scholarly journals Time-adaptive Unsupervised Auditory Attention Decoding Using EEG-based Stimulus Reconstruction

2022 ◽  
Author(s):  
Simon Geirnaert ◽  
Tom Francart ◽  
Alexander Bertrand
Keyword(s):  
Performance Metrics ◽  
Brain Activity ◽  
Training Session ◽  
Ground Truth ◽  
Auditory Attention ◽  
Reconstruction Method ◽  
Fundamental Building Block ◽  
Hearing Devices ◽  
Stimulus Reconstruction ◽  
The Brain

The goal of auditory attention decoding (AAD) is to determine to which speaker out of multiple competing speakers a listener is attending based on the brain signals recorded via, e.g., electroencephalography (EEG). AAD algorithms are a fundamental building block of so-called neuro-steered hearing devices that would allow identifying the speaker that should be amplified based on the brain activity. A common approach is to train a subject-specific decoder that reconstructs the amplitude envelope of the attended speech signal. However, training this decoder requires a dedicated 'ground-truth' EEG recording of the subject under test, during which the attended speaker is known. Furthermore, this decoder remains fixed during operation and can thus not adapt to changing conditions and situations. Therefore, we propose an online time-adaptive unsupervised stimulus reconstruction method that continuously and automatically adapts over time when new EEG and audio data are streaming in. The adaptive decoder does not require ground-truth attention labels obtained from a training session with the end-user, and instead can be initialized with a generic subject-independent decoder or even completely random values. We propose two different implementations: a sliding window and recursive implementation, which we extensively validate based on multiple performance metrics on three independent datasets. We show that the proposed time-adaptive unsupervised decoder outperforms a time-invariant supervised decoder, representing an important step towards practically applicable AAD algorithms for neuro-steered hearing devices.

scholarly journals Single-trial neural dynamics influence auditory category learning

2020 ◽  
Author(s):  
Kelsey Mankel ◽  
Philip I. Pavlik ◽  
Gavin M. Bidelman
Keyword(s):  
Computational Modeling ◽  
Category Learning ◽  
Brain Activity ◽  
Educational Data Mining ◽  
Training Session ◽  
Performance Model ◽  
Learning Performance ◽  
Single Trial ◽  
Brain Behavior ◽  
The Brain

AbstractPercepts are naturally grouped into meaningful categories to process continuous stimulus variations in the environment. Theories of category acquisition have existed for decades, but how they arise in the brain due to learning is not well understood. Here, advanced computational modeling techniques borrowed from educational data mining and cognitive psychology were used to trace the development of auditory categories within a short-term training session. Nonmusicians were rapidly trained for 20 min on musical interval identification (i.e., minor and major 3rd interval dyads) while their brain activity was recorded via EEG. Categorization performance and neural responses were then assessed for the trained (3rds) and novel untrained (major/minor 6ths) continua. Computational modeling was used to predict behavioral identification responses and whether the inclusion of single-trial features of the neural data could predict successful learning performance. Model results revealed meaningful brain-behavior relationships in auditory category learning detectible on the single-trial level; smaller P2 amplitudes were associated with a greater probability of correct interval categorization after learning. These findings highlight the nuanced dynamics of brain-behavior coupling that help explain the temporal emergence of auditory categorical learning in the brain.

scholarly journals Analysis of Performance Metrics Using Emotiv EPOC+

2018 ◽  
Vol 210 ◽  
pp. 04046 ◽  
Author(s):  
Martin Strmiska ◽  
Zuzana Koudelkova
Keyword(s):  
Human Brain ◽  
Performance Metrics ◽  
Brain Activity ◽  
Brain Computer Interface ◽  
Real Life ◽  
Computer Interface ◽  
Medical Field ◽  
Precise Tool ◽  
Analysis Of Performance ◽  
The Brain

Brain-computer interface (BCI) is a device that enables the connection between the human brain and a computer, therefore, it allows us to observe the brain activity. The goal of this article is to prove that brain-computer interface is a helpful and quite precise tool. This goal will be achieved by presenting various examples from real-life situations. The results show that this device is indeed helpful, e.g. in a medical field, however, it is not commonly used in hospitals.

