214 papers with code • 3 benchmarks • 5 datasets
Electroencephalogram (EEG) is a method of recording brain activity using electrophysiological indexes. When the brain is active, a large number of postsynaptic potentials generated synchronously by neurons are formed after summation. It records the changes of electric waves during brain activity and is the overall reflection of the electrophysiological activities of brain nerve cells on the surface of cerebral cortex or scalp.  Brain waves originate from the postsynaptic potential of the apical dendrites of pyramidal cells. The formation of synchronous rhythm of EEG is also related to the activity of nonspecific projection system of cortex and thalamus. EEG is the basic theoretical research of brain science. EEG monitoring is widely used in its clinical application.
Partial warm restarts are also gaining popularity in gradient-based optimization to improve the rate of convergence in accelerated gradient schemes to deal with ill-conditioned functions.
One of the challenges in modeling cognitive events from electroencephalogram (EEG) data is finding representations that are invariant to inter- and intra-subject differences, as well as to inherent noise associated with such data.
We introduce the use of depthwise and separable convolutions to construct an EEG-specific model which encapsulates well-known EEG feature extraction concepts for BCI.
This demonstrated that, without changing the model architecture and the training algorithm, our model could automatically learn features for sleep stage scoring from different raw single-channel EEGs from different datasets without utilizing any hand-engineered features.
PLEASE READ AND CITE THE REVISED VERSION at Human Brain Mapping: http://onlinelibrary. wiley. com/doi/10. 1002/hbm. 23730/full Code available here: https://github. com/robintibor/braindecode
We propose U-Time, a fully feed-forward deep learning approach to physiological time series segmentation developed for the analysis of sleep data.
Near-sensor data analytics is a promising direction for IoT endpoints, as it minimizes energy spent on communication and reduces network load - but it also poses security concerns, as valuable data is stored or sent over the network at various stages of the analytics pipeline.
Brain-computer interfaces (BCIs) have been gaining momentum in making human-computer interaction more natural, especially for people with neuro-muscular disabilities.
We introduce coroICA, confounding-robust independent component analysis, a novel ICA algorithm which decomposes linearly mixed multivariate observations into independent components that are corrupted (and rendered dependent) by hidden group-wise stationary confounding.
To help the field progress, we provide a list of recommendations for future studies and we make our summary table of DL and EEG papers available and invite the community to contribute.