CoChat
Sign Up
Cited by 55EEG and Brain-Computer InterfacesEmotion and Mood RecognitionNeuroscience and Music Perception

The DOI matches its Crossref record; 79 of the 79 references it cites were found in a registry or an index.

A GRU–CNN model for auditory attention detection using microstate and recurrence quantification analysis

Open access
EskandariNasab, MohammadReza, Raeisi, Zahra, Lashaki, Reza Ahmadi, Najafi, Hamidreza·2024·Scientific Reports
DOI 10.1038/s41598-024-58886-yPMC PMC11024110
Open this paper in CoChat — free accountOpen PDF

Abstract

Attention as a cognition ability plays a crucial role in perception which helps humans to concentrate on specific objects of the environment while discarding others. In this paper, auditory attention detection (AAD) is investigated using different dynamic features extracted from multichannel electroencephalography (EEG) signals when listeners attend to a target speaker in the presence of a competing talker. To this aim, microstate and recurrence quantification analysis are utilized to extract different types of features that reflect changes in the brain state during cognitive tasks. Then, an optimized feature set is determined by employing the processes of significant feature selection based on classification performance. The classifier model is developed by hybrid sequential learning that employs Gated Recurrent Units (GRU) and Convolutional Neural Network (CNN) into a unified framework for accurate attention detection. The proposed AAD method shows that the selected feature set achieves the most discriminative features for the classification process. Also, it yields the best performance as compared with state-of-the-art AAD approaches from the literature in terms of various measures. The current study is the first to validate the use of microstate and recurrence quantification parameters to differentiate auditory attention using reinforcement learning without access to stimuli.

Overview

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1038/s41598-024-58886-y

Cites

79 of 79 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 The proposed AAD method based on microstate and recurrence quantification analysis.
Figure 1 The proposed AAD method based on microstate and recurrence quantification analysis.CC BY · PubMed Central
Figure 2 Schematic flowchart of the EEG microstate analysis using MNE. The GFP of each sampling point is calculated and all topographic maps at the local GFP maxima are obtained. The K-means clustering analysis method is used to analyze topographic maps to obtain optimal microstate classes. At the bottom, microstate temporal sequences are obtained by fitting microstate classes back to complete EEG data.
Figure 2 Schematic flowchart of the EEG microstate analysis using MNE. The GFP of each sampling point is calculated and all topographic maps at the local GFP maxima are obtained. The K-means clustering analysis method is used to analyze topographic maps to obtain optimal microstate classes. At the bottom, microstate temporal sequences are obtained by fitting microstate classes back to complete EEG data.CC BY · PubMed Central
Figure 3 Changes in occurrence values of microstate features depend on each subject of DTU database and performance. Boxplots represent the first quantile, third quantile, and median values.
Figure 3 Changes in occurrence values of microstate features depend on each subject of DTU database and performance. Boxplots represent the first quantile, third quantile, and median values.CC BY · PubMed Central
Figure 4 Example of recurrence plots (RP) with 12 different scales for the GFP extracted from EEG of DTU database.
Figure 4 Example of recurrence plots (RP) with 12 different scales for the GFP extracted from EEG of DTU database.CC BY · PubMed Central
Figure 5 The block diagram of the proposed GCQL to improve estimating the value function.
Figure 5 The block diagram of the proposed GCQL to improve estimating the value function.CC BY · PubMed Central
Figure 6 AAD performance only with MS feature vectors on DTU and KUL databases.
Figure 6 AAD performance only with MS feature vectors on DTU and KUL databases.CC BY · PubMed Central
Figure 7 AAD performance only with RP feature vectors among all subjects on DTU and KUL databases.
Figure 7 AAD performance only with RP feature vectors among all subjects on DTU and KUL databases.CC BY · PubMed Central
Figure 8 Performance of the proposed GCQL-AAD using multivariate feature (i.e., “mean GFP + RR”) and GCQL classifier for different EEG segments on DTU and KUL databases.
Figure 8 Performance of the proposed GCQL-AAD using multivariate feature (i.e., “mean GFP + RR”) and GCQL classifier for different EEG segments on DTU and KUL databases.CC BY · PubMed Central
Figure 9 Comparison of the proposed AAD method (purple) with the others including “O’Sullivan et al16. (blue), Lu et al25. (light blue), Ciccarelli et al20. (orange), Geirnaert et al26. (red), Zakeri et al27. (yellow), Cai et al56. (neutral), and Niu et al87. (green) in terms of accuracy.
Figure 9 Comparison of the proposed AAD method (purple) with the others including “O’Sullivan et al16. (blue), Lu et al25. (light blue), Ciccarelli et al20. (orange), Geirnaert et al26. (red), Zakeri et al27. (yellow), Cai et al56. (neutral), and Niu et al87. (green) in terms of accuracy.CC BY · PubMed Central

