scholarly journals Deep learning-based EEG analysis: investigating P3 ERP components

2021 ◽  
Vol 20 (4) ◽  
pp. 791-811
Author(s):  
Davide Borra ◽  
Elisa Magosso
Keyword(s):  
Deep Learning ◽  
Eeg Analysis

scholarly journals A Novel Local Explainability Approach for Spectral Insight into Raw EEG-Based Deep Learning Classifiers

2021 ◽  
Author(s):  
Charles A Ellis ◽  
Robyn L Miller ◽  
Vince Calhoun
Keyword(s):  
Deep Learning ◽  
Sleep Stage ◽  
Sleep Stages ◽  
Eeg Analysis ◽  
Frequency Bands ◽  
Learning Classifiers ◽  
Eeg Data ◽  
Stage Classification ◽  
Sleep Stage Classification ◽  
Insight Into

The frequency domain of electroencephalography (EEG) data has developed as a particularly important area of EEG analysis. EEG spectra have been analyzed with explainable machine learning and deep learning methods. However, as deep learning has developed, most studies use raw EEG data, which is not well-suited for traditional explainability methods. Several studies have introduced methods for spectral insight into classifiers trained on raw EEG data. These studies have provided global insight into the frequency bands that are generally important to a classifier but do not provide local insight into the frequency bands important for the classification of individual samples. This local explainability could be particularly helpful for EEG analysis domains like sleep stage classification that feature multiple evolving states. We present a novel local spectral explainability approach and use it to explain a convolutional neural network trained for automated sleep stage classification. We use our approach to show how the relative importance of different frequency bands varies over time and even within the same sleep stages. Furthermore, to better understand how our approach compares to existing methods, we compare a global estimate of spectral importance generated from our local results with an existing global spectral importance approach. We find that the δ band is most important for most sleep stages, though β is most important for the non-rapid eye movement 2 (NREM2) sleep stage. Additionally, θ is particularly important for identifying Awake and NREM1 samples. Our study represents the first approach developed for local spectral insight into deep learning classifiers trained on raw EEG time series.

Deep Learning

2009 ◽  
Author(s):  
Stellan Ohlsson
Keyword(s):  
Deep Learning

Shall I Move My Right or My Left Hand?

2003 ◽  
Vol 17 (2) ◽  
pp. 69-86 ◽  
Author(s):  
Claudio Babiloni ◽  
Fabio Babiloni ◽  
Filippo Carducci ◽  
Febo Cincotti ◽  
Claudio Del Percio ◽  
...  
Keyword(s):  
Bimanual Coordination ◽  
Central Area ◽  
Eeg Analysis ◽  
Complementary Information ◽  
Left Hand ◽  
Mirror Movements ◽  
Related Potentials ◽  
Motor Acts ◽  
Abstract Event

Abstract Event-related desynchronization/synchronization (ERD/ERS) at alpha (10Hz), beta (20Hz), and gamma (40Hz) bands and movement-related potentials (MRPs) were investigated in right-handed subjects who were “free” to decide the side of unilateral finger movements (“fixed” side as a control). As a novelty, this “multi-modal” EEG analysis was combined with the evaluation of involuntary mirror movements, taken as an index of “bimanual competition.” A main issue was whether the decision regarding the hand to be moved (“free” movements) could modulate ERD/ERS or MRPs overlying sensorimotor cortical areas typically involved in bimanual tasks. Compared to “fixed” movements, “free” movements induced the following effects: (1) more involuntary mirror movements discarded from EEG analysis; (2) stronger vertex MRPs (right motor acts); (3) a positive correlation between these potentials and the number of involuntary mirror movements; (4) gamma ERS over central areas; and (5) preponderance of postmovement beta ERS over left central area (dominant hemisphere). These results suggest that ERD/ERS and MRPs provide complementary information on the cortical processes belonging to a lateralized motor act. In this context, the results on vertex MRPs would indicate a key role of supplementary/cingulate motor areas not only for bimanual coordination but also for the control of “bimanual competition” and involuntary mirror movements.

Intelligence artificielle : le futur de l’Orthodontie ?

2019 ◽  
Vol 53 (3) ◽  
pp. 281-294
Author(s):  
Jean-Michel Foucart ◽  
Augustin Chavanne ◽  
Jérôme Bourriau
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Intelligence Artificielle ◽  
Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Sign in / Sign up

Export Citation Format

Share Document