scholarly journals Fast EEG-based decoding of the directional focus of auditory attention using common spatial patterns

2020 ◽  
Author(s):  
Simon Geirnaert ◽  
Tom Francart ◽  
Alexander Bertrand
Keyword(s):  
High Accuracy ◽  
Auditory Attention ◽  
Multiple Sources ◽  
Common Spatial Pattern ◽  
Major Step ◽  
Neural Network Approach ◽  
Hearing Devices ◽  
Stimulus Reconstruction ◽  
The Individual ◽  
Short Signal

AbstractObjectiveNoise reduction algorithms in current hearing devices lack information about the sound source a user attends to when multiple sources are present. To resolve this issue, they can be complemented with auditory attention decoding (AAD) algorithms, which decode the attention using electroencephalography (EEG) sensors. State-of-the-art AAD algorithms employ a stimulus reconstruction approach, in which the envelope of the attended source is reconstructed from the EEG and correlated with the envelopes of the individual sources. This approach, however, performs poorly on short signal segments, while longer segments yield impractically long detection delays when the user switches attention.MethodsWe propose decoding the directional focus of attention using filterbank common spatial pattern filters (FB-CSP) as an alternative AAD paradigm, which does not require access to the clean source envelopes.ResultsThe proposed FB-CSP approach outperforms both the stimulus reconstruction approach on short signal segments, as well as a convolutional neural network approach on the same task. We achieve a high accuracy (80% for 1 s windows and 70% for quasi-instantaneous decisions), which is sufficient to reach minimal expected switch durations below 4 s. We also demonstrate that the decoder can adapt to unlabeled data from an unseen subject and works with only a subset of EEG channels located around the ear to emulate a wearable EEG setup.ConclusionThe proposed FB-CSP method provides fast and accurate decoding of the directional focus of auditory attention.SignificanceThe high accuracy on very short data segments is a major step forward towards practical neuro-steered hearing devices.

Complexity Measures of Brain Electrophysiological Activity

2010 ◽  
Vol 24 (2) ◽  
pp. 131-135 ◽  
Author(s):  
Włodzimierz Klonowski ◽  
Pawel Stepien ◽  
Robert Stepien
Keyword(s):  
Brain Activity ◽  
Deterministic Chaos ◽  
Epileptic Seizures ◽  
Eeg Signal ◽  
Eeg Signals ◽  
Complexity Measures ◽  
Electrophysiological Activity ◽  
Signal Complexity ◽  
Physiological Sleep ◽  
The Brain

Over 20 years ago, Watt and Hameroff (1987 ) suggested that consciousness may be described as a manifestation of deterministic chaos in the brain/mind. To analyze EEG-signal complexity, we used Higuchi’s fractal dimension in time domain and symbolic analysis methods. Our results of analysis of EEG-signals under anesthesia, during physiological sleep, and during epileptic seizures lead to a conclusion similar to that of Watt and Hameroff: Brain activity, measured by complexity of the EEG-signal, diminishes (becomes less chaotic) when consciousness is being “switched off”. So, consciousness may be described as a manifestation of deterministic chaos in the brain/mind.

Relation Between Level of Prefrontal Activity and Subject's Performance

1999 ◽  
Vol 13 (2) ◽  
pp. 117-125 ◽  
Author(s):  
Laurence Casini ◽  
Françoise Macar ◽  
Marie-Hélène Giard
Keyword(s):  
Brain Activity ◽  
Sensory Information ◽  
Practice Phase ◽  
Trained Subjects ◽  
Anagram Task ◽  
Economic Information ◽  
Long Duration ◽  
Level Of Activity ◽  
The Brain ◽  
Processing Mechanism

