EEG channel interpolation using ellipsoid geodesic length

Courellis, Hristos; Iversen, John R.; Poizner, Howard; Cauwenberghs, Gert

doi:10.1109/biocas.2016.7833851

Cited by 22 publications

(31 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bad channels were identified via visual inspection by two experts (S. C. and A. P.) following the exact same approach used by our team in previous EEG studies on semantic and motoric processes (Dottori et al, 2017(Dottori et al, , 2020Vilas et al, 2019;Yoris et al, 2017;García-Cordero et al, 2016;Melloni et al, 2015;Ibáñez et al, 2010Ibáñez et al, , 2013Aravena et al, 2010). Once identified, such channels were replaced with statistically weighted spherical interpolation (based on all sensors), and then the variance of the signal across trials was calculated to guarantee stability of the averaged waveform (Courellis, Iversen, Poizner, & Cauwenberghs, 2016). HD-EEG data were then segmented offline into 1.5-sec epochs extending from 500 msec prestimulus to 1000 msec poststimulus for stimulus-locked segments in N400 analyses (where Time 0 corresponds to stimulus onset) and for hand responselocked segments in MRCP analyses (where Time 0 corresponds to motor response execution).…”

Section: Hd-eeg Data Acquisition and Processingmentioning

confidence: 99%

The Neural Blending of Words and Movement: Event-Related Potential Signatures of Semantic and Action Processes during Motor–Language Coupling

Cervetto

Díaz-Rivera

Petroni

et al. 2021

Journal of Cognitive Neuroscience

View full text Add to dashboard Cite

Behavioral embodied research shows that words evoking limb-specific meanings can affect responses performed with the corresponding body part. However, no study has explored this phenomenon's neural dynamics under implicit processing conditions, let alone by disentangling its conceptual and motoric stages. Here, we examined whether the blending of hand actions and manual action verbs, relative to nonmanual action verbs and nonaction verbs, modulates electrophysiological markers of semantic integration (N400) and motor-related cortical potentials during a lexical decision task. Relative to both other categories, manual action verbs involved reduced posterior N400 amplitude and greater modulations of frontal motor-related cortical potentials. Such effects overlapped in a window of ∼380–440 msec after word presentation and ∼180 msec before response execution, revealing the possible time span in which both semantic and action-related stages reach maximal convergence. These results allow refining current models of motor–language coupling while affording new insights on embodied dynamics at large.

show abstract

Section: Hd-eeg Data Acquisition and Processingmentioning

confidence: 99%

The Neural Blending of Words and Movement: Event-Related Potential Signatures of Semantic and Action Processes during Motor–Language Coupling

Cervetto

Díaz-Rivera

Petroni

et al. 2021

Journal of Cognitive Neuroscience

View full text Add to dashboard Cite

show abstract

“…To the best of the author's knowledge, this is a standard assumption for EEG interpolation algorithms. For instance, Petrichella et al and Courellis et al calculate the interpolated values of the missing data at each time point separately ( 11 , 12 ). However, research on convolutional neural networks for EEG decoding and visualization have shown performance benefits from presenting the input as a column of electrodes unfolding in time, as this facilitates the learning of temporal modulations ( 50 ).…”

Section: Methodsmentioning

confidence: 99%

“…This problem is equivalent to the "frame-interpolation" task of filling in missing frames in a video (19). (11,12). However, research on convolutional neural networks for EEG decoding and visualization have shown performance benefits from presenting the input as a column of electrodes unfolding in time, as this facilitates the learning of temporal modulations (50).…”

Section: Artifact Correctionmentioning

confidence: 99%

“…Channel interpolation is the process of replacing the signal of a corrupted channel with one that is interpolated from surrounding clean channels. Patrichella et al demonstrated that knowing specific electrode locations (namely the exact electrode locations for each subject), and the distances between them can improve interpolation results ( 11 , 12 ). However, this type of additional information is rarely available and often requires special dedicated hardware.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised EEG Artifact Detection and Correction

