Neuroscience › Cognitive Neuroscience

EEG and Brain-Computer Interfaces

Works Count: 133848

Wikipedia

Description

This cluster of papers focuses on the development and application of Brain-Computer Interfaces (BCIs) in neuroscience and medicine. It covers topics such as EEG analysis, neuroprosthetics, BCI technology, motor imagery, epilepsy detection, cortical control, neural ensemble physiology, BCI communication, and deep learning for EEG decoding.

Keywords

Brain-Computer Interfaces; EEG Analysis; Neuroprosthetics; BCI Technology; Motor Imagery; Epilepsy Detection; Cortical Control; Neural Ensemble Physiology; BCI Communication; Deep Learning for EEG

Neuro-dynamic Programming

2012-01-01

Dimitri P. Bertsekas , John N. Tsitsiklis

Investigating Critical Frequency Bands and Channels for EEG-Based Emotion Recognition with Deep Neural Networks

2015-05-08

Wei‐Long Zheng , Bao‐Liang Lu

To investigate critical frequency bands and channels, this paper introduces deep belief networks (DBNs) to constructing EEG-based emotion recognition models for three emotions: positive, neutral and negative. We develop an … To investigate critical frequency bands and channels, this paper introduces deep belief networks (DBNs) to constructing EEG-based emotion recognition models for three emotions: positive, neutral and negative. We develop an EEG dataset acquired from 15 subjects. Each subject performs the experiments twice at the interval of a few days. DBNs are trained with differential entropy features extracted from multichannel EEG data. We examine the weights of the trained DBNs and investigate the critical frequency bands and channels. Four different profiles of 4, 6, 9, and 12 channels are selected. The recognition accuracies of these four profiles are relatively stable with the best accuracy of 86.65%, which is even better than that of the original 62 channels. The critical frequency bands and channels determined by using the weights of trained DBNs are consistent with the existing observations. In addition, our experiment results show that neural signatures associated with different emotions do exist and they share commonality across sessions and individuals. We compare the performance of deep models with shallow models. The average accuracies of DBN, SVM, LR, and KNN are 86.08%, 83.99%, 82.70%, and 72.60%, respectively.

Contingent Negative Variation : An Electric Sign of Sensori-Motor Association and Expectancy in the Human Brain

1964-07-01

W. Grey Walter , R. Cooper , V.J. Aldridge +2 more

Hirnpotential�nderungen bei Willk�rbewegungen und passiven Bewegungen des Menschen: Bereitschaftspotential und reafferente Potentiale

1965-01-01

H. H. Kornhuber , L�der Deecke

Unconscious cerebral initiative and the role of conscious will in voluntary action

1985-12-01

Benjamin Libet

Abstract Voluntary acts are preceded by electrophysiological “readiness potentials” (RPs). With spontaneous acts involving no preplanning, the main negative RP shift begins at about—550 ms. Such RPs were used to … Abstract Voluntary acts are preceded by electrophysiological “readiness potentials” (RPs). With spontaneous acts involving no preplanning, the main negative RP shift begins at about—550 ms. Such RPs were used to indicate the minimum onset times for the cerebral activity that precedes a fully endogenous voluntary act. The time of conscious intention to act was obtained from the subject's recall of the spatial clock position of a revolving spot at the time of his initial awareness of intending or wanting to move (W). W occurred at about—200 ms. Control experiments, in which a skin stimulus was timed (S), helped evaluate each subject's error in reporting the clock times for awareness of any perceived event. For spontaneous voluntary acts, RP onset preceded the uncorrected Ws by about 350 ms and the Ws corrected for S by about 400 ms. The direction of this difference was consistent and significant throughout, regardless of which of several measures of RP onset or W were used. It was concluded that cerebral initiation of a spontaneous voluntary act begins unconsciously. However, it was found that the final decision to act could still be consciously controlled during the 150 ms or so remaining after the specific conscious intention appears. Subjects can in fact “veto” motor performance during a 100–200-ms period before a prearranged time to act. The role of conscious will would be not to initiate a specific voluntary act but rather to select and control volitional outcome. It is proposed that conscious will can function in a permissive fashion, either to permit or to prevent the motor implementation of the intention to act that arises unconsciously. Alternatively, there may be the need for a conscious activation or triggering, without which the final motor output would not follow the unconscious cerebral initiating and preparatory processes.

Publication Recommendations for Electrodermal Measurements

1981-05-01

Don C. Fowles , Margaret J. Christie , Robert Edelberg +3 more

ABSTRACT The paper recommends an acceptable methodology for recording electrodermal activity which reflects a consensus of experts in the field. These recommendations are presented with a minimum of technical discussion … ABSTRACT The paper recommends an acceptable methodology for recording electrodermal activity which reflects a consensus of experts in the field. These recommendations are presented with a minimum of technical discussion in order to maximize their usefulness to investigators who are not specialists in this area. For most purposes, skin conductance (SC) is to be preferred over skin potential (SP). It is recommended that SC be recorded from palmar sites with silver‐silver chloride electrodes and an electrode paste consisting of a sodium chloride electrolyte in a neutral ointment cream medium. The area of contact with the skin should be controlled and time allowed for stabilization of the skin‐electrode paste interface. Electrode bias potentials and polarization should be monitored during use. Signal conditioning is achieved by the application of a constant 0.5 volt across the electrodes and measurement of the resultant current flow by amplifying the voltage developed across a small resistor in series with the skin. The measurement of the amplitude‐or even the detection‐of small responses requires some form of tonic level control, permitting an adjustment of the tonic level. A circuit is provided for signal conditioning and tonic level control. SP can be recorded with the same electrodes and electrode paste, unless the results are to be related to the British work on SP level, in which case the original potassium chloride electrolyte in an agar medium should be used. SP recordings require that one of the electrodes be placed over an inactive reference site, preferably over the ulnar bone near the elbow. No external voltage is applied, but some form of tonic level control may be needed. Electrodes need to be checked for bias potentials but not polarization.

View PDF Chat

Controlled and automatic human information processing: I. Detection, search, and attention.

1977-01-01

Walter Schneider , Richard M. Shiffrin

NON-INVASIVE MAGNETIC STIMULATION OF HUMAN MOTOR CORTEX

1985-05-01

A.T. Barker , Reza Jalinous , I.L. Freeston

Electric Fields of the Brain: The Neurophysics of EEG

1982-04-02

Joseph Fermaglich

Computer technology is widely used to process biomedical information. Indeed, electrodiagnostic studies of heart, nervous system, and blood flow as well as radiographic procedures are dependent on computer assistance. Clinical … Computer technology is widely used to process biomedical information. Indeed, electrodiagnostic studies of heart, nervous system, and blood flow as well as radiographic procedures are dependent on computer assistance. Clinical electroencephalography, by contrast, remains largely a test, the interpretation of which must be done the old-fashioned way—by people. In their book the authors present mathematical, physical, physiological, engineering, and medical facts in an effort to diminish a communication gap amongst electroencephalographers, engineers, and physicists. In fact, their book is directed to practitioners of each of those disciplines. The book focuses on the various aspects of electrophysiology of the brain. The first three chapters concern the relationship of physics and electrophysiology, while subsequent chapters are related to potentials in different biologic media and the generation and recording of cerebral electrical activity. Computer methodology applicable to electroencephalography is mentioned. This book has considerable value in its presentation of clinical, theoretical, and speculative

Learning to Control a Brain–Machine Interface for Reaching and Grasping by Primates

2003-10-13

Jose M. Carmena , Mikhail Lebedev , Roy E. Crist +6 more

Reaching and grasping in primates depend on the coordination of neural activity in large frontoparietal ensembles. Here we demonstrate that primates can learn to reach and grasp virtual objects by … Reaching and grasping in primates depend on the coordination of neural activity in large frontoparietal ensembles. Here we demonstrate that primates can learn to reach and grasp virtual objects by controlling a robot arm through a closed-loop brain–machine interface (BMIc) that uses multiple mathematical models to extract several motor parameters (i.e., hand position, velocity, gripping force, and the EMGs of multiple arm muscles) from the electrical activity of frontoparietal neuronal ensembles. As single neurons typically contribute to the encoding of several motor parameters, we observed that high BMIc accuracy required recording from large neuronal ensembles. Continuous BMIc operation by monkeys led to significant improvements in both model predictions and behavioral performance. Using visual feedback, monkeys succeeded in producing robot reach-and-grasp movements even when their arms did not move. Learning to operate the BMIc was paralleled by functional reorganization in multiple cortical areas, suggesting that the dynamic properties of the BMIc were incorporated into motor and sensory cortical representations.

