Uladzislau Barayeu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Uladzislau Barayeu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Andrea Cumpelick
Institute of Science and Technology Austria (ISTA), Klosterneuburg, Austria
1 shared publication- Arno Libert
Katholieke Univ Leuven, Lab Neuro & Psychophysiol, Computat Neurosci Res Grp, Leuven, Belgium
1 shared publication - Jozsef Csicsvari
Institute of Science and Technology Austria (ISTA), Klosterneuburg, Austria
1 shared publication Karola Kaefer
Institute of Science and Technology Austria (ISTA), Klosterneuburg, Austria
1 shared publication- Marc M. Van Hulle
Laboratory for Neuro- & Psychophysiology, Department of Neurosciences, KU Leuven—University of Leuven, B-3000 Leuven, Belgium
1 shared publication - Nastassya Horlava
Institute of Computational Biology, Helmholtz Center Munich
1 shared publication
Latest Publications
- Open Access
Prefrontal representations can specialize rather than generalize with experience
While the medial prefrontal cortex (mPFC) interacts with the hippocampus to support learning and consolidation, how its neural representations evolve remains unclear. We recorded population activity from CA1 and the mPFC as rats trained on radial maze tasks over weeks. Low-dimensional mPFC manifolds generated using UMAP or PCA embeddings initially tracked session progression, showing within-session drift. As animals gained task familiarity, this temporal tracking weakened; mPFC manifolds differentiated specific arms, mirroring hippocampal representations. Arm discriminability was selectively enhanced at locations requiring spatial choices, but weakened when such demands were absent. These findings demonstrate that systems consolidation does not uniformly promote cortical generalization. Instead, the mPFC may slowly refine representations in response to specific task demands to support tailored task schemas.
Open AccessPrefrontal representations can specialize rather than generalize with experience
While the medial prefrontal cortex (mPFC) interacts with the hippocampus to support learning and consolidation, how its neural representations evolve remains unclear. We recorded population activity from CA1 and the mPFC as rats trained on radial maze tasks over weeks. Low-dimensional mPFC manifolds generated using UMAP or PCA embeddings initially tracked session progression, showing within-session drift. As animals gained task familiarity, this temporal tracking weakened; mPFC manifolds differentiated specific arms, mirroring hippocampal representations. Arm discriminability was selectively enhanced at locations requiring spatial choices, but weakened when such demands were absent. These findings demonstrate that systems consolidation does not uniformly promote cortical generalization. Instead, the mPFC may slowly refine representations in response to specific task demands to support tailored task schemas.
- Open Access
- 13 September 2020
- Published by MDPI AG in Biosensors
- Vol. 10 (9) , 124
Robust Single-Trial EEG-Based Authentication Achieved with a 2-Stage Classifier
The risk of personal data exposure through unauthorized access has never been as imminent as today. To counter this, biometric authentication has been proposed: the use of distinctive physiological and behavioral characteristics as a form of identification and access control. One of the recent developments is electroencephalography (EEG)-based authentication. It builds on the subject-specific nature of brain responses which are difficult to recreate artificially. We propose an authentication system based on EEG signals recorded in response to a simple motor paradigm. Authentication is achieved with a novel two-stage decoder. In the first stage, EEG signal features are extracted using an inception- and a VGG-like deep learning neural network (NN) both of which we compare with principal component analysis (PCA). In the second stage, a support vector machine (SVM) is used for binary classification to authenticate the subject based on the extracted features. All decoders are trained on EEG motor-movement data recorded from 105 subjects. We achieved with the VGG-like NN-SVM decoder a false-acceptance rate (FAR) of 2.55% with an overall accuracy of 88.29%, a FAR of 3.33% with an accuracy of 87.47%, and a FAR of 2.89% with an accuracy of 90.68% for 8, 16, and 64 channels, respectively. With the Inception-like NN-SVM decoder we achieved a false-acceptance rate (FAR) of 4.08% with an overall accuracy of 87.29%, a FAR of 3.53% with an accuracy of 85.31%, and a FAR of 1.27% with an accuracy of 93.40% for 8, 16, and 64 channels, respectively. The PCA-SVM decoder achieved accuracies of 92.09%, 92.36%, and 95.64% with FARs of 2.19%, 2.17%, and 1.26% for 8, 16, and 64 channels, respectively.
- 13 September 2020
- Published by MDPI AG in Biosensors
- Vol. 10 (9) , 124
Open AccessRobust Single-Trial EEG-Based Authentication Achieved with a 2-Stage Classifier
The risk of personal data exposure through unauthorized access has never been as imminent as today. To counter this, biometric authentication has been proposed: the use of distinctive physiological and behavioral characteristics as a form of identification and access control. One of the recent developments is electroencephalography (EEG)-based authentication. It builds on the subject-specific nature of brain responses which are difficult to recreate artificially. We propose an authentication system based on EEG signals recorded in response to a simple motor paradigm. Authentication is achieved with a novel two-stage decoder. In the first stage, EEG signal features are extracted using an inception- and a VGG-like deep learning neural network (NN) both of which we compare with principal component analysis (PCA). In the second stage, a support vector machine (SVM) is used for binary classification to authenticate the subject based on the extracted features. All decoders are trained on EEG motor-movement data recorded from 105 subjects. We achieved with the VGG-like NN-SVM decoder a false-acceptance rate (FAR) of 2.55% with an overall accuracy of 88.29%, a FAR of 3.33% with an accuracy of 87.47%, and a FAR of 2.89% with an accuracy of 90.68% for 8, 16, and 64 channels, respectively. With the Inception-like NN-SVM decoder we achieved a false-acceptance rate (FAR) of 4.08% with an overall accuracy of 87.29%, a FAR of 3.53% with an accuracy of 85.31%, and a FAR of 1.27% with an accuracy of 93.40% for 8, 16, and 64 channels, respectively. The PCA-SVM decoder achieved accuracies of 92.09%, 92.36%, and 95.64% with FARs of 2.19%, 2.17%, and 1.26% for 8, 16, and 64 channels, respectively.