models, we also explored a novel fusion method, applying boosting technique. |
| first_indexed | 2024-12-11T01:48:48Z |
| format | Article |
| id | doaj.art-776e7109571347b3ae3d537b5bb263ff |
| institution | Directory Open Access Journal |
| issn | 1999-5903 |
| language | English |
| last_indexed | 2024-12-11T01:48:48Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj.art-776e7109571347b3ae3d537b5bb263ff2022-12-22T01:24:48ZengMDPI AGFuture Internet1999-59032019-05-0111510510.3390/fi11050105fi11050105Combining Facial Expressions and Electroencephalography to Enhance Emotion RecognitionYongrui Huang0Jianhao Yang1Siyu Liu2Jiahui Pan3School of Software, South China Normal University, Guangzhou 510641, ChinaSchool of Software, South China Normal University, Guangzhou 510641, ChinaSchool of Software, South China Normal University, Guangzhou 510641, ChinaSchool of Software, South China Normal University, Guangzhou 510641, ChinaEmotion recognition plays an essential role in human−computer interaction. Previous studies have investigated the use of facial expression and electroencephalogram (EEG) signals from single modal for emotion recognition separately, but few have paid attention to a fusion between them. In this paper, we adopted a multimodal emotion recognition framework by combining facial expression and EEG, based on a valence-arousal emotional model. For facial expression detection, we followed a transfer learning approach for multi-task convolutional neural network (CNN) architectures to detect the state of valence and arousal. For EEG detection, two learning targets (valence and arousal) were detected by different support vector machine (SVM) classifiers, separately. Finally, two decision-level fusion methods based on the enumerate weight rule or an adaptive boosting technique were used to combine facial expression and EEG. In the experiment, the subjects were instructed to watch clips designed to elicit an emotional response and then reported their emotional state. We used two emotion datasets—a Database for Emotion Analysis using Physiological Signals (DEAP) and MAHNOB-human computer interface (MAHNOB-HCI)—to evaluate our method. In addition, we also performed an online experiment to make our method more robust. We experimentally demonstrated that our method produces state-of-the-art results in terms of binary valence/arousal classification, based on DEAP and MAHNOB-HCI data sets. Besides this, for the online experiment, we achieved 69.75% accuracy for the valence space and 70.00% accuracy for the arousal space after fusion, each of which has surpassed the highest performing single modality (69.28% for the valence space and 64.00% for the arousal space). The results suggest that the combination of facial expressions and EEG information for emotion recognition compensates for their defects as single information sources. The novelty of this work is as follows. To begin with, we combined facial expression and EEG to improve the performance of emotion recognition. Furthermore, we used transfer learning techniques to tackle the problem of lacking data and achieve higher accuracy for facial expression. Finally, in addition to implementing the widely used fusion method based on enumerating different weights between two models, we also explored a novel fusion method, applying boosting technique.https://www.mdpi.com/1999-5903/11/5/105emotion recognitionEEGfacial expressionsdecision-level fusiontransfer learning |
| spellingShingle | Yongrui Huang Jianhao Yang Siyu Liu Jiahui Pan Combining Facial Expressions and Electroencephalography to Enhance Emotion Recognition Future Internet emotion recognition EEG facial expressions decision-level fusion transfer learning |
| title | Combining Facial Expressions and Electroencephalography to Enhance Emotion Recognition |
| title_full | Combining Facial Expressions and Electroencephalography to Enhance Emotion Recognition |
| title_fullStr | Combining Facial Expressions and Electroencephalography to Enhance Emotion Recognition |
| title_full_unstemmed | Combining Facial Expressions and Electroencephalography to Enhance Emotion Recognition |
| title_short | Combining Facial Expressions and Electroencephalography to Enhance Emotion Recognition |
| title_sort | combining facial expressions and electroencephalography to enhance emotion recognition |
| topic | emotion recognition EEG facial expressions decision-level fusion transfer learning |
| url | https://www.mdpi.com/1999-5903/11/5/105 |
| work_keys_str_mv | AT yongruihuang combiningfacialexpressionsandelectroencephalographytoenhanceemotionrecognition AT jianhaoyang combiningfacialexpressionsandelectroencephalographytoenhanceemotionrecognition AT siyuliu combiningfacialexpressionsandelectroencephalographytoenhanceemotionrecognition AT jiahuipan combiningfacialexpressionsandelectroencephalographytoenhanceemotionrecognition |