Saba-Sadiya

Alhanai

Liu

et al. 2021

Front. Digit. Health

View full text Add to dashboard Cite

Electroencephalography (EEG) is used in the diagnosis, monitoring, and prognostication of many neurological ailments including seizure, coma, sleep disorders, brain injury, and behavioral abnormalities. One of the primary challenges of EEG data is its sensitivity to a breadth of non-stationary noises caused by physiological-, movement-, and equipment-related artifacts. Existing solutions to artifact detection are deficient because they require experts to manually explore and annotate data for artifact segments. Existing solutions to artifact correction or removal are deficient because they assume that the incidence and specific characteristics of artifacts are similar across both subjects and tasks (i.e., “one-size-fits-all”). In this paper, we describe a novel EEG noise-reduction method that uses representation learning to perform patient- and task-specific artifact detection and correction. More specifically, our method extracts 58 clinically relevant features and applies an ensemble of unsupervised outlier detection algorithms to identify EEG artifacts that are unique to a given task and subject. The artifact segments are then passed to a deep encoder-decoder network for unsupervised artifact correction. We compared the performance of classification models trained with and without our method and observed a 10% relative improvement in performance when using our approach. Our method provides a flexible end-to-end unsupervised framework that can be applied to novel EEG data without the need for expert supervision and can be used for a variety of clinical decision tasks, including coma prognostication and degenerative illness detection. By making our method, code, and data publicly available, our work provides a tool that is of both immediate practical utility and may also serve as an important foundation for future efforts in this domain.

show abstract

“…Within the last few years, alternative interpolation methods reporting improved performance have been proposed: Petrichella et al proposed a euclidean inverse distance method [12] while Courellis et al demonstrated an interpolation approach that (while also being based on an inverse distance calculation) used geodesic lengths and electrode localization to extract more exact channel locations, thereby performing more accurate interpolation. [13]. Effective interpolation is a necessary preliminary step to any subsequent preprocessing or formal analysis of the EEG, including Independent Component Analysis (ICA).…”

mentioning

confidence: 99%

EEG Channel Interpolation Using Deep Encoder-decoder Netwoks

Saba-Sadiya,

Alhanai,

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

Electrode "pop" artifacts originate from the spontaneous loss of connectivity between a surface and an electrode. Electroencephalography (EEG) uses a dense array of electrodes, hence popped segments are among the most pervasive type of artifact seen during the collection of EEG data. In many cases, the continuity of EEG data is critical for downstream applications (e.g. brain machine interface) and requires that popped segments be accurately interpolated. In this paper we frame the interpolation problem as a self-learning task using a deep encoder-decoder network. We compare our approach against contemporary interpolation methods on a publicly available EEG data set. Our approach exhibited a minimum of ∼ 15% improvement over contemporary approaches when tested on subjects and tasks not used during model training. We demonstrate how our model's performance can be enhanced further on novel subjects and tasks using transfer learning. All code and data associated with this study is open-source to enable ease of extension and practical use. To our knowledge, this work is the first solution to the EEG interpolation problem that uses deep learning. I. INTRODUCTIONElectroencephalography (EEG) devices have become increasingly popular in recent years and are used in a wide range of applications. Naturally, the medical applications of EEG are centered on neurological diagnosis, but EEG has proven useful for other problems in healthcare domain [1], [2]. Moreover, the use of EEG devices extends far beyond the medical domain; novel applications of EEG may be found in wide a variety of fields including advertising [3], education[4], entertainment [5], and security [6].A fundamental challenge of EEG data is the low signal to noise ratio. Different sources contribute to this noisiness but, in general, they can be categorized as either movement artifacts or electrode artifacts. The most common, and particularly persistent, electrode artifact is the electrode "pop" [7], [8]. These artifacts result from abrupt changes in impedance, usually due to a loose electrode or bad conductivity. Furthermore, these artifacts are difficult to avoid because, even if the greatest care is taken when applying electrodes, the most minor subject movement or change in perspiration can cause the electrode to "pop".A common solution to EEG "pops" is to interpolate the missing segments using recordings from nearby electrodes

show abstract

EEG channel interpolation using ellipsoid geodesic length

Cited by 22 publications

References 8 publications

The Neural Blending of Words and Movement: Event-Related Potential Signatures of Semantic and Action Processes during Motor–Language Coupling

The Neural Blending of Words and Movement: Event-Related Potential Signatures of Semantic and Action Processes during Motor–Language Coupling

Unsupervised EEG Artifact Detection and Correction

EEG Channel Interpolation Using Deep Encoder-decoder Netwoks

Contact Info

Product

Resources

About