EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Vikas Reddy Venkannagari, Shivansh Sharma iD, Parthan Olikkal iD, Dev Parikh iD, Jay Paun iD, Farshad Safavi, Ramana Vinjamuri iD

Sensors · 22.07.2026 · 26 (14) · 4636

DOI: 10.3390/s26144636 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.07.2026. Verfasst von Vikas Reddy Venkannagari und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, Baltimore, MD 21250, USA. Hauptthemen laut MEDLINE: Electroencephalography, Signal Processing, Computer-Assisted. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographySignal Processing, Computer-AssistedConvolutional Neural NetworksHumansAlgorithmsBrain

Stichwörter der Autor:innen

P300-based deception detectionconvolutional neural networkdata augmentationelectroencephalographyemotion recognitiontransformer

Autor:innen und Institutionen

  • Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, Baltimore, MD 21250, USA.

ORCID-Profile: Shivansh Sharma, Parthan Olikkal, Dev Parikh, Jay Paun, Ramana Vinjamuri

Förderung

  • National Science Foundation

Zitieren

APA

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, 26(14), 4636. https://doi.org/10.3390/s26144636

Vancouver

Venkannagari VR, Sharma S, Olikkal P, Parikh D, Paun J, Safavi F, et al. Toward Robust EEG Classification Using Adaptive CNN–Transformer and Inception Architectures and Signal Level Augmentation. Sensors. 2026;26(14):4636. doi:10.3390/s26144636

BibTeX
@article{Venkannagari2026,
  author = {Venkannagari, Vikas Reddy and Sharma, Shivansh and Olikkal, Parthan and Parikh, Dev and Paun, Jay and Safavi, Farshad and Vinjamuri, Ramana},
  title = {Toward Robust EEG Classification Using Adaptive CNN–Transformer and Inception Architectures and Signal Level Augmentation},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4636},
  doi = {10.3390/s26144636}
}
Kostenlos starten →