View PDF Chat

Functional role of the supplementary and pre-supplementary motor areas

2008-10-09

Parashkev Nachev , Christopher Kennard , Masud Husain

Coding and use of tactile signals from the fingertips in object manipulation tasks

2009-04-08

Roland S. Johansson , J. Randall Flanagan

A review of classification algorithms for EEG-based brain–computer interfaces

2007-01-31

Fabien Lotte , Marco Congedo , A. Lécuyer +2 more

In this paper we review classification algorithms used to design brain–computer interface (BCI) systems based on electroencephalography (EEG). We briefly present the commonly employed algorithms and describe their critical properties. … In this paper we review classification algorithms used to design brain–computer interface (BCI) systems based on electroencephalography (EEG). We briefly present the commonly employed algorithms and describe their critical properties. Based on the literature, we compare them in terms of performance and provide guidelines to choose the suitable classification algorithm(s) for a specific BCI.

View PDF Chat

Identifying true brain interaction from EEG data using the imaginary part of coherency

2004-07-06

Guido Nolte , Ou Bai , Lewis A. Wheaton +3 more

Electroencephalography: Basic Principles, Clinical Applications and Related Fields

1983-03-01

Fábio R. Torres

This book has 44 chapters written by 23 authors from Europe and the United States. It represents a commendable attempt at producing a one-volume, comprehensive textbook on EEG. Many chapters … This book has 44 chapters written by 23 authors from Europe and the United States. It represents a commendable attempt at producing a one-volume, comprehensive textbook on EEG. Many chapters are good, but some are especially clear and didactic. "Biophysical Aspects of EEG and MEG Generation" deals with its subject in a clear and well-organized fashion understandable to all readers, leaving the mathematical foundations in an appendix for those whose interests are more basic. The chapter on the EEG laboratory goes into a discussion of laboratory design and organization, including comments on reporting EEGs and handling the reports. This is a useful feature that is not commonly seen in texts on EEG. The contingent negative variation is amply discussed in a review that includes techniques and physiologic and psychological correlates, updating previous reviews by the authors of the chapters. Some of the chapters are outstanding. The one on psychiatric disorders

Reach and grasp by people with tetraplegia using a neurally controlled robotic arm

2012-05-01

Leigh R. Hochberg , Daniel Bacher , Beata Jarosiewicz +7 more

View PDF Chat

Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials

1988-12-01

Lawrence A. Farwell , Emanuel Donchin

EEG alpha and theta oscillations reflect cognitive and memory performance: a review and analysis

1999-04-01

Wolfgang Klimesch

The P300 Wave of the Human Event-Related Potential

1992-10-01

Terence W. Picton

The P300 wave is a positive deflection in the human event-related potential. It is most commonly elicited in an "oddball" paradigm when a subject detects an occasional "target" stimulus in … The P300 wave is a positive deflection in the human event-related potential. It is most commonly elicited in an "oddball" paradigm when a subject detects an occasional "target" stimulus in a regular train of standard stimuli. The P300 wave only occurs if the subject is actively engaged in the task of detecting the targets. Its amplitude varies with the improbability of the targets. Its latency varies with the difficulty of discriminating the target stimulus from the standard stimuli. A typical peak latency when a young adult subject makes a simple discrimination is 300 ms. In patients with decreased cognitive ability, the P300 is smaller and later than in age-matched normal subjects. The intracerebral origin of the P300 wave is not known and its role in cognition not clearly understood. The P300 may have multiple intracerebral generators, with the hippocampus and various association areas of the neocortex all contributing to the scalp-recorded potential. The P300 wave may represent the transfer of information to consciousness, a process that involves many different regions of the brain.

Optimizing Spatial filters for Robust EEG Single-Trial Analysis

2008-01-01

Benjamin Blankertz , Ryota Tomioka , Steven Lemm +2 more

Due to the volume conduction multichannel electroencephalogram (EEG) recordings give a rather blurred image of brain activity. Therefore spatial filters are extremely useful in single-trial analysis in order to improve … Due to the volume conduction multichannel electroencephalogram (EEG) recordings give a rather blurred image of brain activity. Therefore spatial filters are extremely useful in single-trial analysis in order to improve the signal-to-noise ratio. There are powerful methods from machine learning and signal processing that permit the optimization of spatio-temporal filters for each subject in a data dependent fashion beyond the fixed filters based on the sensor geometry, e.g., Laplacians. Here we elucidate the theoretical background of the common spatial pattern (CSP) algorithm, a popular method in brain-computer interface (BCD research. Apart from reviewing several variants of the basic algorithm, we reveal tricks of the trade for achieving a powerful CSP performance, briefly elaborate on theoretical aspects of CSP, and demonstrate the application of CSP-type preprocessing in our studies of the Berlin BCI (BBCI) project.

The five percent electrode system for high-resolution EEG and ERP measurements

2001-04-01

Robert Oostenveld , Peter Praamstra

View PDF Chat

Brain–computer interfaces for communication and control

2002-06-01

Jonathan R. Wolpaw , Niels Birbaumer , Dennis J. McFarland +2 more

Neuronal ensemble control of prosthetic devices by a human with tetraplegia

2006-07-01

Leigh R. Hochberg , Mijail D. Serruya , Gerhard M. Friehs +7 more

A new method for off-line removal of ocular artifact

1983-04-01

Gabriele Gratton , Michael Coles , Emanuel Donchin

Cortical control of a prosthetic arm for self-feeding

2008-05-28

Meel Velliste , Sagi Perel , M. Chance Spalding +2 more

View PDF Chat

ERPLAB: an open-source toolbox for the analysis of event-related potentials

2014-04-14

Javier López‐Calderón , Steven J. Luck

ERPLAB Toolbox is a freely available, open-source toolbox for processing and analyzing event-related potential (ERP) data in the MATLAB environment. ERPLAB is closely integrated with EEGLAB, a popular open-source toolbox … ERPLAB Toolbox is a freely available, open-source toolbox for processing and analyzing event-related potential (ERP) data in the MATLAB environment. ERPLAB is closely integrated with EEGLAB, a popular open-source toolbox that provides many EEG preprocessing steps and an excellent user interface design. ERPLAB adds to EEGLAB's EEG processing functions, providing additional tools for filtering, artifact detection, re-referencing, and sorting of events, among others. ERPLAB also provides robust tools for averaging EEG segments together to create averaged ERPs, for creating difference waves and other recombinations of ERP waveforms through algebraic expressions, for filtering and re-referencing the averaged ERPs, for plotting ERP waveforms and scalp maps, and for quantifying several types of amplitudes and latencies. ERPLAB's tools can be accessed either from an easy-to-learn graphical user interface or from MATLAB scripts, and a command history function makes it easy for users with no programming experience to write scripts. Consequently, ERPLAB provides both ease of use and virtually unlimited power and flexibility, making it appropriate for the analysis of both simple and complex ERP experiments. Several forms of documentation are available, including a detailed user's guide, a step-by-step tutorial, a scripting guide, and a set of video-based demonstrations.

