CoChat
Cited by 200

The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.

Cross-Subject Multimodal Emotion Recognition Based on Hybrid Fusion

Open access
Cimtay, Yucel, Ekmekcioglu, Erhan, Caglar-Ozhan, Seyma · 2020 · IEEE Access

Abstract

Multimodal emotion recognition has gained traction in affective computing research community to overcome the limitations posed by the processing a single form of data and to increase recognition robustness. In this study, a novel emotion recognition system is introduced, which is based on multiple modalities including facial expressions, galvanic skin response (GSR) and electroencephalogram (EEG). This method follows a hybrid fusion strategy and yields a maximum one-subject-out accuracy of 81.2% and a mean accuracy of 74.2% on our bespoke multimodal emotion dataset (LUMED-2) for 3 emotion classes: sad, neutral and happy. Similarly, our approach yields a maximum one-subject-out accuracy of 91.5% and a mean accuracy of 53.8% on the Database for Emotion Analysis using Physiological Signals (DEAP) for varying numbers of emotion classes, 4 in average, including angry, disgust, afraid, happy, neutral, sad and surprised. The presented model is particularly useful in determining the correct emotional state in the case of natural deceptive facial expressions. In terms of emotion recognition accuracy, this study is superior to, or on par with, the reference subject-independent multimodal emotion recognition studies introduced in the literature.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/access.2020.3023871

