Toward Robust EEG Classification Using Adaptive CNN-Transformer and Inception Architectures and Signal Level Augmentation.

Overview

1. Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, Baltimore, MD 21250, USA; (V.R.V.); (S.S.); (P.O.); (D.P.); (J.P.); (F.S.)

Abstract

Non-invasive electroencephalography (EEG) enables practical brain-state monitoring for applications such as emotion recognition and event-related potential (ERP)-based deception detection. However, robust EEG classification remains challenging because of noise, non-stationarity, limited labeled data, and substantial inter-subject variability. In this work, we present a sensor-density-aware framework that applies different deep architectures to low- and high-channel EEG acquisition settings and augments the training data using a physiologically constrained signal-level procedure. For the 5-channel LieWaves dataset, the CNN–Transformer achieved 97.14±1.36% subject-dependent accuracy with augmentation, compared with 92.91±4.34% without augmentation. For the 62-channel SEED dataset, the Inception CNN achieved 98.52±0.79% with augmentation and 98.44±0.83% without augmentation. The improvement on LieWaves was statistically significant, whereas the small improvement on SEED was not statistically significant. Under subject-independent evaluation, performance was 57.83±8.96% on LieWaves with augmentation and 57.95±8.38% on SEED. These results demonstrate strong subject-dependent performance while confirming that cross-subject generalization remains challenging. Overall, the proposed framework combines sensor-density-aware architecture selection with signal-level augmentation and provides a systematic comparison of subject-dependent and subject-independent EEG classification.

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

• data.mendeley.com/datasets/5gzxb2bzs2, at Mendeley Data; found in “Data Availability Statement”

Data Availability Statement

The EEG datasets used for training and evaluation are publicly available as follows: The SEED (SJTU Emotion EEG Dataset) is available from the BCMI Laboratory at SJTU (available at https://bcmi.sjtu.edu.cn/home/seed/, accessed on 28 March 2025). The LieWaves dataset is available upon request or via its official repository (available at https://data.mendeley.com/datasets/5gzxb2bzs2/2, accessed on 28 March 2025). These datasets are subject to the data usage and license policies of their respective providers.

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, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 7 authors, 6 keywords, 6 MeSH terms, 1 funder, 25 references.

Cite

This paper

Venkannagari, V. R., Sharma, S., Olikkal, P., Parikh, D., Paun, J., Safavi, F., & Vinjamuri, R. (2026). Toward Robust EEG Classification Using Adaptive CNN-Transformer and Inception Architectures and Signal Level Augmentation. Sensors (Basel, Switzerland), 26(14), 4636. https://doi.org/10.3390/s26144636

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.3390/s26175327 [code]

Subject Identity Confounds qEEG Emotion Recognition on DEAP and DREAMER.

Journal: Sensors (Basel, Switzerland)

In common: EEG, 3 references

[2] doi:10.3390/bios16080400

EEG and ECG Wearable Biosensor-Based Affective State Analysis Using Deep Learning over 6G IoT Healthcare Networks.

Journal: Biosensors

In common: EEG, 3 references

[3] doi:10.3390/bios16080421

GLSTNet: A Global-Local Spatial Relations and Temporal Dynamics Network for EEG-Based Emotion Recognition.

Journal: Biosensors

In common: EEG, 2 references

[4] doi:10.3389/fnins.2026.1810609

A dual-branch network with brain region-constrained attention for EEG emotion recognition.

Journal: Frontiers in neuroscience

In common: EEG, 2 references

[5] doi:10.1038/s41598-026-68506-6

Frequency-aware transformer networks for robust and generalizable EEG-based seizure detection.

Journal: Scientific reports

In common: EEG, 1 reference

[6] doi:10.3390/bios16080437 [code]

Deep Learning for Ear-EEG-Based Brain-Computer Interface: A Systematic Comparison and Design Insights.

Journal: Biosensors

In common: EEG, 1 reference

[7] doi:10.1371/journal.pone.0347671 [code]

RMETNet: A cross-subject motor imagery EEG signal classification model based on TSLANet and riemannian geometry features.

Journal: PloS one

In common: EEG, 1 reference

[8] doi:10.1038/s41598-026-50997-y [code]

Comprehensive benchmarking and explainable machine learning analysis of EEG imagery activity recognition.

Journal: Scientific reports

In common: EEG, 1 reference

[9] doi:10.1007/s10548-026-01214-6

Operational Transformer: An investigation of epilepsy detection.

Journal: Brain topography

In common: EEG, 1 reference

[10] doi:10.3390/s26092749 [code]

Decoding Mandarin Action Verbs from EEG Using a Dual-LSTM Network: Towards Practical Assistive Brain-Computer Interfaces.

Journal: Sensors (Basel, Switzerland)

In common: EEG, 1 reference

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.

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: 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.