View PDF Chat

Brain Computer Interfaces, a Review

2012-01-31

Luis F. Nicolás-Alonso , J. Gil

A brain-computer interface (BCI) is a hardware and software communications system that permits cerebral activity alone to control computers or external devices. The immediate goal of BCI research is to … A brain-computer interface (BCI) is a hardware and software communications system that permits cerebral activity alone to control computers or external devices. The immediate goal of BCI research is to provide communications capabilities to severely disabled people who are totally paralyzed or ‘locked in’ by neurological neuromuscular disorders, such as amyotrophic lateral sclerosis, brain stem stroke, or spinal cord injury. Here, we review the state-of-the-art of BCIs, looking at the different steps that form a standard BCI: signal acquisition, preprocessing or signal enhancement, feature extraction, classification and the control interface. We discuss their advantages, drawbacks, and latest advances, and we survey the numerous technologies reported in the scientific literature to design each step of a BCI. First, the review examines the neuroimaging modalities used in the signal acquisition step, each of which monitors a different functional brain activity such as electrical, magnetic or metabolic activity. Second, the review discusses different electrophysiological control signals that determine user intentions, which can be detected in brain activity. Third, the review includes some techniques used in the signal enhancement step to deal with the artifacts in the control signals and improve the performance. Fourth, the review studies some mathematic algorithms used in the feature extraction and classification steps which translate the information in the control signals into commands that operate a computer or other device. Finally, the review provides an overview of various BCI applications that control a range of devices.

View PDF Chat

Motor imagery and direct brain-computer communication

2001-07-01

G. Pfurtscheller , Christa Neuper

Motor imagery can modify the neuronal activity in the primary sensorimotor areas in a very similar way as observable with a real executed movement. One part of EEG-based brain-computer interfaces … Motor imagery can modify the neuronal activity in the primary sensorimotor areas in a very similar way as observable with a real executed movement. One part of EEG-based brain-computer interfaces (BCI) is based on the recording and classification of circumscribed and transient EEG changes during different types of motor imagery such as, e.g., imagination of left-hand, right-hand, or foot movement. Features such as, e.g., band power or adaptive autoregressive parameters are either extracted in bipolar EEG recordings overlaying sensorimotor areas or from an array of electrodes located over central and neighboring areas. For the classification of the features, linear discrimination analysis and neural networks are used. Characteristic for the Graz BCI is that a classifier is set up in a learning session and updated after one or more sessions with online feedback using the procedure of "rapid prototyping." As a result, a discrimination of two brain states (e.g., leftversus right-hand movement imagination) can be reached within only a few days of training. At this time, a tetraplegic patient is able to operate an EEG-based control of a hand orthosis with nearly 100% classification accuracy by mental imagination of specific motor commands.

View PDF Chat

Optimal spatial filtering of single trial EEG during imagined hand movement

2000-12-01

Herbert Ramoser , Johannes Müller-Gerking , G. Pfurtscheller

The development of an electroencephalograph (EEG)-based brain-computer interface (BCI) requires rapid and reliable discrimination of EEG patterns, e.g., associated with imaginary movement. One-sided hand movement imagination results in EEG changes … The development of an electroencephalograph (EEG)-based brain-computer interface (BCI) requires rapid and reliable discrimination of EEG patterns, e.g., associated with imaginary movement. One-sided hand movement imagination results in EEG changes located at contra- and ipsilateral central areas. The authors demonstrate that spatial filters for multichannel EEG effectively extract discriminatory information from two populations of single-trial EEG, recorded during left- and right-hand movement imagery. The best classification results for three subjects are 90.8%, 92.7%, and 99.7%. The spatial filters are estimated from a set of data by the method of common spatial patterns and reflect the specific activation of cortical areas. The method performs a weighting of the electrodes according to their importance for the classification task. The high recognition rates and computational simplicity make it a promising method for an EEG-based brain-computer interface.

View PDF Chat

High-performance neuroprosthetic control by an individual with tetraplegia

2012-12-17

Jennifer L. Collinger , Brian Wodlinger , John E. Downey +7 more

View PDF Chat

Brain-computer interface technology: a review of the first international meeting

2000-06-01

Jonathan R. Wolpaw , Niels Birbaumer , William Heetderks +7 more

Over the past decade, many laboratories have begun to explore brain-computer interface (BCI) technology as a radically new communication option for those with neuromuscular impairments that prevent them from using … Over the past decade, many laboratories have begun to explore brain-computer interface (BCI) technology as a radically new communication option for those with neuromuscular impairments that prevent them from using conventional augmentative communication methods. BCI's provide these users with communication channels that do not depend on peripheral nerves and muscles. This article summarizes the first international meeting devoted to BCI research and development. Current BCI's use electroencephalographic (EEG) activity recorded at the scalp or single-unit activity recorded from within cortex to control cursor movement, select letters or icons, or operate a neuroprosthesis. The central element in each BCI is a translation algorithm that converts electrophysiological input from the user into output that controls external devices. BCI operation depends on effective interaction between two adaptive controllers, the user who encodes his or her commands in the electrophysiological input provided to the BCI, and the BCI which recognizes the commands contained in the input and expresses them in device control. Current BCI's have maximum information transfer rates of 5-25 b/min. Achievement of greater speed and accuracy depends on improvements in signal processing, translation algorithms, and user training. These improvements depend on increased interdisciplinary cooperation between neuroscientists, engineers, computer programmers, psychologists, and rehabilitation specialists, and on adoption and widespread application of objective methods for evaluating alternative methods. The practical use of BCI technology depends on the development of appropriate applications, identification of appropriate user groups, and careful attention to the needs and desires of individual users. BCI research and development will also benefit from greater emphasis on peer-reviewed publications, and from adoption of standard venues for presentations and discussion.

View PDF Chat

The functional states of the thalamus and the associated neuronal interplay.

1988-07-01

Mircea Steriade , R. R. Llinas

A Core System for the Implementation of Task Sets

2006-06-01

Nico U.F. Dosenbach , Kristina Visscher , Erica D. Palmer +7 more

View PDF Chat

BCI2000: A General-Purpose Brain-Computer Interface (BCI) System

2004-05-25

Gerwin Schalk , Dennis J. McFarland , Thilo Hinterberger +2 more

Many laboratories have begun to develop brain-computer interface (BCI) systems that provide communication and control capabilities to people with severe motor disabilities. Further progress and realization of practical applications depends … Many laboratories have begun to develop brain-computer interface (BCI) systems that provide communication and control capabilities to people with severe motor disabilities. Further progress and realization of practical applications depends on systematic evaluations and comparisons of different brain signals, recording methods, processing algorithms, output formats, and operating protocols. However, the typical BCI system is designed specifically for one particular BCI method and is, therefore, not suited to the systematic studies that are essential for continued progress. In response to this problem, we have developed a documented general-purpose BCI research and development platform called BCI2000. BCI2000 can incorporate alone or in combination any brain signals, signal processing methods, output devices, and operating protocols. This report is intended to describe to investigators, biomedical engineers, and computer scientists the concepts that the BC12000 system is based upon and gives examples of successful BCI implementations using this system. To date, we have used BCI2000 to create BCI systems for a variety of brain signals, processing methods, and applications. The data show that these systems function well in online operation and that BCI2000 satisfies the stringent real-time requirements of BCI systems. By substantially reducing labor and cost, BCI2000 facilitates the implementation of different BCI systems and other psychophysiological experiments. It is available with full documentation and free of charge for research or educational purposes and is currently being used in a variety of studies by many research groups.

Electroencephalography—Basic principles, clinical applications and related fields

1982-09-01

Large‐scale neurocognitive networks and distributed processing for attention, language, and memory

1990-11-01

M‐Marsel Mesulam

Cognition and comportment are subserved by interconnected neural networks that allow high-level computational architectures including parallel distributed processing. Cognitive problems are not resolved by a sequential and hierarchical progression toward … Cognition and comportment are subserved by interconnected neural networks that allow high-level computational architectures including parallel distributed processing. Cognitive problems are not resolved by a sequential and hierarchical progression toward predetermined goals but instead by a simultaneous and interactive consideration of multiple possibilities and constraints until a satisfactory fit is achieved. The resultant texture of mental activity is characterized by almost infinite richness and flexibility. According to this model, complex behavior is mapped at the level of multifocal neural systems rather than specific anatomical sites, giving rise to brain-behavior relationships that are both localized and distributed. Each network contains anatomically addressed channels for transferring information content and chemically addressed pathways for modulating behavioral tone. This approach provides a blueprint for reexploring the neurological foundations of attention, language, memory, and frontal lobe function.