Abstract The experiment reported here was aimed at determining whether the level of brain activity can be related to performance in trained subjects. Two tasks were compared: a temporal and a linguistic task. An array of four letters appeared on a screen. In the temporal task, subjects had to decide whether the letters remained on the screen for a short or a long duration as learned in a practice phase. In the linguistic task, they had to determine whether the four letters could form a word or not (anagram task). These tasks allowed us to compare the level of brain activity obtained in correct and incorrect responses. The current density measures recorded over prefrontal areas showed a relationship between the performance and the level of activity in the temporal task only. The level of activity obtained with correct responses was lower than that obtained with incorrect responses. This suggests that a good temporal performance could be the result of an efficacious, but economic, information-processing mechanism in the brain. In addition, the absence of this relation in the anagram task results in the question of whether this relation is specific to the processing of sensory information only.

Brain FDG PET for the Etiological Diagnosis of Clinically Uncertain Cognitive Impairment During Delirium in Remission

2020 ◽  
Vol 77 (4) ◽  
pp. 1609-1622
Author(s):  
Franziska Mathies ◽  
Catharina Lange ◽  
Anja Mäurer ◽  
Ivayla Apostolova ◽  
Susanne Klutmann ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Fdg Pet ◽  
False Negative ◽  
Ground Truth ◽  
Etiological Diagnosis ◽  
Geriatric Unit ◽  
Positron Emission ◽  
The Brain ◽  
Hospitalized Geriatric Patients

Background: Positron emission tomography (PET) of the brain with 2-[F-18]-fluoro-2-deoxy-D-glucose (FDG) is widely used for the etiological diagnosis of clinically uncertain cognitive impairment (CUCI). Acute full-blown delirium can cause reversible alterations of FDG uptake that mimic neurodegenerative disease. Objective: This study tested whether delirium in remission affects the performance of FDG PET for differentiation between neurodegenerative and non-neurodegenerative etiology of CUCI. Methods: The study included 88 patients (82.0±5.7 y) with newly detected CUCI during hospitalization in a geriatric unit. Twenty-seven (31%) of the patients were diagnosed with delirium during their current hospital stay, which, however, at time of enrollment was in remission so that delirium was not considered the primary cause of the CUCI. Cases were categorized as neurodegenerative or non-neurodegenerative etiology based on visual inspection of FDG PET. The diagnosis at clinical follow-up after ≥12 months served as ground truth to evaluate the diagnostic performance of FDG PET. Results: FDG PET was categorized as neurodegenerative in 51 (58%) of the patients. Follow-up after 16±3 months was obtained in 68 (77%) of the patients. The clinical follow-up diagnosis confirmed the FDG PET-based categorization in 60 patients (88%, 4 false negative and 4 false positive cases with respect to detection of neurodegeneration). The fraction of correct PET-based categorization did not differ between patients with delirium in remission and patients without delirium (86% versus 89%, p = 0.666). Conclusion: Brain FDG PET is useful for the etiological diagnosis of CUCI in hospitalized geriatric patients, as well as in patients with delirium in remission.

Classification of methods for generating pseudo-CT from MRI images for MRI-alone RT

2017 ◽  
Vol 1 (3) ◽  
pp. 54
Author(s):  
BOUKELLOUZ Wafa ◽  
MOUSSAOUI Abdelouahab
Keyword(s):  
Performance Metrics ◽  
Radiation Treatment ◽  
Hybrid Methods ◽  
Dose Calculation ◽  
Absolute Error ◽  
Ct Images ◽  
General Technique ◽  
Therapy Field ◽  
The Brain

Background: Since the last decades, research have been oriented towards an MRI-alone radiation treatment planning (RTP), where MRI is used as the primary modality for imaging, delineation and dose calculation by assigning to it the needed electron density (ED) information. The idea is to create a computed tomography (CT) image or so-called pseudo-CT from MRI data. In this paper, we review and classify methods for creating pseudo-CT images from MRI data. Each class of methods is explained and a group of works in the literature is presented in detail with statistical performance. We discuss the advantages, drawbacks and limitations of each class of methods. Methods: We classified most recent works in deriving a pseudo-CT from MR images into four classes: segmentation-based, intensity-based, atlas-based and hybrid methods. We based the classification on the general technique applied in the approach. Results: Most of research focused on the brain and the pelvis regions. The mean absolute error (MAE) ranged from 80 HU to 137 HU and from 36.4 HU to 74 HU for the brain and pelvis, respectively. In addition, an interest in the Dixon MR sequence is increasing since it has the advantage of producing multiple contrast images with a single acquisition. Conclusion: Radiation therapy field is emerging towards the generalization of MRI-only RT thanks to the advances in techniques for generation of pseudo-CT images. However, a benchmark is needed to set in common performance metrics to assess the quality of the generated pseudo-CT and judge on the efficiency of a certain method.

