1,721,021 research outputs found
The Sensory-Cognitive Interplay: Insights into Neural Mechanisms and Circuits
Full text linkSenses are our interface for acting in the external
world. Consequently, sensory-motor information grounds
and drives our higher cognitive processes. At the same
time, we are impinged by a multitude of sensory inputs with
variable saliency. It is therefore crucial that the process-
ing of sensory inputs and motor signals is modulated by
cognitive and executive mechanisms such as expectation,
memory, attention, emotion, planning, monitoring. This is
needed to highlight sensory information that is currently rel-
evant for task goals, and to adapt motor control and behav-
ior accordingly. The strict intertwining of sensory, motor,
and cognitive functions is evidenced in aging and in neuro-
logical disorders. Indeed, sensory-motor dysfunctions of-
ten accompany higher-level dysfunctions in older popula-
tions [1] and in neurological subjects (e.g., in dyslexia, at-
tention deficit hyperactivity disorders, or autism spectrum
disorders) [2,3] [...
Deep learning-based EEG analysis: investigating P3 ERP components
Full text linkThe neural processing of incoming stimuli can be analysed from the electroencephalogram (EEG) through event-related potentials (ERPs). The P3 component is largely investigated as it represents an important psychophysiological marker of psychiatric disorders. This is composed by several subcomponents, such as P3a and P3b, reflecting distinct but interrelated sensory and cognitive processes of incoming stimuli. Due to the low EEG signal-to-noise-ratio, ERPs emerge only after an averaging procedure across trials and subjects. Thus, this canonical ERP analysis lacks in the ability to highlight EEG neural signatures at the level of single-subject and single-trial. In this study, a deep learning-based workflow is investigated to enhance EEG neural signatures related to P3 subcomponents already at single-subject and at single-trial level. This was based on the combination of a convolutional neural network (CNN) with an explanation technique (ET). The CNN was trained using two different strategies to produce saliency representations enhancing signatures shared across subjects or more specific for each subject and trial. Cross-subject saliency representations matched the signatures already emerging from ERPs, i.e., P3a and P3b-related activity within 350–400 ms (frontal sites) and 400–650 ms (parietal sites) post-stimulus, validating the CNN+ET respect to canonical ERP analysis. Single-subject and single-trial saliency representations enhanced P3 signatures already at the single-trial scale, while EEG-derived representations at single-subject and single-trial level provided no or only mildly evident signatures. Empowering the analysis of P3 modulations at single-subject and at single-trial level, CNN+ET could be useful to provide insights about neural processes linking sensory stimulation, cognition and behaviour
Interpretable and lightweight convolutional neural network for EEG decoding: Application to movement execution and imagination
Full text linkConvolutional neural networks (CNNs) are emerging as powerful tools for EEG decoding: these techniques, by automatically learning relevant features for class discrimination, improve EEG decoding performances without relying on handcrafted features. Nevertheless, the learned features are difficult to interpret and most of the existing CNNs introduce many trainable parameters. Here, we propose a lightweight and interpretable shallow CNN (Sinc-ShallowNet), by stacking a temporal sinc-convolutional layer (designed to learn band-pass filters, each having only the two cut-off frequencies as trainable parameters), a spatial depthwise convolutional layer (reducing channel connectivity and learning spatial filters tied to each band-pass filter), and a fully-connected layer finalizing the classification. This convolutional module limits the number of trainable parameters and allows direct interpretation of the learned spectral–spatial features via simple kernel visualizations. Furthermore, we designed a post-hoc gradient-based technique to enhance interpretation by identifying the more relevant and more class-specific features. Sinc-ShallowNet was evaluated on benchmark motor-execution and motor-imagery datasets and against different design choices and training strategies. Results show that (i) Sinc-ShallowNet outperformed a traditional machine learning algorithm and other CNNs for EEG decoding; (ii) The learned spectral–spatial features matched well-known EEG motor-related activity; (iii) The proposed architecture performed better with a larger number of temporal kernels still maintaining a good compromise between accuracy and parsimony, and with a trialwise rather than a cropped training strategy. In perspective, the proposed approach, with its interpretative capacity, can be exploited to investigate cognitive/motor aspects whose EEG correlates are yet scarcely known, potentially characterizing their relevant features
A Dual-Branched Convolutional Neural Network for P300 detection and feature interpretation
No full textModulation of EEG Theta and Alpha Power by an Internal Attention Task with and Without Visual Distractors