On a confusion about a function of consciousness

1995-06-01

Ned Block

Abstract Consciousness is a mongrel concept: there are a number of very different “consciousnesses.” Phenomenal consciousness is experience; the phenomenally conscious aspect of a state is what it is like … Abstract Consciousness is a mongrel concept: there are a number of very different “consciousnesses.” Phenomenal consciousness is experience; the phenomenally conscious aspect of a state is what it is like to be in that state. The mark of access-consciousness, by contrast, is availability for use in reasoning and rationally guiding speech and action. These concepts are often partly or totally conflated, with bad results. This target article uses as an example a form of reasoning about a function of “consciousness” based on the phenomenon of blindsight. Some information about stimuli in the blind field is represented in the brains of blindsight patients, as shown by their correct “guesses.” They cannot harness this information in the service of action, however, and this is said to show that a function of phenomenal consciousness is somehow to enable information represented in the brain to guide action. But stimuli in the blind field are both access-unconscious and phenomenally unconscious. The fallacy is: an obvious function of the machinery of accessconsciousness is illicitly transferred to phenomenal consciousness.

A Neural System for Error Detection and Compensation

1993-11-01

William J. Gehring , Brian Michael Goss , Michael Coles +2 more

Humans can monitor actions and compensate for errors. Analysis of the human event-related brain potentials (ERPs) accompanying errors provides evidence for a neural process whose activity is specifically associated with … Humans can monitor actions and compensate for errors. Analysis of the human event-related brain potentials (ERPs) accompanying errors provides evidence for a neural process whose activity is specifically associated with monitoring and compensating for erroneous behavior. This error-related activity is enhanced when subjects strive for accurate performance but is diminished when response speed is emphasized at the expense of accuracy. The activity is also related to attempts to compensate for the erroneous behavior.

Scalp distributions of event-related potentials: An ambiguity associated with analysis of variance models

1985-05-01

Gregory McCarthy , Charles Cresson Wood

Brain–machine interfaces: past, present and future

2006-07-22

Mikhail Lebedev , Miguel A. L. Nicolelis

EVIDENCE FOR THE EXISTENCE OF MONOAMINE NEURONS IN THE CENTRAL NERVOUS SYSTEM. IV. DISTRIBUTION OF MONOAMINE NERVE TERMINALS IN THE CENTRAL NERVOUS SYSTEM.

1965-01-01

Kjell Fuxé

Report of the committee on methods of clinical examination in electroencephalography

1958-05-01

Deep learning with convolutional neural networks for EEG decoding and visualization

2017-08-07

Robin Tibor Schirrmeister , Jost Tobias Springenberg , Lukas D. J. Fiederer +6 more

Abstract Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end‐to‐end learning, that is, learning from the raw data. There is increasing interest in using deep … Abstract Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end‐to‐end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end‐to‐end EEG analysis, but a better understanding of how to design and train ConvNets for end‐to‐end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task‐related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG‐based brain mapping. Hum Brain Mapp 38:5391–5420, 2017 . © 2017 Wiley Periodicals, Inc.

View PDF Chat

A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update

2018-02-28

Fabien Lotte , Laurent Bougrain , Andrzej Cichocki +4 more

Most current electroencephalography (EEG)-based brain-computer interfaces (BCIs) are based on machine learning algorithms. There is a large diversity of classifier types that are used in this field, as described in … Most current electroencephalography (EEG)-based brain-computer interfaces (BCIs) are based on machine learning algorithms. There is a large diversity of classifier types that are used in this field, as described in our 2007 review paper. Now, approximately ten years after this review publication, many new algorithms have been developed and tested to classify EEG signals in BCIs. The time is therefore ripe for an updated review of EEG classification algorithms for BCIs.We surveyed the BCI and machine learning literature from 2007 to 2017 to identify the new classification approaches that have been investigated to design BCIs. We synthesize these studies in order to present such algorithms, to report how they were used for BCIs, what were the outcomes, and to identify their pros and cons.We found that the recently designed classification algorithms for EEG-based BCIs can be divided into four main categories: adaptive classifiers, matrix and tensor classifiers, transfer learning and deep learning, plus a few other miscellaneous classifiers. Among these, adaptive classifiers were demonstrated to be generally superior to static ones, even with unsupervised adaptation. Transfer learning can also prove useful although the benefits of transfer learning remain unpredictable. Riemannian geometry-based methods have reached state-of-the-art performances on multiple BCI problems and deserve to be explored more thoroughly, along with tensor-based methods. Shrinkage linear discriminant analysis and random forests also appear particularly useful for small training samples settings. On the other hand, deep learning methods have not yet shown convincing improvement over state-of-the-art BCI methods.This paper provides a comprehensive overview of the modern classification algorithms used in EEG-based BCIs, presents the principles of these methods and guidelines on when and how to use them. It also identifies a number of challenges to further advance EEG classification in BCI.

View PDF Chat

EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces

2018-06-22

Vernon J. Lawhern , Amelia J. Solon , Nicholas R. Waytowich +3 more

Brain computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) … Brain computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI paradigm, feature extractors and classifiers are tailored to the distinct characteristics of its expected EEG control signal, limiting its application to that specific signal. Convolutional Neural Networks (CNNs), which have been used in computer vision and speech recognition, have successfully been applied to EEG-based BCIs; however, they have mainly been applied to single BCI paradigms and thus it remains unclear how these architectures generalize to other paradigms. Here, we ask if we can design a single CNN architecture to accurately classify EEG signals from different BCI paradigms, while simultaneously being as compact as possible. In this work we introduce EEGNet, a compact convolutional network for EEG-based BCIs. 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. We compare EEGNet to current state-of-the-art approaches across four BCI paradigms: P300 visual-evoked potentials, error-related negativity responses (ERN), movement-related cortical potentials (MRCP), and sensory motor rhythms (SMR). We show that EEGNet generalizes across paradigms better than the reference algorithms when only limited training data is available. We demonstrate three different approaches to visualize the contents of a trained EEGNet model to enable interpretation of the learned features. Our results suggest that EEGNet is robust enough to learn a wide variety of interpretable features over a range of BCI tasks, suggesting that the observed performances were not due to artifact or noise sources in the data.

View PDF Chat

Principles of neural science

1982-01-01

View PDF Chat

EEG Arousals: Scoring Rules and Examples

1992-03-01

View PDF Chat

Temporary suppression of visual processing in an RSVP task: An attentional blink?

1992-01-01

Jane E. Raymond , Kimron L. Shapiro , Karen M. Arnell

Design and Analysis of a Fault-Tolerant Control System for Pacemaker-Based Heart Rate Regulation

2025-06-25

| International Research Journal of Modernization in Engineering Technology and Science

Exploring the Potential of Electroencephalography Signal–Based Image Generation Using Diffusion Models: Integrative Framework Combining Mixed Methods and Multimodal Analysis

