A5027848784- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Advanced Memory and Neural Computing
- Machine Learning and Data Classification
- Blind Source Separation Techniques
- Neuroscience and Neural Engineering
- Advanced Adaptive Filtering Techniques
- Speech and Audio Processing
- Gene expression and cancer classification
- Target Tracking and Data Fusion in Sensor Networks
- Face and Expression Recognition
- Epilepsy research and treatment
- Spectroscopy and Chemometric Analyses
KU Leuven
2018-2021
Dynamic Systems (United States)
2018
Concealable, miniaturized electroencephalography (mini-EEG) recording devices are crucial enablers toward long-term ambulatory EEG monitoring. However, the resulting miniaturization limits inter-electrode distance and scalp area that can be covered by a single device. The concept of wireless sensor networks (WESNs) attempts to overcome this limitation placing multitude these mini-EEG at various locations. We investigate whether optimizing WESN topology compensate for effects in an auditory...
Electroencephalography (EEG) is an essential tool in clinical practice for the diagnosis and monitoring of people with epilepsy. Manual annotation epileptic seizures a time consuming process performed by expert neurologists. Hence, procedure which automatically detects would be hugely beneficial fast cost-effective diagnosis. Recent progress machine learning techniques, especially deep methods, coupled availability large public EEG seizure databases provide new opportunities towards design...
Recent technological advances in the design of concealable miniature electroencephalography (mini-EEG) devices are paving way towards 24/7 neuromonitoring applications daily life. However, such mini-EEG only cover a small area and record EEG over much shorter inter- electrode distances than traditional headsets. These drawbacks can potentially be compensated for by deploying multitude then jointly processing their recorded signals. In this study, we simulate investigate effect using...
Channel selection or electrode placement for neural decoding is a commonly encountered problem in electroencephalography (EEG). Since evaluating all possible channel combinations usually infeasible, one has to settle heuristic methods convex approximations without optimality guarantees. To date, it remains unclear how large the gap between made by these approximate and truly optimal selection. The goal of this paper quantify several state-of-the-art context least-squares based decoding. end,...
Feature selection techniques are very useful approaches for dimensionality reduction in data analysis. They provide interpretable results by reducing the dimensions of to a subset original set features. When lack annotations, unsupervised feature selectors required their Several algorithms this aim exist literature, but despite large applicability, they can be inaccessible or cumbersome use, mainly due need tuning non-intuitive parameters and high computational demands. In work, publicly...
Abstract Objective Concealable, miniaturized electroencephalo-graphy (‘mini-EEG’) recording devices are crucial enablers towards long-term ambulatory EEG monitoring. However, the resulting miniaturization limits inter-electrode distance and scalp area that can be covered by a single device. The concept of wireless sensor networks (WESNs) attempts to overcome this limitation placing multitude these mini-EEG at various locations. We investigate whether optimizing WESN topology compensate for...
Objective.Unobtrusive EEG monitoring in everyday life requires the availability of highly miniaturized devices (mini-EEGs), which ideally consist a wireless node with small scalp area footprint, electrodes, amplifier and radio are embedded.By attaching multitude mini-EEGs at relevant positions on scalp, 'EEG sensor network' (WESN) can be formed.However, each mini-EEG network only has access to its own local thereby recording potentials short interelectrode distances.This is unlike using...
In sensor arrays or networks, tracking each sensors utility helps in excluding those which do not sufficiently contribute to the task at hand, thereby reducing energy consumption avoiding model overfitting. a linearly-constrained minimum variance (LCMV) beamformer, of is defined as increase beamformer's output noise power when would be removed and beamformer coefficients re-optimized. An expression efficiently compute this metric has been found for case where removal corresponds single...
Abstract Channel selection or electrode placement for neural decoding is a commonly encountered problem in electroencephalography (EEG). Since evaluating all possible channel combinations usually infeasible, one has to settle heuristic methods convex approximations without optimality guarantees. To date, it remains unclear how large the gap between made by these approximate and truly optimal selection. The goal of this paper quantify several state-of-the-art context least-squares based...