No full textAttention to internal representations is crucial in tasks involving temporary storage and mental manipulation of information (working memory tasks), to suppress concurrent interfering processes, such as sensory-intake processes. Theta activity (4–8 Hz), especially frontal, has been extensively associated to working memory tasks, increasing with task complexity and error monitoring. Alpha rhythm (8–14 Hz) has been hypothesized to enhance processes within the attentional focus via inhibition of task-irrelevant regions (alpha increase) and engagement of task-relevant regions (alpha decrease). Here, we provide further contribution to the investigation of alpha and theta activity by computing electroencephalographic (EEG) alpha and theta power from 10 participants who performed a resting phase (no attention) and a mental arithmetic task (internal attention), under two different visual conditions i.e., pictures and no picture presentation. Pictures stimulated external attention and acted as distractors during the math task but not during rest. Results show that frontal theta power increased during the math task vs rest, more largely in presence of visual distractors. Posterior alpha power increased in the math task vs rest in picture condition, but not in the no picture condition; moreover, it decreased in the picture vs no picture condition during rest but not during the math task. These results support frontal theta as a mechanism implementing cortical control in complex tasks and indicate that EEG alpha power reflects a sophisticate balance between increase in some regions and decrease in other regions, depending on the current goal and external context
Alpha and theta mechanisms operating in internal-external attention competition
Full text linkAttention is the ability to prioritize a set of information at expense of others and can be internally- or externally-oriented. Alpha and theta oscillations have been extensively implicated in attention. However, it is unclear how these oscillations operate when sensory distractors are presented continuously during task-relevant internal processes, in close-to-real-life conditions. Here, EEG signals from healthy participants were obtained at rest and in three attentional conditions, characterized by the execution of a mental math task (internal attention), presentation of pictures on a monitor (external attention), and task execution under the distracting action of picture presentation (internal-external competition). Alpha and theta power were investigated at scalp level and at some cortical regions of interest (ROIs); moreover, functional directed connectivity was estimated via spectral Granger Causality. Results show that frontal midline theta was distinctive of mental task execution and was more prominent during competition compared to internal attention alone, possibly reflecting higher executive control; anterior cingulate cortex appeared as mainly involved and causally connected to distant (temporal/ occipital) regions. Alpha power in visual ROIs strongly decreased in external attention alone, while it assumed values close to rest during competition, reflecting reduced visual engagement against distractors; connectivity results suggested that bidirectional alpha influences between frontal and visual regions could contribute to reduce visual interference in internal attention. This study can help to understand how our brain copes with internal-external attention competition, a condition intrinsic in the human sensory-cognitive interplay, and to elucidate the relationships between brain oscillations and attentional functions/dysfunctions in daily tasks
A Lightweight Multi-Scale Convolutional Neural Network for P300 Decoding: Analysis of Training Strategies and Uncovering of Network Decision
Full text linkConvolutional neural networks (CNNs), which automatically learn features from raw data to approximate functions, are being increasingly applied to the end-to-end analysis of electroencephalographic (EEG) signals, especially for decoding brain states in brain-computer interfaces (BCIs). Nevertheless, CNNs introduce a large number of trainable parameters, may require long training times, and lack in interpretability of learned features. The aim of this study is to propose a CNN design for P300 decoding with emphasis on its lightweight design while guaranteeing high performance, on the effects of different training strategies, and on the use of post-hoc techniques to explain network decisions. The proposed design, named MS-EEGNet, learned temporal features in two different timescales (i.e., multi-scale, MS) in an efficient and optimized (in terms of trainable parameters) way, and was validated on three P300 datasets. The CNN was trained using different strategies (within-participant and within-session, within-participant and cross-session, leave-one-subject-out, transfer learning) and was compared with several state-of-the-art (SOA) algorithms. Furthermore, variants of the baseline MS-EEGNet were analyzed to evaluate the impact of different hyper-parameters on performance. Lastly, saliency maps were used to derive representations of the relevant spatio-temporal features that drove CNN decisions. MS-EEGNet was the lightest CNN compared with the tested SOA CNNs, despite its multiple timescales, and significantly outperformed the SOA algorithms. Post-hoc hyper-parameter analysis confirmed the benefits of the innovative aspects of MS-EEGNet. Furthermore, MS-EEGNet did benefit from transfer learning, especially using a low number of training examples, suggesting that the proposed approach could be used in BCIs to accurately decode the P300 event while reducing calibration times. Representations derived from the saliency maps matched the P300 spatio-temporal distribution, further validating the proposed decoding approach. This study, by specifically addressing the aspects of lightweight design, transfer learning, and interpretability, can contribute to advance the development of deep learning algorithms for P300-based BCIs