2025-06-25

Chi-Sheng Chen , S. Grace Chang , Che‐Wei Liu +1 more | JMIR Medical Informatics

Background Electroencephalography (EEG) has been widely used to measure brain activity, but its potential to generate accurate images from neural signals remains a challenge. Most EEG-decoding research has focused on … Background Electroencephalography (EEG) has been widely used to measure brain activity, but its potential to generate accurate images from neural signals remains a challenge. Most EEG-decoding research has focused on tasks such as motor imagery, emotion recognition, and brain wave classification, which involve EEG signal analysis and classification. Some studies have explored the correlation between EEG and images, primarily focusing on EEG-image pair classification or transformation. However, EEG-based image generation remains underexplored. Objective The primary goal of this study was to extend EEG-based classification to image generation, addressing the limitations of previous methods and unlocking the full potential of EEG for image synthesis. To achieve more meaningful EEG-to-image generation, we developed a novel framework, Neural-Cognitive Multimodal EEG-Informed Image (NECOMIMI), which was specifically designed to generate images directly from EEG signals. Methods We developed a 2-stage NECOMIMI method, which integrated the novel Neural Encoding Representation Vectorizer (NERV) EEG encoder that we designed with a diffusion-based generative model. The Category-Based Assessment Table (CAT) score was introduced to evaluate the semantic quality of EEG-generated images. In addition, the ThingsEEG dataset was used to validate and benchmark the CAT score, providing a standardized measure for assessing EEG-to-image generation performance. Results The NERV EEG encoder achieved state-of-the-art performance in several zero-shot classification tasks, with an average accuracy of 94.8% (SD 1.7%) in the 2-way task and 86.8% (SD 3.4%) in the 4-way task, outperforming models such as Natural Image Contrast EEG, Multimodal Similarity-Keeping Contrastive Learning, and Adaptive Thinking Mapper ShallowNet. This highlighted its superiority as a feature extraction tool for EEG signals. In a 1-stage image generation framework, EEG embeddings often resulted in abstract or generalized images such as landscapes instead of specific objects. Our proposed 2-stage NECOMIMI architecture effectively extracted semantic information from noisy EEG signals, showing its ability to capture and represent underlying concepts derived from brain wave activity. We further conducted a perturbation study to test whether the model overly depended on visual cortex EEG signals for scene-based image generation. The perturbation of visual cortex EEG channels led to a notable increase in Fréchet inception distance scores, suggesting that our model relied heavily on posterior brain signals to generate semantically coherent images. Conclusions NECOMIMI demonstrated the potential of EEG-to-image generation, revealing the challenges of translating noisy EEG data into accurate visual representations. The novel NERV EEG encoder for multimodal contrastive learning reached state-of-the-art performance both on n-way zero-shot and EEG-informed image generation. The introduction of the CAT score provided a new evaluation metric, paving the way for future research to refine generative models. In addition, this study highlighted the significant clinical potential of EEG-to-image generation, particularly in enhancing brain-machine interface systems and improving quality of life for individuals with motor impairments.

A Call for the Inclusion of Standardized Filter Parameters in the ACNS Standardized Critical Care EEG Terminology

2025-06-25

Fábio A. Nascimento , Lawrence J. Hirsch , Peter W. Kaplan +3 more | Journal of Clinical Neurophysiology

Smaller stepping thresholds in older adults might be related to reduced ability to suppress conflicting sensory information

2025-06-25

Hannah Carey , Friedl De Groote | bioRxiv (Cold Spring Harbor Laboratory)

Aging leads to alterations in the sensorimotor system and balance control but it is not well understood how changes in sensorimotor function affect how people respond to postural disturbances. Elucidating … Aging leads to alterations in the sensorimotor system and balance control but it is not well understood how changes in sensorimotor function affect how people respond to postural disturbances. Elucidating the relationships between balance control and sensorimotor function is crucial for developing effective rehabilitations. Here, we compared the kinematic responses to platform translations and rotations during standing in 10 young and 30 older adults and explored relationships between sensorimotor function and balance responses. We found that older adults were less able to withstand perturbations without stepping, not because their non-stepping strategies were less effective but because they chose to step at smaller deviations of the extrapolated center of mass. Older adults performed worse than young adults on measures of sensory and motor function but lower stepping thresholds were associated with susceptibility to unreliable visual information and not with reduced sensory acuity or reduced strength. Poor sensory reweighting may contribute to and combine with age-related cognitive rigidity, leading to a higher priority on safer strategies. Older adults may resort to stepping, even if a step is not necessary, rather than rely on potentially inaccurate sensory signals to inform a corrective response. Our results provide initial evidence that sensory reweighting could be a potential target for fall prevention methods.

Adverse Outcome Pathway on Binding to voltage gate sodium channels during development leading to cognitive impairment

2025-06-25

Iris Mangas , Antonio F. Hernández , Kevin M. Crofton +7 more | OECD series on adverse outcome pathways

Brain-Computer Interface for Taste Perception

2025-06-24

Rakesh Balakumar , Anbarasan Rajan , R. Mahendran | CRC Press eBooks

Hierarchical Deep Learning for Comprehensive Epileptic Seizure Analysis: From Detection to Fine-Grained Classification

2025-06-24

Peter Akor , Godwin Enemali , Usman Muhammad +2 more | Information

Epileptic seizure detection and classification from EEG recordings faces significant challenges due to extreme class imbalance. Analysis of the Temple University Hospital Seizure (TUSZ) dataset reveals imbalance ratios of 150:1 … Epileptic seizure detection and classification from EEG recordings faces significant challenges due to extreme class imbalance. Analysis of the Temple University Hospital Seizure (TUSZ) dataset reveals imbalance ratios of 150:1 between common and rare seizure types, with high temporal heterogeneity (seizure durations of 1–1638 s). We propose a cascaded deep learning architecture with two specialized CNNs: a binary detector followed by a multi-class classifier. This approach decomposes the classification problem, reducing the maximum imbalance from 150:1 to manageable levels (9:1 binary, 5:1 type). The architecture implements a high-confidence filtering mechanism (threshold = 0.9), creating a 99.5% pure dataset for type classification, dynamic class-weighted optimization proportional to inverse class frequencies, and information flow refinement through progressive stages. Loss dynamics analysis reveals that our weighting scheme strategically redistributes optimization attention, reducing variance by 90.7% for majority classes while increasing variance for minority classes, ensuring all seizure types receive proportional learning signals regardless of representation. The binary classifier achieves 99.64% specificity and 98.23% sensitivity (ROC-AUC = 0.995). The type classifier demonstrates >99% accuracy across seven seizure categories with perfect (100%) classification for three seizure types despite minimal representation. Cross-dataset validation on the University of Bonn dataset confirms robust generalization (96.0% accuracy) for binary seizure detection. This framework effectively addresses multi-level imbalance in neurophysiological signal classification with hierarchical class structures.

Resting-State Connectivity and Neuroimaging of Prefrontal Cortex Activity During a Block-Design Yoga Asana Practice Using fNIRS

2025-06-24

Michelle Goodrick , Daniel Eduardo Limón-Cano , Eleazar Samuel Kolosovas‐Machuca +1 more | Journal of Visualized Experiments

Brain-Computer Interface for Aroma Perception

2025-06-24

Monica Velusamy , R. Mahendran | CRC Press eBooks

Abnormal Elevated Connectivity During Language Processing is Associated with Poor Cognitive Performance in Children with Self-limited Epilepsy with Centrotemporal Spikes

2025-06-24

Wendy Qi , Katharine Emily Lee , Kerry C. Nix +6 more

Self-Limited Epilepsy with Centrotemporal Spikes (SeLECTS) is associated with language impairments despite seizures originating in the motor cortex, suggesting aberrant cross-network interactions. Here we tested whether functional connectivity in SeLECTS … Self-Limited Epilepsy with Centrotemporal Spikes (SeLECTS) is associated with language impairments despite seizures originating in the motor cortex, suggesting aberrant cross-network interactions. Here we tested whether functional connectivity in SeLECTS during language tasks predicts language performance. We recorded high-density EEG from right-handed children with SeLECTS (n=31) and age-matched controls (n=32) during verb generation, repetition, and resting tasks. Phonological awareness was assessed using the Comprehensive Test of Phonological Processing-2. Connectivity between bilateral motor cortices and language regions (the left inferior frontal and superior temporal cortices and their right hemisphere homologues) was measured using weighted Phase Lag Index (wPLI). Children with SeLECTS demonstrated significantly elevated connectivity between motor and language regions during language processing. Motor-to-frontal connectivity was higher in SeLECTS during both verb generation and repetition tasks. Frontal-to-temporal connectivity was elevated specifically during verb generation. Higher interhemispheric connectivity (between the left and right hemispheres) during language tasks strongly predicted worse phonological awareness in children with SeLECTS (β = -40 to -61, all p<0.005), but not controls. Together, we found that children with SeLECTS exhibited pathologically elevated connectivity between motor and language networks that was strongly associated with impaired phonological awareness. These findings identify aberrant interhemispheric connectivity as a pathophysiological mechanism underlying language dysfunction and establish EEG-based connectivity measures as a potential biomarker for guiding targeted neuromodulation therapies to treat cognitive impairments in pediatric epilepsy.

