EEG imagined speech neuro-signal preprocessing and deep learning classification.

Overview

Authors: Fatma Elwasify¹, Eman Shaaban¹, Randa M. Abdelmoneem¹

ORCID iDs: Fatma Elwasify

Computer Systems Department, Faculty of Computer and Information Science, Ain Shams University,Cairo, Egypt

Institutions: Ain Shams University (Egypt)

Journal: Scientific reports, volume 16, issue 1, article 10604

Dates: received 20 May 2025; accepted 4 February 2026; published online 30 March 2026

Type: Research article · Language: English

License: CC BY

Identifiers: DOI 10.1038/s41598-026-39395-6 · PMID 41912561 · PMCID PMC13039726 · OpenAlex W7143420620

Open access: gold, a free copy (OpenAlex)

Status: data only (how the code is found and verified)

Categories: EEG (modality), human (organism), cognitive (subfield)

Methods: Smoothing, state filtering, decompositions, Machine learning, Preprocessing, Spectral & time-frequency, Physiology & signal measures, Connectivity

Keywords: Imagined speech, EEG, Brain-computer interface, Deep learning, CNN-LSTM, LOSO cross-validation, ICA, Frequency-domain filtering, Cross-subject generalization, Software, Learning algorithms, Network models, Neural decoding, Machine learning

MeSH: Deep Learning*, Electroencephalography*, Imagination*, Signal Processing, Computer-Assisted*, Speech*, Convolutional Neural Networks, Humans, Long Short Term Memory (* major topic)

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

Funding: Ain Shams University

Citations: cited by 1 paper (Europe PMC); 39 references in the paper

Abstract

This study presents an advanced approach for classifying imagined speech from Electroencephalography (EEG) signals, leveraging deep learning architectures and tailored preprocessing techniques. Five Convolutional Neural Network (CNN)–Long Short-Term Memory (LSTM) hybrid architectures are proposed and investigated, to extract spatial and temporal features in EEG signals, in conjunction with a proposed six-phase preprocessing pipeline combining Independent Component Analysis (ICA) for artifact attenuation with zero-phase Frequency-Domain Filtering (FD-F) and adaptive normalization. The proposed approach is evaluated across single- and multi-category classification and across multiple cross-validation strategies including random splits, GroupKFold and Leave-One-Subject-Out (LOSO) using weighted metrics, per-class, and per-subject analysis. Experiment results demonstrate the superior performance achieved by FD-F, and that by integrating the most effective proposed bidirectional temporal modeling architecture CNN-2-Bi-LSTM, with the proposed preprocessing pipeline, the approach achieves higher accuracy (exceeding 99%) for 30-class classification maintaining cross-subject generalization against state-of-the-art.

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

Code

The paper links to its data and to no code of its authors: 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

kaggle.com/datasets/ignazio, at Kaggle; found in “Data availability”
osf:pq7vb, at OSF; found in the references

Data availability

The Kumar EEG Imagined Speech Dataset26, which is raw data used in this study. The dataset is publicly available on Kaggle at the following URL: https://www.kaggle.com/datasets/ignazio/kumars-eeg-imagined-speech.

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, 30 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 3 authors, 14 keywords, 8 MeSH terms, 1 funder, 39 references.

Cite

This paper

Elwasify, F., Shaaban, E., & Abdelmoneem, R. M. (2026). EEG imagined speech neuro-signal preprocessing and deep learning classification. Scientific reports, 16(1), 10604. https://doi.org/10.1038/s41598-026-39395-6

BibTeX

@article{elwasify2026eeg, author = {Elwasify, Fatma and Shaaban, Eman and Abdelmoneem, Randa M.}, title = {{EEG imagined speech neuro-signal preprocessing and deep learning classification}}, journal = {Scientific reports}, year = {2026}, month = mar, volume = {16}, number = {1}, pages = {10604}, publisher = {Nature Publishing Group}, issn = {2045-2322}, doi = {10.1038/s41598-026-39395-6}, url = {https://doi.org/10.1038/s41598-026-39395-6}, pmid = {41912561}, pmcid = {PMC13039726} }

RIS

TY - JOUR AU - Elwasify, Fatma AU - Shaaban, Eman AU - Abdelmoneem, Randa M. TI - EEG imagined speech neuro-signal preprocessing and deep learning classification T2 - Scientific reports J2 - Sci Rep PY - 2026 DA - 2026/03/30 VL - 16 IS - 1 SP - 10604 SN - 2045-2322 PB - Nature Publishing Group DO - 10.1038/s41598-026-39395-6 UR - https://doi.org/10.1038/s41598-026-39395-6 LA - en ER -

CSL-JSON

{ "id": "10.1038/s41598-026-39395-6", "type": "article-journal", "title": "EEG imagined speech neuro-signal preprocessing and deep learning classification", "container-title": "Scientific reports", "author": [ { "family": "Elwasify", "given": "Fatma" }, { "family": "Shaaban", "given": "Eman" }, { "family": "Abdelmoneem", "given": "Randa M." } ], "container-title-short": "Sci Rep", "volume": "16", "issue": "1", "page": "10604", "DOI": "10.1038/s41598-026-39395-6", "PMID": "41912561", "PMCID": "PMC13039726", "ISSN": "2045-2322", "publisher": "Nature Publishing Group", "URL": "https://doi.org/10.1038/s41598-026-39395-6", "language": "en", "issued": { "date-parts": [ [ 2026, 3, 30 ] ] } }

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: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

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