EEG-ShuffleFormer: A Multi-View Hybrid Network Integrating Time-Frequency and Raw Signal Representations for Few-Channel Motor Imagery EEG Classification.

Overview

Authors: Kang Fan¹, Qin Gu¹, Yaduan Ruan¹

ORCID iDs: Kang Fan, Yaduan Ruan

Department of Critical Care Medicine, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing 210008, China; (K.F.); (Q.G.)

Institutions: Nanjing Drum Tower Hospital (China); Nanjing University (China)

Journal: Bioengineering (Basel, Switzerland), volume 13, issue 5, article 578

Dates: received 5 April 2026; accepted 15 May 2026; published online 19 May 2026

Type: Research article · Language: English

License: CC BY

Identifiers: DOI 10.3390/bioengineering13050578 · PMID 42194335 · PMCID PMC13203743 · OpenAlex W7161816312

Open access: gold, a free copy (OpenAlex)

Status: data only

Categories: EEG (modality), cellular / molecular (subfield)

Methods: Spectral & time-frequency, Preprocessing, Machine learning

Keywords: few-channel MI EEG, ShuffleNet, Transformer, hybrid network, multi-view feature fusion, continuous wavelet transform, transfer learning

Topic: EEG and Brain-Computer Interfaces (Cognitive Neuroscience, Neuroscience), according to OpenAlex

Citations: not cited yet (Europe PMC); 31 references in the paper

Abstract

Electroencephalogram (EEG) signals hold significant research value in brain function decoding, disease diagnosis, and brain–computer interfaces (BCIs). Few-channel EEG recording devices feature superior portability, simple operation, and facilitated real-time monitoring implementation. However, few-channel motor imagery (MI) EEG signals inherently suffer from data scarcity and limited spatial discriminative information, which pose critical challenges, including insufficient feature extraction and poor robustness in classification tasks. To address these issues, this paper presents EEG–ShuffleFormer, a hybrid network that integrates two complementary views of EEG signals: time–frequency representations obtained via continuous wavelet transform and the original raw signal representations. A lightweight ShuffleNet backbone extracts local features, followed by a Transformer encoder that models long-range temporal dependencies. Evaluated on the BCI Competition IV Dataset 2b, the proposed method achieves an average classification accuracy of 82.23%, with a substantial improvement on challenging subjects compared to the closest baseline method. Compared with existing methods, the proposed multi-view fusion strategy raises the performance floor while maintaining high accuracy on typical subjects, demonstrating its potential to enhance robustness for different subjects in few-channel scenarios.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data, not to its authors' code: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

bbci.de/competition/iv — at bbci.de; found in “Data Availability Statement”

Data Availability Statement

The data presented in this study are available in BCI Competition IV at https://www.bbci.de/competition/iv/ (accessed on 4 January 2024), reference number [24].

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 28 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 3 authors, 7 keywords, 30 references.

Cite

This paper

Fan, K., Gu, Q., & Ruan, Y. (2026). EEG-ShuffleFormer: A Multi-View Hybrid Network Integrating Time-Frequency and Raw Signal Representations for Few-Channel Motor Imagery EEG Classification. Bioengineering (Basel, Switzerland), 13(5), 578. https://doi.org/10.3390/bioengineering13050578

BibTeX

@article{fan2026eeg, author = {Fan, Kang and Gu, Qin and Ruan, Yaduan}, title = {{EEG-ShuffleFormer: A Multi-View Hybrid Network Integrating Time-Frequency and Raw Signal Representations for Few-Channel Motor Imagery EEG Classification}}, journal = {Bioengineering (Basel, Switzerland)}, year = {2026}, month = may, volume = {13}, number = {5}, pages = {578}, publisher = {Multidisciplinary Digital Publishing Institute (MDPI)}, issn = {2306-5354}, doi = {10.3390/bioengineering13050578}, url = {https://doi.org/10.3390/bioengineering13050578}, pmid = {42194335}, pmcid = {PMC13203743} }

RIS

TY - JOUR AU - Fan, Kang AU - Gu, Qin AU - Ruan, Yaduan TI - EEG-ShuffleFormer: A Multi-View Hybrid Network Integrating Time-Frequency and Raw Signal Representations for Few-Channel Motor Imagery EEG Classification T2 - Bioengineering (Basel, Switzerland) J2 - Bioengineering (Basel) PY - 2026 DA - 2026/05/19 VL - 13 IS - 5 SP - 578 SN - 2306-5354 PB - Multidisciplinary Digital Publishing Institute (MDPI) DO - 10.3390/bioengineering13050578 UR - https://doi.org/10.3390/bioengineering13050578 LA - en ER -

CSL-JSON

{ "id": "10.3390/bioengineering13050578", "type": "article-journal", "title": "EEG-ShuffleFormer: A Multi-View Hybrid Network Integrating Time-Frequency and Raw Signal Representations for Few-Channel Motor Imagery EEG Classification", "container-title": "Bioengineering (Basel, Switzerland)", "author": [ { "family": "Fan", "given": "Kang" }, { "family": "Gu", "given": "Qin" }, { "family": "Ruan", "given": "Yaduan" } ], "container-title-short": "Bioengineering (Basel)", "volume": "13", "issue": "5", "page": "578", "DOI": "10.3390/bioengineering13050578", "PMID": "42194335", "PMCID": "PMC13203743", "ISSN": "2306-5354", "publisher": "Multidisciplinary Digital Publishing Institute (MDPI)", "URL": "https://doi.org/10.3390/bioengineering13050578", "language": "en", "issued": { "date-parts": [ [ 2026, 5, 19 ] ] } }

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.