BioTWavePat: An EEG-Based Mental Performance Detection Model
6 affiliations
- 1Department of Digital Forensics Engineering, Technology Faculty, Firat University, 23119 Elazig, Türkiye
- 2Department of Computer Engineering, College of Engineering, Erzurum Technical University, 25050 Erzurum, Türkiye
- 3Department of Neurology, School of Medicine, Firat University, 23119 Elazig, Türkiye
- 4Department of Computer Technologies, Bingöl University, 12000 Bingöl, Türkiye
- 5Department of Computer Engineering, Faculty of Engineering, Munzur University, 62000 Tunceli, Türkiye
- 6Department of Electrical and Energy, Vocational School of Technical Sciences, Firat University, 23119 Elazig, Türkiye
Abstract
Background/Objectives: EEG-based mental performance classification requires participant-separated validation and traceable feature identities. Methods: BioTWavePat-XFE constructs five single-rhythm and 15 signed cross-rhythm channel-rank transition layers, uses four cumulative-weighted selectors and tkNN/IMV classification, and decodes retained identities with Directed Lobish. We compared Protocol A (whole-dataset feature and pooled-test outcome selection), Protocol B (training-fold outcome selection with Protocol A features), and Protocol C (all data-dependent steps restricted to outer training data). STEW and MAT used participant-wise LOSO. TMPD included all 55 participants in 54 identifier groups; two same-class participants sharing an identifier were withheld together. Results: Protocol A segment accuracies were 83.08% (STEW), 93.14% (TMPD), and 91.15% (MAT). Protocol C accuracies were 80.46%, 82.50%, and 74.65%, with balanced accuracies of 80.46%, 75.17%, and 64.15%, respectively. These are the primary estimates without the identified selection leakage under the stated participant-separated validation design. Conclusions: Whole-dataset selection inflated the original estimates, particularly for TMPD and MAT. MAT Protocol C performance was close to majority prediction. Directed Lobish exposes selected feature identities without establishing physiological connectivity, causality or biomarker validity.
Related
- Performance of the University of California, San Diego Brief Assessment of Capacity to Consent (UBACC) questionnaire in mental health genetic research in Africa
- AI-enabled and comparator digital interventions for adolescent mental health (2020–2025): early detection, human–AI collaboration, and ethical governance—a PRISMA-ScR scoping review
- Understanding How the Self-Regulation in Sport Practice Survey is Received by Mental Performance Consultants for Prospective Use in Applied Practice
- Emotion Recognition From AI-Generated and Human Faces: Performance, Mental Health, and Demographic Diversity
- Association of Senior Dance Participation with Mental Well-Being and Functional Performance in Older Women: A Cross-Sectional Study
BibTeX
@article{keles2026biotwavepat,
title = {{BioTWavePat: An EEG-Based Mental Performance Detection Model}},
author = {Tugce Keles and Mehmet Baygin and Irem Tasci and Erdem Gonultas and Taha Muezzinoglu and Burak Tasci and Sengul Dogan and Turker Tuncer},
journal = {Journal of Clinical Medicine},
year = {2026},
month = oct,
doi = {10.3390/jcm15218471},
url = {https://www.mdpi.com/2077-0383/15/21/8471},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - BioTWavePat: An EEG-Based Mental Performance Detection Model
AU - Tugce Keles
AU - Mehmet Baygin
AU - Irem Tasci
AU - Erdem Gonultas
AU - Taha Muezzinoglu
AU - Burak Tasci
AU - Sengul Dogan
AU - Turker Tuncer
PY - 2026
DA - 2026/10/30
JO - Journal of Clinical Medicine
DO - 10.3390/jcm15218471
UR - https://www.mdpi.com/2077-0383/15/21/8471
AB - Background/Objectives: EEG-based mental performance classification requires participant-separated validation and traceable feature identities. Methods: BioTWavePat-XFE constructs five single-rhythm and 15 signed cross-rhythm channel-rank transition layers, uses four cumulative-weighted selectors and tkNN/IMV classification, and decodes retained identities with Directed Lobish. We compared Protocol A (whole-dataset feature and pooled-test outcome selection), Protocol B (training-fold outcome selection with Protocol A features), and Protocol C (all data-dependent steps restricted to outer training data). STEW and MAT used participant-wise LOSO. TMPD included all 55 participants in 54 identifier groups; two same-class participants sharing an identifier were withheld together. Results: Protocol A segment accuracies were 83.08% (STEW), 93.14% (TMPD), and 91.15% (MAT). Protocol C accuracies were 80.46%, 82.50%, and 74.65%, with balanced accuracies of 80.46%, 75.17%, and 64.15%, respectively. These are the primary estimates without the identified selection leakage under the stated participant-separated validation design. Conclusions: Whole-dataset selection inflated the original estimates, particularly for TMPD and MAT. MAT Protocol C performance was close to majority prediction. Directed Lobish exposes selected feature identities without establishing physiological connectivity, causality or biomarker validity.
SN - 2077-0383
ER -