Narrowband Theta Investigations for Detecting Cognitive Mental Load

2025-06-23

Silviu Ioniţă , Daniela Andreea Coman | Sensors

The way in which EEG signals reflect mental tasks that vary in duration and intensity is a key topic in the investigation of neural processes concerning neuroscience in general and … The way in which EEG signals reflect mental tasks that vary in duration and intensity is a key topic in the investigation of neural processes concerning neuroscience in general and BCI technologies in particular. More recent research has reinforced historical studies that highlighted theta band activity in relation to cognitive performance. In our study, we propose a comparative analysis of experiments with cognitive load imposed by arithmetic calculations performed mentally. The analysis of EEG signals captured with 64 electrodes is performed on low theta components extracted by narrowband filtering. As main signal discriminators, we introduced an original measure inspired by the integral of the curve of a function—specifically the signal function over the period corresponding to the filter band. Another measure of the signal considered as a discriminator is energy. In this research, it was used just for model comparison. A cognitive load detection algorithm based on these signal metrics was developed and tested on original experimental data. The results present EEG activity during mental tasks and show the behavioral pattern across 64 channels. The most precise and specific EEG channels for discriminating cognitive tasks induced by arithmetic tests are also identified.

Neuro-VisAge: a visual and statistical strategy to investigate age effect on brain activity

2025-06-23

Igor A. Rodrigues , Juliana Almeida da Silva , Emerson Carvalho +1 more | Research Square (Research Square)

<title>Abstract</title> The last decade was marked by a spike in the use of Machine Learning (ML) andfunctional magnetic resonance image for neurological disorders diagnoses. How-ever, there is a limitation considering … <title>Abstract</title> The last decade was marked by a spike in the use of Machine Learning (ML) andfunctional magnetic resonance image for neurological disorders diagnoses. How-ever, there is a limitation considering age bias when designing their experiments,which can impact the final result. Here, we investigate the effects of age bias ona sample of typical neurological subjects, looking for patterns in brain activity.We also suggest that age groups be used in the ML training and classificationfor future works. Our results show that for the five brain regions investigated(Frontal Gyrus, Cingulum Bundle, Putamen, Angular Gyrus, and Heschl Gyrus),using a 10-year span would increase the reliability of ML experiments aiming todiagnose neural disorders by reducing the age bias effect on the models.

LG-TriCapsNet: A lightweight graph capsule framework with nearest neighbor graphs for multi-disease EEG classification

2025-06-23

Shraddha Jain , Rajeev Srivastava | Computers in Biology and Medicine

A longitudinal EEG dataset of event-related potential

2025-06-23

Yufeng Zhang , Hongxin Zhang , Yixuan Li +3 more | Scientific Data

Electroencephalogram (EEG)-based biometric emerges as a promising authentication method, offering a novel insight into the future security systems. However, its long-term stability and inter-individual variability necessitate further exploration. This paper … Electroencephalogram (EEG)-based biometric emerges as a promising authentication method, offering a novel insight into the future security systems. However, its long-term stability and inter-individual variability necessitate further exploration. This paper presents an event-related potential (ERP) dataset acquired through EEG recordings under rapid serial visual presentation stimulation. The dataset encompasses 200 days of ERP recordings from 15 participants, along with single-session observations from 52 individuals. During the experiment, participants were tasked with identifying a target face to elicit ERP responses. This dataset provides comprehensive and high-quality data for the development of EEG-based identity authentication systems. Additionally, the dataset holds research value for ERP investigation on facial perception and target detection.

Advances in Neuromodulation and Digital Brain–Spinal Cord Interfaces for Spinal Cord Injury

2025-06-23

Phillip Jaszczuk , Denis Bratelj , Crescenzo Capone +4 more | International Journal of Molecular Sciences

Spinal cord injury (SCI) results in a significant loss of motor, sensory, and autonomic function, imposing substantial biosocial and economic burdens. Traditional approaches, such as stem cell therapy and immune … Spinal cord injury (SCI) results in a significant loss of motor, sensory, and autonomic function, imposing substantial biosocial and economic burdens. Traditional approaches, such as stem cell therapy and immune modulation, have faced translational challenges, whereas neuromodulation and digital brain–spinal cord interfaces combining brain–computer interface (BCI) technology and epidural spinal cord stimulation (ESCS) to create brain–spine interfaces (BSIs) offer promising alternatives by leveraging residual neural pathways to restore physiological function. This review examines recent advancements in neuromodulation, focusing on the future translation of clinical trial data to clinical practice. We address key considerations, including scalability, patient selection, surgical techniques, postoperative rehabilitation, and ethical implications. By integrating interdisciplinary collaboration, standardized protocols, and patient-centered design, neuromodulation has the potential to revolutionize SCI rehabilitation, reducing long-term disability and enhancing quality of life globally.

Systematic review: progress in EEG-based speech imagery brain-computer interface decoding and encoding research

2025-06-23

Ke Su , Tian Liang | PeerJ Computer Science

This article systematically reviews the latest developments in electroencephalogram (EEG)-based speech imagery brain-computer interface (SI-BCI). It explores the brain connectivity of SI-BCI and reveals its key role in neural encoding … This article systematically reviews the latest developments in electroencephalogram (EEG)-based speech imagery brain-computer interface (SI-BCI). It explores the brain connectivity of SI-BCI and reveals its key role in neural encoding and decoding. It analyzes the research progress on vowel-vowel and vowel-consonant combinations, as well as Chinese characters, words, and long-words speech imagery paradigms. In the neural encoding section, the preprocessing and feature extraction techniques for EEG signals are discussed in detail. The neural decoding section offers an in-depth analysis of the applications and performance of machine learning and deep learning algorithms. Finally, the challenges faced by current research are summarized, and future directions are outlined. The review highlights that future research should focus on brain region mechanisms, paradigms innovation, and the optimization of decoding algorithms to promote the practical application of SI-BCI technology.

ASL in the Aging Mind: Tracing Perfusion Patterns in Emerging Dementia

2025-06-23

Malgireddy Vinitha , Uma M. Reddy , Rama Krishna Rao Baru +1 more | International Journal of Science and Research (IJSR)

Detection of pre-ictal epileptic events using a self-attention based neural network from raw Neonatal EEG data

2025-06-22

K. Tejaswi , Vikas Maheshkar , Himala Praharsha +4 more | Computers in Biology and Medicine

Liveness‐Verified Dynamic Time Warping‐Based Authentication and Hybrid Adaptive Neuro‐Fuzzy Inference System Identification for Single‐Channel Diaphragmatic Breathing Surface Electromyography Biometrics

2025-06-22

Beyza Eraslan , Kutlucan Görür , Feyzullah Temurtaş | Advanced Intelligent Systems

This article introduces a novel hybrid biometric identification framework that harnesses respiratory‐induced surface electromyography signals recorded from the diaphragm using a single‐channel electrode. The proposed system capitalizes on the unique, … This article introduces a novel hybrid biometric identification framework that harnesses respiratory‐induced surface electromyography signals recorded from the diaphragm using a single‐channel electrode. The proposed system capitalizes on the unique, dynamic muscle activation patterns elicited during deep‐normal‐deep breathing sequences. In this framework, robust statistical features are first extracted and reduced via principal component analysis, then a streamlined parallel adaptive neuro‐fuzzy inference system structure, designed to capture individual‐specific patterns with minimal training error, is employed for feature vector generation. Finally, dynamic time warping is incorporated as a supportive tool to align temporal respiration patterns, refining decision thresholds and enhancing intersubject discrimination. Experimental results demonstrate that this integrated approach achieves high recognition accuracy, underscoring its potential for secure, real‐time biometric authentication.