Verification

Claims the paper makes

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

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

Research works printed but not linked: 12

  1. D. E. Broadbent, Perception and communication. Elsevier, (2013).
  2. Kallenberg, M., Desain, P. & Gielen, S. Auditory selective attention as a method for a brain computer interface. Nijmegen CNS. 2(1), 1–6 (2006).
  3. Das, N., Zegers, J., Francart, T. & Bertrand, A. EEG-informed speaker extraction from noisy recordings in neuro-steered hearing aids: Linear versus deep learning methods. BioRxiv https://doi.org/10.1101/2020.01.22.915181 (2020). · DOI
  4. Mesgarani, N. & Chang, E. F. Selective cortical representation of attended speaker in multi-talker speech perception. J. Nat. 485(7397), 233–236 (2012). · DOI
  5. Lu, Y., Wang, M., Zhang, Q. & Han, Y. Identification of auditory object-specific attention from single-trial electroencephalogram signals via entropy measures and machine learning. Entropy 20(5), 386 (2018). · DOI
  6. O’sullivan, J. A. et al. Attentional selection in a cocktail party environment can be decoded from single-trial EEG. J. Cerebral Cortex 25(7), 1697–1706 (2015). · DOI
  7. L. Deckers, N. Das, A. Ansari, A. Bertrand, and T. Francart, EEG-based detection of the attended speaker and the locus of auditory attention with convolutional neural networks. BioRxiv, 475673, (2018)
  8. Wong, D. D. et al. A comparison of regularization methods in forward and backward models for auditory attention decoding. J. Front. Neurosci. 12, 352049 (2018).
  9. Ciccarelli, G. et al. Comparison of two-talker attention decoding from EEG with nonlinear neural networks and linear methods. J. Sci. Rep. 9(1), 11538 (2019). · DOI
  10. Baghdadi, G., Amiri, M., Falotico, E. & Laschi, C. Recurrence quantification analysis of EEG signals for tactile roughness discrimination. J. Int. J. Mach. Learn. Cybern. 12, 1115–1136 (2021). · DOI
  11. V. Vapnik, The nature of statistical learning theory. Springer science & business media, (2013)
  12. Zhu, W., Zeng, N. & Wang, N. Sensitivity, specificity, accuracy, associated confidence interval and ROC analysis with practical SAS implementations. NESUG Proceed. Health Care Life Sci. Baltimore Maryland 19, 67 (2010).

Cited by

Sorted by citations

See all 55

Related

See all

Metadata

Authors
EskandariNasab, M., Raeisi, Z., Lashaki, R. A., & Najafi, H.
Affiliations
  • Utah State University (US)
  • University of Tabriz (IR)
  • Iran University of Science and Technology (IR)
Corresponding author
EskandariNasab, MohammadReza
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2024-04-17
Volume
14
Issue
1
Pages
8861-8861
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-024-58886-y
PMC
PMC11024110
OpenAlex
W4394881920
Cited by
55
References
79
Citations by year
2026: 8 · 2025: 20 · 2024: 27
FWCI
13.36
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • Research Square (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
  • Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Neuroscience and Music Perception
Keywords
auditory attention detection, EEG microstates, recurrence quantification analysis, gated recurrent unit, convolutional neural networks, feature selection, competing talkers, brain state dynamics, reinforcement learning
MeSH terms
Machine Learning, Attention, Brain, Brain Mapping, Electroencephalography, Humans, Neural Networks, Computer

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