Convolutional Neural Network for a P300 Brain-Computer Interface to Improve Social Attention in Autistic Spectrum Disorder
No full textA Brain-Computer Interface (BCI) relies on machine learning algorithms to decode the brain signals. An accurate detection of P300 response in electroencephalography (EEG) data can be used to design P300-based BCIs to improve social attention in Autistic Spectrum Disorder (ASD). Recently, there was a growing interest in the application of Convolutional Neural Networks (CNNs) to decode P300 in an end-to-end fashion. However, the complexity of these models needs to be carefully taken into account. In this study, a lightweight CNN previously validated for P300 detection (EEGNet) was used to decode which object ASD participants were paying attention to in a virtual environment. Two learning strategies were deepened: within-session and cross-session trainings. Cross-session training resulted in a higher target object accuracy scoring 92.27% on average across sessions and subjects, and in a lower decoding variability across sessions
Modulation of brain alpha rhythm and heart rate variability by attention-related mechanisms
Full text linkAccording to recent evidence, oscillations in the alpha-band (8-14 Hz) play an active role in attention via allocation of cortical resources: decrease in alpha activity enhances neural processes in task-relevant regions, while increase in alpha activity reduces processing in task-irrelevant regions. Here, we analyzed changes in alpha-band power of 13-channel electroencephalogram (EEG) acquired from 30 subjects while performing four tasks that differently engaged visual, computational and motor attentional components. The complete (visual + computational + motor) task required to read and solve an arithmetical operation and provide a motor response; three simplified tasks involved a subset of these components (visual + computational task, visual task, motor task). Taskrelated changes in alpha power were quantified by aggregating electrodes into two main regions (fronto-central and parieto-occipital), to test regional specificity of alpha modulation depending on the involved attentional aspects. Independent Component Analysis (ICA) was applied to discover the main independent processes accounting for alpha power over the two scalp regions. Furthermore, we performed analysis of Heart Rate Variability (HRV) from one electrocardiogram signal acquired simultaneously with EEG, to test autonomic reaction to attentional loads. Results showed that alpha power modulation over the two scalp regions not only reflected the number of involved attentional components (the larger their number the larger the alpha power suppression) but was also fine-tuned by the nature of the recruited mechanisms (visual, computational, motor) relative to the functional specification of the regions. ICA revealed topologically dissimilar and differently attention-regulated processes of alpha power over the two regions. HRV indexes were less sensitive to different attentional aspects compared to alpha power, with vagal activity index presenting larger changes. This study contributes to improve our understanding of the electroencephalographic and autonomic correlates of attention and may have practical implications in neurofeedback, brain-computer interfaces, neuroergonomics as well as in clinical practice and neuroscience research exploring attention-deficit disorders
Transfer Entropy as a Measure of Brain Connectivity: A Critical Analysis With the Help of Neural Mass Models
Full text linkObjective: Assessing brain connectivity from electrophysiological signals is of great relevance in neuroscience, but results are still debated and depend crucially on how connectivity is defined and on mathematical instruments utilized. Aim of this work is to assess the capacity of bivariate Transfer Entropy (TE) to evaluate connectivity, using data generated from simple neural mass models of connected Regions of Interest (ROIs). Approach: Signals simulating mean field potentials were generated assuming two, three or four ROIs, connected via excitatory or by-synaptic inhibitory links. We investigated whether the presence of a statistically significant connection can be detected and if connection strength can be quantified. Main Results: Results suggest that TE can reliably estimate the strength of connectivity if neural populations work in their linear regions, and if the epoch lengths are longer than 10 s. In case of multivariate networks, some spurious connections can emerge (i.e., a statistically significant TE even in the absence of a true connection); however, quite a good correlation between TE and synaptic strength is still preserved. Moreover, TE appears more robust for distal regions (longer delays) compared with proximal regions (smaller delays): an approximate a priori knowledge on this delay can improve the procedure. Finally, non-linear phenomena affect the assessment of connectivity, since they may significantly reduce TE estimation: information transmission between two ROIs may be weak, due to non-linear phenomena, even if a strong causal connection is present. Significance: Changes in functional connectivity during different tasks or brain conditions, might not always reflect a true change in the connecting network, but rather a change in information transmission. A limitation of the work is the use of bivariate TE. In perspective, the use of multivariate TE can improve estimation and reduce some of the problems encountered in the present study
- …