Combined Auditory, Tactile, and Visual fMRI Reveals Sensory-Biased and Supramodal Working Memory Regions in Human Frontal Cortex

2025-06-21

Sean Tobyne , James A. Brissenden , Abigail L. Noyce +1 more | bioRxiv (Cold Spring Harbor Laboratory)

Selectivity for sensory modality characterizes distinct subregions of the human brain, well beyond the primary sensory cortices. We previously identified frontal and posterior cortical regions that are preferentially recruited for … Selectivity for sensory modality characterizes distinct subregions of the human brain, well beyond the primary sensory cortices. We previously identified frontal and posterior cortical regions that are preferentially recruited for visual vs. auditory attention and working memory (WM). Here, we extend our approach to include tactile cognition and to characterize cortical regions recruited by WM in each of three sensory modalities. The joint organization of visual-selective, auditory-selective, tactile-selective, and supramodal WM recruitment within individual subjects has not been fully investigated previously. Male and female human subjects participated in a blocked fMRI task requiring them to perform N-back WM judgements in auditory, visual, or tactile (haptic) modalities. We confirmed our prior reports of multiple visual-biased and auditory-biased frontal lobe regions. We also observed several bilateral tactile-selective regions abutting previously described visual- and auditory-selective regions, including dorsal and ventral precentral sulcus, the postcentral sulcus, and the anterior intraparietal sulcus. Several cortical regions were recruited by WM in all three sensory modalities in individual subjects, including precentral sulcus, inferior frontal sulcus, intraparietal sulcus, anterior insula and pre-supplementary motor area. Supramodal regions exhibited substantial overlap with visual-biased regions in frontal and parietal cortex and comparatively little overlap with tactile- or auditory-biased regions. Lastly, resting-state analyses revealed that auditory-, visual- and tactile-selective WM regions segregate into modality-specific networks that span frontal and posterior cortex. Together, these results shed light on the functional organization of sensory-selective and supramodal regions supporting higher-order cognition.

Leveraging QEEG neuro-biomarkers of alcohol-related visual cognitive impairment for alcohol abuse and dependence diagnosis

2025-06-21

Ruchi Holker , Seba Susan | Applied Neuropsychology Adult

This paper presents a novel approach for leveraging Quantitative Electroencephalography (QEEG) neuro-biomarkers of alcohol-induced impairment of visual memory for alcohol abuse and dependence diagnosis. To achieve this, a spectral filter … This paper presents a novel approach for leveraging Quantitative Electroencephalography (QEEG) neuro-biomarkers of alcohol-induced impairment of visual memory for alcohol abuse and dependence diagnosis. To achieve this, a spectral filter bank with a wide frequency range (0-100 Hz) is used in conjunction with a spatial filter bank constructed using the Common Spatial Pattern algorithm. We extract a broad set of QEEG features, including power, spectral distribution, and inter-hemisphere functional connectivity, from filtered EEG signals. A total of 1620 QEEG features are extracted from two independent cohorts to demonstrate the generalization ability of the proposed method. Further, Sequential Forward Selection (SFS) with stratified 10-fold cross-validation is used as a wrapper technique to select the subset of features with maximum predictive power, which is determined as 248 and 263 for the two cohorts. SFS was selected for its computational efficiency and effectiveness in optimizing feature subsets within a wrapper-based framework, while mitigating overfitting and preserving model interpretability. The proposed approach outperforms state-of-the-art models, achieving top diagnostic accuracies of 99.63% and 99.25% for the two cohorts using a Support Vector Machine classifier. Our findings reveal that features extracted from the lowest frequencies (delta, theta, and lower alpha bands) and the highest frequencies (higher gamma band) are most discriminative for identifying alcoholic individuals.

Brain activation during vocal motor imagery: a pilot functional near-infrared spectroscopy (fNIRS) study

2025-06-20

Narihiro Kodama , Ryo Hatazoe , Kohei Kotegawa | Experimental Brain Research

Improved LSTM-SqueezeNet Model and Improved Kalman Filtering Process for Epileptic Seizure Prediction Using EEG Signal

2025-06-20

Ratnaprabha Ravindra Borhade , Pushpa M. Bangare , Manoj L. Bangare +2 more | International Journal of Image and Graphics

Epilepsy is a neurological condition resulting in irregular activity in the brain’s neurons, which leads to frequent unexpected seizure occurrences. Hence, it is essential to predict this disorder at an … Epilepsy is a neurological condition resulting in irregular activity in the brain’s neurons, which leads to frequent unexpected seizure occurrences. Hence, it is essential to predict this disorder at an early stage that prevents the patient’s life. Various Deep Learning (DL)-based techniques are employed in this aspect. Still, the models rely on inaccurate performance with improper training. In this work, a hybrid classification system consisting of SqueezeNet and Improved Long Short-Term Memory (ILSTM) models is proposed to predict epileptic seizures using Electroencephalography (EEG) inputs. The prediction of seizure involves three stages. The EEG signal initially undergoes preprocessing, where the improved Kalman filter is employed to preprocess the signal. After that, several features such as Empirical Mode Decomposition (EMD), improved Stockwell transform, spectral density, spectral skewness, and statistical features are derived from the preprocessed signal. The extracted features are subjected as the input to the prediction stage with a hybrid classification system utilized. The hybrid system is the integration of ILSTM and SqueezeNet classifiers. Additionally, the performance of the proposed method is compared to that of conventional models using a range of performance metrics. As a result, the suggested model shows superior performance compared to the existing techniques.

Potential Therapeutic Application of Closed-Loop Brain Computer Interfaces for the Treatment of Neurological Disorders: A Review and Methodological Framework

2025-06-20

Yi Cao | Theoretical and Natural Science

Closed - loop brain - computer interfaces (BCIs) are a promising advancement in treating neurological disorders as they enable real-time interaction between the brain and external devices. This paper reviews … Closed - loop brain - computer interfaces (BCIs) are a promising advancement in treating neurological disorders as they enable real-time interaction between the brain and external devices. This paper reviews the fundamental principles of closed-loop BCI technology, its potential therapeutic applications, and the technical frameworks supporting their operation. The review concentrates on the application of closed - loop BCIs in stroke rehabilitation and paralysis recovery, emphasizing how these systems can provide real - time feedback and adaptive responses to promote neural plasticity and functional recovery. By capturing and decoding brain activity, BCIs offer a non-invasive method to restore motor function and improve the quality of life for patients with stroke or paralysis. Despite the promising advantages, challenges such as signal noise, clinical scalability, hardware limitations, and ethical concerns persist. The study emphasizes the need for interdisciplinary collaboration to overcome these challenges and further advance closed-loop BCIs as effective tools for neurological treatment. These technologies have significant potential for improving the outcomes of stroke and paralysis rehabilitation

Fourier-Based Spectral Analysis of EEG Signals for Sleep Stage Classification

2025-06-20

Lin Cao | Theoretical and Natural Science

This paper explores the application of Fourier Transform for analyzing EEG signals in the context of sleep stage classification. The study seeks to enhance classification accuracy by extracting spectral features … This paper explores the application of Fourier Transform for analyzing EEG signals in the context of sleep stage classification. The study seeks to enhance classification accuracy by extracting spectral features through Fourier analysis. The research methodology integrates EEG preprocessing, feature extraction via frequency analysis, and a straightforward machine learning model for classifying different sleep stages. The results show moderate classification accuracy (~57%) using simple Fourier features and traditional classifiers (SVM, KNN), demonstrating feasibility but highlighting challenges especially in identifying REM sleep. This suggests potential for practical implementation in automated sleep monitoring systems and clinical diagnostics.

Cross-subject EEG Emotion Classification on Datasets with Limited Channels

2025-06-20

Jinhao Chen , Zixin Chen , Jianping Pan | Theoretical and Natural Science

To solve the challenge of achieving strong and accurate EEG datasets, while solving the domain shift problem, this research focused on integrating the Few-Label Adversarial Domain Adaptation (FLADA) method with … To solve the challenge of achieving strong and accurate EEG datasets, while solving the domain shift problem, this research focused on integrating the Few-Label Adversarial Domain Adaptation (FLADA) method with attention mechanism to see if the addition of the attention mechanism improves the performance over FLADA alone on EEG datasets with a small number of channels (specifically, 14 channels). We first apply the FLADA method to the research by solving the "domain shift" problem. Next, we added channel-wise-attention in an attempt to improve the algorithm. However, we found that the addition of channel-wise-attention failed to improve accuracy over the FLADA method alone, and in some cases made it even worse.

