Design and Implementation of a Portable EEG-Based Visual Reasoning Assessment System
Engineering, Technology & Applied Science Research · 11.08.2026 · 16 (4) · 37504-37511
DOI: 10.48084/etasr.17837 ↗Kurz gefasst
Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 11.08.2026. Verfasst von K. S. Mohan und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper presents the design and implementation of a portable EEG-based visual reasoning assessment system that integrates behavioral and neurophysiological data to evaluate cognitive performance. The system employs noninvasive EEG electrodes to record brain signals during a visual reasoning task inspired by Raven's Progressive Matrices (RPM). The architecture combines hardware components for signal amplification, analog-to-digital conversion, and Bluetooth-based wireless transmission. The software interface, built in Python, records user accuracy and response time during visual reasoning tasks and synchronizes them with the EEG data in real time. The acquired EEG signals undergo preprocessing using bandpass and notch filtering to remove noise and artifacts, followed by segmentation aligned with task timestamps. Feature extraction techniques, including Power Spectral Density (PSD), Power Spectral Entropy (PSE), and Discrete Wavelet Transform (DWT), are utilized to quantify neural activity in the alpha (8-13 Hz) and gamma (30-80 Hz) bands, which correspond to attention, focus, and reasoning. The extracted features are then processed by a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) architecture that learns both spatial-spectral correlations and temporal dependencies in the EEG data. The proposed deep learning model achieved high accuracy and robust discrimination between reasoning and non-reasoning cognitive states, as validated by Receiver Operating Characteristic (ROC) and confusion matrix analyses. Overall, the results confirm that the integration of EEG-based feature extraction and CNN-LSTM deep learning provides a reliable, low-cost, and portable framework for real-time cognitive evaluation, offering significant potential for educational, psychological, and neurocognitive research applications.
Zitieren
APA
Mohan, K. S., & Ravishankar, K. C. (2026). Design and Implementation of a Portable EEG-Based Visual Reasoning Assessment System. Engineering, Technology & Applied Science Research, 16(4), 37504-37511. https://doi.org/10.48084/etasr.17837
Vancouver
Mohan KS, Ravishankar KC. Design and Implementation of a Portable EEG-Based Visual Reasoning Assessment System. Engineering, Technology & Applied Science Research. 2026;16(4):37504-37511. doi:10.48084/etasr.17837
BibTeX
@article{Mohan2026,
author = {Mohan, K. S. and Ravishankar, K. C.},
title = {Design and Implementation of a Portable EEG-Based Visual Reasoning Assessment System},
journal = {Engineering, Technology & Applied Science Research},
year = {2026},
volume = {16},
number = {4},
pages = {37504--37511},
doi = {10.48084/etasr.17837}
}
EUVIMED