Cites

22 of 22 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 22 references

Research works printed but not linked: 86

  1. 10.1109/MIS.2017.23 · DOI · Paper page
  2. 10.1109/MIS.2017.57 · DOI
  3. 10.1109/MIS.2019.2904691 · DOI · Paper page
  4. 10.1109/MIS.2019.2954966 · DOI
  5. 10.1109/MIS.2020.2979203 · DOI
  6. 10.1109/MIS.2016.31 · DOI · Paper page
  7. 10.1109/MIS.2017.3711649 · DOI
  8. 10.1109/MIS.2018.033001419 · DOI
  9. 10.1109/MIS.2019.2899142 · DOI
  10. 10.1109/MIS.2017.22 · DOI
  11. 10.1109/MIS.2018.2882362 · DOI · Paper page
  12. hazer-rau, 2020, The uulmMAC database—A multimodal affective corpus for affective computing in human-computer interaction, SENSORS, 20, 2308, 10.3390/s20082308 · DOI
  13. 10.1109/TENCON.2016.7847950 · DOI
  14. masui, 2020, Continuous estimation of emotional change using multimodal affective responses, Proc IEEE/CVF Conf Comput Vis Pattern Recognit (CVPR) Workshops, 290
  15. 10.1109/ICIMIA.2017.7975659 · doi:10.1109/icimia.2017.7975659
  16. 10.1109/BDCloud-SocialCom-SustainCom.2016.29 · DOI
  17. 10.1109/MIS.2019.2925204 · DOI
  18. 10.1109/TNN.2010.2091281 · DOI · Paper page
  19. 10.1109/ICBDA.2017.8078794 · DOI
  20. 10.1109/TCYB.2016.2633306 · DOI · Paper page
  21. 10.1109/JSTSP.2017.2764438 · doi:10.1109/jstsp.2017.2764438 · Paper page
  22. 2020, Seeds Dataset
  23. tipping, 2001, Sparse Bayesian learning and the relevance vector machine, J Mach Learn Res, 1, 211
  24. 10.1145/2911996.2912059 · DOI
  25. 10.1109/CVPR.1993.1626170 · DOI
  26. 10.1145/2070481.2070487 · DOI
  27. 10.1007/3-540-45014-9_5 · doi:10.1007/3-540-45014-9_5
  28. reuderink, 2008, Decision-level fusion for audio-visual laughter detection, Machine Learning for Multimodal Interaction (MLMI), 5237, 137, 10.1007/978-3-540-85853-9_13 · DOI
  29. 10.1109/CIHLI.2013.6613272 · DOI
  30. 10.1109/ICCP.2018.8516437 · DOI
  31. 10.1080/10447318.2016.1159799 · DOI
  32. 10.1109/BIBM.2015.7359713 · DOI
  33. wang, 2020, A review of emotion sensing: Categorization models and algorithms, Multimedia Tools Appl, 1
  34. 10.1109/URAI.2018.8441795 · DOI
  35. 10.1109/CSICC.2009.5349653 · DOI
  36. 10.1109/ACCESS.2019.2914872 · DOI
  37. 10.1109/TechSym.2016.7872646 · DOI
  38. 10.1109/TAFFC.2015.2411280 · DOI
  39. 2020, LUMED-2 Dataset
  40. 2020, FacesDB
  41. 10.1080/02699930903485076 · DOI · Paper page
  42. 10.1016/j.jneumeth.2010.04.028 · DOI · Paper page
  43. 2020, DEAP Dataset
  44. 2020, Pretrained Deep Neural Networks
  45. 2020, IMOTIONS
  46. 2020, Top 14 EEG Hardware companies [Ranked]
  47. 10.1109/ACIIAsia.2018.8470379 · DOI
  48. kim, 2005, Integrating information from speech and physiological signals to achieve emotional sensitivity, Proc INTERSPEECH, 809, 10.21437/Interspeech.2005-380 · DOI
  49. 10.1109/CVPR.2016.374 · DOI · Paper page
  50. syeda, 2017, Cross-subject continuous emotion recognition using speech and body motion in dyadic interactions, Proc INTERSPEECH, 1731
  51. 10.1007/s10579-015-9300-0 · DOI
  52. 10.1186/s12911-017-0562-x · DOI
  53. szegedy, 2017, Inception-v4, inception-resnet and the impact of residual connections on learning, Proc AAAI, 4, 1
  54. 10.1515/sh-2016-0011 · DOI
  55. 2020, Empatica e4
  56. cimtay, 2020, Investigating the use of pretrained convolutional neural network on cross-subject and cross-dataset EEG emotion recognition, SENSORS, 20, 2034, 10.3390/s20072034 · DOI · Paper page
  57. 10.1109/ICASSP.2013.6637858 · DOI
  58. zhang, 2019, Cross-subject EEG-based emotion recognition with deep domain confusion, Intelligent Robotics and Applications (ICIRA), 11740, 558, 10.1007/978-3-030-27526-6_49 · DOI
  59. 10.1088/1742-6596/705/1/012051 · DOI
  60. 10.1162/089976698300017467 · DOI · Paper page
  61. 10.1109/FSKD.2016.7603437 · DOI
  62. gong, 2012, Geodesic flow kernel for unsupervised domain adaptation, Proc IEEE Conf Comput Vis Pattern Recognit, 2066
  63. shi, 2012, Information-theoretical learning of discriminative clusters for unsupervised domain adaptation, Proc Intl Conf on Machine Learning (ICML) 2012, 1275
  64. 10.1109/ICCV.2013.368 · DOI · Paper page
  65. 10.3389/fncom.2019.00053 · DOI
  66. 10.1016/j.jksuci.2019.11.003 · DOI · Paper page
  67. 10.1109/JSEN.2018.2883497 · DOI · Paper page
  68. 10.3389/fnbot.2017.00019 · DOI · Paper page
  69. 10.1037/0022-3514.53.4.712 · DOI · Paper page
  70. 10.1109/T-AFFC.2012.36 · DOI
  71. fabien, 2015, AVEC 2015: The first affect recognition challenge bridging across audio, video, and physiological data, Proc of International Audio/Visual Emotion Challenge and Workshop, 3
  72. 10.1109/ACCESS.2019.2949741 · DOI · Paper page
  73. 10.1109/ACCESS.2017.2672722 · DOI
  74. 10.1109/ACCESS.2019.2928691 · DOI · Paper page
  75. 10.3390/e18090272 · DOI · Paper page
  76. osman, 2016, Multimodal Affect Recognition Current Approaches and Challenges
  77. 10.1016/j.knosys.2013.02.014 · DOI · Paper page
  78. arns, 2013, A decade of EEG theta/beta ratio research in ADHD a meta-analysis, 17, 374
  79. 10.1145/3332169.3333569 · DOI
  80. 10.1093/brain/awy251 · DOI · Paper page
  81. 10.1016/j.neuroimage.2006.09.024 · DOI · Paper page
  82. thejaswini, 2019, Analysis of EEG based emotion detection of DEAP and SEED-IV databases using SVM, International Journal of Recent Technology and Engineering, 8, 207
  83. 10.1371/journal.pone.0174949 · DOI · Paper page
  84. 10.3390/s130810273 · DOI · Paper page
  85. 10.1371/journal.pone.0214507 · DOI
  86. 10.1109/ICSPIS.2017.8311585 · DOI

Cited by

Metadata

Authors
Cimtay, Y., Ekmekcioglu, E., & Caglar-Ozhan, S.
Venue
IEEE Access
Published
2020
Volume
8
Pages
168865-168878
ISSN
2169-3536 (ISSN-L)
OpenAlex
W3084624816
Cited by
200
References
22
FWCI
18.51
Type
journal article
Language
en
Open access
gold
Funders
  • Institutional Links grant (352175665)
  • Newton–Katip Celebi partnership between the U.K. and Turkey
  • U.K. Department of Business, Energy and Industrial Strategy (BEIS) and The Scientific and Technological Research Council of Turkey (TUBITAK) and delivered by the British Council

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.