Electroencephalography: A valuable tool for assessing motor impairment and recovery post-stroke

2025-06-20

Jinru Feng , Weili Jia , Zixiao Li | Journal of Neuroscience Methods

Stroke is a leading cause of adult disability, and restoring motor function post-stroke is critical to improving the well-being and quality of life of affected individuals. Accurate and timely assessment … Stroke is a leading cause of adult disability, and restoring motor function post-stroke is critical to improving the well-being and quality of life of affected individuals. Accurate and timely assessment of motor function is essential for developing effective rehabilitation strategies and predicting recovery outcomes. Electroencephalography (EEG) offers a non-invasive, real-time monitoring of brain activity, offering personalized insights into motor impairment and recovery. Its simplicity and bedside applicability make EEG a valuable tool and a potential biomarker for brain function. In recent years, the integration of EEG with the brain-computer interface technology and neuromodulation techniques has revolutionized personalized rehabilitation therapy, offering new hope for patients with motor dysfunction following stroke. This review synthesizes evidence on EEG-derived biomarkers and their integration with brain-computer interface and neuromodulation techniques, proposing a framework for personalized rehabilitation strategies in stroke recovery.

Signal Quality Comparison of Wireless Dry and Wired Wet EEG Systems in Driving Conditions

2025-06-20

Seonghyun Kim , Joshua Yang , C.R. Kim +2 more | Transactions of the Korean Society for Noise and Vibration Engineering

NEUROCOGNITIVE STIMULATION IN MILITARY TRAINING: IMPACT ON PERFORMANCE AND EMOTIONAL REGULATION

2025-06-20

Iasmina-Georgiana SAUCIUC | Review of the Air Force Academy/Revista Academiei Forţelor Aeriene "Henri Coandă"

This research investigates the impact of neurocognitive stimulation on performance and emotional regulation in military training. Historically, research has focused on the physical and objective factors of performance, often neglecting … This research investigates the impact of neurocognitive stimulation on performance and emotional regulation in military training. Historically, research has focused on the physical and objective factors of performance, often neglecting the neurocognitive and emotional aspects that are crucial in high-stress operational conditions. The study proposes an integrated approach combining EEG monitoring with non-invasive neurostimulation using the HALO Sport device to assess its impact on focus, emotional regulation, and physical performance. In a simulated military biathlon experiment, participants were exposed to complex tasks under three experimental conditions: no stimulation, active stimulation, and placebo stimulation. The results revealed that neurostimulation with HALO Sport significantly improved cognitive and motor performance while reducing negative emotional responses such as anxiety and enhancing mental resilience. The study demonstrates that neurocognitive stimulation can be an effective method for optimizing military training, contributing to better emotional self-regulation and more efficient operational performance under stress. The findings suggest that this integrated neurocognitive approach could revolutionize military training strategies, fostering a balance between physical and mental performance crucial for critical operational contexts.

AQMFB-DWT: A Preprocessing Technique for Removing Blink Artifacts Before Extracting Pain-evoked Potential EEG

2025-06-20

Wenjia Gao , Dan Liu , Qisong Wang +2 more | Neuroscience Bulletin

EEG Feature Selection Techniques for Epileptic Seizure Detection: Performance and Evaluation Study

2025-06-20

Ali Al Farawn , Salam Al-Khammasi , Ahmed Hazim Alhilali +1 more | International Journal of Mathematics Statistics and Computer Science

Electroencephalography (EEG) is a measuring instrument to measure the electrical activity of the brain observed due to a chemical difference in the brain, “EEG “is regarded as one of the … Electroencephalography (EEG) is a measuring instrument to measure the electrical activity of the brain observed due to a chemical difference in the brain, “EEG “is regarded as one of the most significant procedures for diagnosing epilepsy around the world. Since there are more than 80 million people suffering from this disease around the world, especially in non-developing countries, the goal of the paper is to reduce the dimensions of the data used in classification, by studying and using the feature selection methods when selecting the features that are most relevant to the classification process, by removing irrelevant features, which leads to improved computational efficiency, and helps to detect disease faster and accurately. The results of the study showed that the accuracy value changes every time a feature in the EEG data is deleted. Therefore, in this project we suggested more than one different Techniques to selection the features (MDI method, Correlation coefficient method, SFS, SBS. etc.), Depending on the use of a random forest classification, we find that the accuracy of classification varies from one method to another depending on the omitted features and the extent of their impact, the accuracy of classification in the MDI method ranges from 98.313% to 98.1%, knowing that it reaches 98.504% in the case of using all the features. As for the correlation method, the highest percentage we obtained was 98.4% after deleting only two features. These two methods work without a model, On the other hand, we have methods that work automatically with a model that selects the relevant features accurately. In the SFS method, the classification accuracy values range from 98.6% to 98.212%, after deleting more than nine features, in addition to the SBS method that the ability to maintain a satisfactory classification accuracy, as it is about 98.6% to 98.2%, has been able to delete at least ten features. The feature selection techniques effect in reducing the dimensions of dataset, which means reducing the complexity, and this also has an impact on the cost.

The Development and Validation of EchoCue, a novel tool for assessing Cortical Visual Impairment in uncooperative children, Registered Report - stage I

2025-06-20

Edwige Smague | medRxiv (Cold Spring Harbor Laboratory)

Abstract: This Stage 1 Registered Report presents EchoCue, an innovative tool designed to detect cortical visual impairments in uncooperative children aged 0 to 18, without requiring verbal instruction or active … Abstract: This Stage 1 Registered Report presents EchoCue, an innovative tool designed to detect cortical visual impairments in uncooperative children aged 0 to 18, without requiring verbal instruction or active participation. The protocol delivers extreme-frequency auditory stimuli (very low and high), paired with directional visual flashes. Reflexive responses, such as eye blinks, gaze shifts, pupil dilation, and startle reactions, are recorded using an eye-tracking system and a flexible frontal EEG device. The assessment is entirely passive, standardised, and suitable for children who are otherwise difficult to evaluate using conventional methods.

Contralesional recruitment and localization of EEG signal complexity in stroke: A recurrence quantification analysis of hierarchical motor tasks

2025-06-20

Parikshat Sirpal , Nishaal Parmar , Hazem H. Refai +2 more | Journal of Neural Engineering

Abstract Objective: This study quantifies EEG complexity in chronic hemiparetic stroke patients performing hierarchical motor tasks, examining the degree of contralesional motor resource recruitment in maladaptive neural responses. Approach: We … Abstract Objective: This study quantifies EEG complexity in chronic hemiparetic stroke patients performing hierarchical motor tasks, examining the degree of contralesional motor resource recruitment in maladaptive neural responses. Approach: We applied recurrence quantification analysis (RQA) and nonlinear dynamical measures to examine spatial patterns of motor-related EEG complexity under varying shoulder abduction torque levels (20% and 40%) in both stroke survivors and healthy control participants, enabling comparative analyses of adaptive neural responses. Results: Our findings show a statistically significant increase in EEG signal complexity within the contralesional hemisphere of stroke participants, particularly under higher shoulder abduction loads. Consistent with previous studies, we observed abnormal muscle coactivation patterns between proximal and distal muscles, along with distinct shifts in EMG vector direction in stroke-impaired limbs. These shifts in coactivation patterns suggest constraints in muscle coactivation patterns resulting from losses in corticofugal projections and upregulated brainstem pathways. Significance: We introduce a novel application of RQA to quantify nonlinear EEG complexity during motor execution in chronic stroke. Unlike traditional spectral or connectivity-based EEG methods, RQA quantifies temporally evolving, nonlinear recurrence patterns that reflect maladaptive contralesional motor recruitment. Our findings demonstrate that increased EEG complexity correlates with impaired motor control and reliance on compensatory pathways, offering new insight into neural reorganization after stroke. These results position RQA as a promising, clinically meaningful, and computationally efficient tool to evaluate cortical dynamics and guide targeted neurorehabilitation strategies aimed at minimizing maladaptive plasticity.

Motor imagery decoding and control techniques for virtual robotic hand movement

2025-06-20

Angie J. Valencia-Casteneda , Luciano Santos Constantin Raptopoulos , Max Suell Dutra | Journal of the Brazilian Society of Mechanical Sciences and Engineering