Automated System for Epileptic Seizures Prediction based on Multi-Channel Recordings of Electrical Brain Activity

2018 ◽  
pp. 115-122 ◽  
Author(s):  
V. A. Maksimenko ◽  
A. A. Harchenko ◽  
A. Lüttjohann
Keyword(s):  
Epileptic Seizure ◽  
Brain Activity ◽  
Epileptic Seizures ◽  
Automated System ◽  
Brain Computer Interfaces ◽  
Electrical Brain Activity ◽  
Computer Interfaces ◽  
Prediction And Prevention ◽  
The Brain

Introduction: Now the great interest in studying the brain activity based on detection of oscillatory patterns on the recorded data of electrical neuronal activity (electroencephalograms) is associated with the possibility of developing brain-computer interfaces. Braincomputer interfaces are based on the real-time detection of characteristic patterns on electroencephalograms and their transformation  into commands for controlling external devices. One of the important areas of the brain-computer interfaces application is the control of the pathological activity of the brain. This is in demand for epilepsy patients, who do not respond to drug treatment.Purpose: A technique for detecting the characteristic patterns of neural activity preceding the occurrence of epileptic seizures.Results:Using multi-channel electroencephalograms, we consider the dynamics of thalamo-cortical brain network, preceded the occurrence of an epileptic seizure. We have developed technique which allows to predict the occurrence of an epileptic seizure. The technique has been implemented in a brain-computer interface, which has been tested in-vivo on the animal model of absence epilepsy.Practical relevance:The results of our study demonstrate the possibility of epileptic seizures prediction based on multichannel electroencephalograms. The obtained results can be used in the development of neurointerfaces for the prediction and prevention of seizures of various types of epilepsy in humans. 

scholarly journals Siamese Reconstruction Network: Accurate Image Reconstruction from Human Brain Activity by Learning to Compare

2019 ◽  
Vol 9 (22) ◽  
pp. 4749
Author(s):  
Lingyun Jiang ◽  
Kai Qiao ◽  
Linyuan Wang ◽  
Chi Zhang ◽  
Jian Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Human Brain ◽  
Brain Activity ◽  
Feature Space ◽  
Training Data ◽  
Reconstruction Method ◽  
Learning Method ◽  
Training Samples ◽  
Visual Reconstruction ◽  
Relationship Of

Decoding human brain activities, especially reconstructing human visual stimuli via functional magnetic resonance imaging (fMRI), has gained increasing attention in recent years. However, the high dimensionality and small quantity of fMRI data impose restrictions on satisfactory reconstruction, especially for the reconstruction method with deep learning requiring huge amounts of labelled samples. When compared with the deep learning method, humans can recognize a new image because our human visual system is naturally capable of extracting features from any object and comparing them. Inspired by this visual mechanism, we introduced the mechanism of comparison into deep learning method to realize better visual reconstruction by making full use of each sample and the relationship of the sample pair by learning to compare. In this way, we proposed a Siamese reconstruction network (SRN) method. By using the SRN, we improved upon the satisfying results on two fMRI recording datasets, providing 72.5% accuracy on the digit dataset and 44.6% accuracy on the character dataset. Essentially, this manner can increase the training data about from n samples to 2n sample pairs, which takes full advantage of the limited quantity of training samples. The SRN learns to converge sample pairs of the same class or disperse sample pairs of different class in feature space.

Sign in / Sign up

Export Citation Format

Share Document