EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deception Detection from Five-Channel Wearable EEG on LieWaves: A Reproducible Baseline for Subject-Dependent and Subject-Independent Evaluation

Șerban-Teodor Nicolescu iD, Felix-Constantin Adochiei iD, Florin-Ciprian Argatu iD, Bogdan-Adrian Enache iD, George-Călin Serițan iD

Sensors · 04.02.2026 · 26 (3) · 1027

DOI: 10.3390/s26031027 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 04.02.2026. Verfasst von Șerban-Teodor Nicolescu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Doctoral School of Electrical Engineering, Faculty of Electrical Engineering, National University of Science and Technology Politehnica Bucharest (NU…. Hauptthemen laut MEDLINE: Electroencephalography, Deception, Wearable Electronic Devices, Lie Detection. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deception detection with low-channel wearable EEG requires protocols that generalize across people while remaining practical for portable devices. Using the public LieWaves dataset (27 subjects recorded with a five-channel Emotiv Insight headset), we evaluate to what extent five-channel head-mounted EEG can support lie–truth discrimination under both subject-independent and subject-dependent evaluations. For the subject-independent setting, we train a compact Residual Network with Squeeze-and-Excitation blocks (ResNet-SE) model on raw overlapping windows with focal loss, light data augmentation, and grouped cross-validation by subject; out-of-fold window probabilities are averaged per session and converted to labels using a single decision threshold estimated from the cross-validated session scores. For the subject-dependent setting, we adopt an overlapping short-window Residual Temporal Convolutional Network with Squeeze-and-Excitation and Attention (Res-TCN-SE-Attention) model that fuses raw EEG with discrete wavelet transform (DWT)-based spectral and handcrafted band-power and Hjorth features, using an 80/10/10 split at the recording/session level (stratified by session label), so that all windows from a given session are assigned to a single subset; because each subject contributes two sessions, the same subject may still appear across subsets via different sessions. The subject-independent model attains 66.70% session-level accuracy with an AUC of 0.58 on unseen subjects, underscoring the difficulty of person-independent generalization from low-channel wearable EEG. Because practical deployment requires generalization to previously unseen individuals, we treat the subject-independent evaluation as the primary estimate of real-world generalization. In contrast, the subject-dependent pipeline reaches 99.94% window-level accuracy under the overlapping sliding-window (OSW) setting with a session-disjoint split (no session contributes windows to more than one subset). This near-ceiling performance reflects the optimistic nature of subject-dependent evaluation with highly overlapping windows, even when avoiding within-session train–test overlap, and should not be interpreted as a meaningful indicator of deception-detection capability under realistic deployment constraints. These results suggest limited, above-chance separability between lie and truth sessions in LieWaves using a five-channel wearable EEG under the studied protocol; however, performance remains far from deployment-ready and is strongly shaped by evaluation design. Explicit reporting of both protocols, together with clear rules for windowing, aggregation, and threshold selection, supports more reproducible and comparable benchmarking.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyDeceptionWearable Electronic DevicesLie DetectionHumansAlgorithmsWavelet AnalysisConvolutional Neural NetworksSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

cross-subject classificationdeception detectiondeep learningdiscrete wavelet transformlow-channel EEGsubject-dependent classificationtemporal convolutional networkswearable EEG

Autor:innen und Institutionen

  • Doctoral School of Electrical Engineering, Faculty of Electrical Engineering, National University of Science and Technology Politehnica Bucharest (NUSTPB), 060042 Bucharest, Romania.
  • Department of Measurements, Electrical Apparatus and Static Converters, Faculty of Electrical Engineering, National University of Science and Technology Politehnica Bucharest (NUSTPB), 060042 Bucharest, Romania.

ORCID-Profile: Șerban-Teodor Nicolescu, Felix-Constantin Adochiei, Florin-Ciprian Argatu, Bogdan-Adrian Enache, George-Călin Serițan

Zitieren

APA

Nicolescu, Ș. T., Adochiei, F. C., Argatu, F. C., Enache, B. A., & Serițan, G. C. (2026). Deception Detection from Five-Channel Wearable EEG on LieWaves: A Reproducible Baseline for Subject-Dependent and Subject-Independent Evaluation. Sensors, 26(3), 1027. https://doi.org/10.3390/s26031027

Vancouver

Nicolescu ȘT, Adochiei FC, Argatu FC, Enache BA, Serițan GC. Deception Detection from Five-Channel Wearable EEG on LieWaves: A Reproducible Baseline for Subject-Dependent and Subject-Independent Evaluation. Sensors. 2026;26(3):1027. doi:10.3390/s26031027

BibTeX
@article{Nicolescu2026,
  author = {Nicolescu, Șerban-Teodor and Adochiei, Felix-Constantin and Argatu, Florin-Ciprian and Enache, Bogdan-Adrian and Serițan, George-Călin},
  title = {Deception Detection from Five-Channel Wearable EEG on LieWaves: A Reproducible Baseline for Subject-Dependent and Subject-Independent Evaluation},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {3},
  pages = {1027},
  doi = {10.3390/s26031027}
}
Kostenlos starten →