Comparing user-dependent and user-independent training of CNN for SSVEP BCI.

Abstract:

OBJECTIVE:We presented a comparative study on the training methodologies of a convolutional neural network (CNN) for the detection of steady-state visually evoked potentials (SSVEP). Two training scenarios were also compared: user-independent (UI) training and user-dependent (UD) training. APPROACH:The CNN was trained in both UD and UI scenarios on two types of features for SSVEP classification: magnitude spectrum features (M-CNN) and complex spectrum features (C-CNN). The canonical correlation analysis (CCA), widely used in SSVEP processing, was used as the baseline. Additional comparisons were performed with task-related components analysis (TRCA) and filter-bank canonical correlation analysis (FBCCA). The performance of the proposed CNN pipelines, CCA, FBCCA and TRCA were evaluated with two datasets: a seven-class SSVEP dataset collected on 21 healthy participants and a twelve-class publicly available SSVEP dataset collected on ten healthy participants. MAIN RESULTS:The UD based training methods consistently outperformed the UI methods when all other conditions were the same, as one would expect. However, the proposed UI-C-CNN approach performed similarly to the UD-M-CNN across all cases investigated on both datasets. On Dataset 1, the average accuracies of the different methods for 1 s window length were: CCA: 69.1%  ±  10.8%, TRCA: 13.4%  ±  1.5%, FBCCA: 64.8%  ±  15.6%, UI-M-CNN: 73.5%  ±  16.1%, UI-C-CNN: 81.6%  ±  12.3%, UD-M-CNN: 87.8%  ±  7.6% and UD-C-CNN: 92.5%  ±  5%. On Dataset 2, the average accuracies of the different methods for data length of 1 s were: UD-C-CNN: 92.33%  ±  11.1%, UD-M-CNN: 82.77%  ±  16.7%, UI-C-CNN: 81.6%  ±  18%, UI-M-CNN: 70.5%  ±  22%, FBCCA: 67.1%  ±  21%, CCA: 62.7%  ±  21.5%, TRCA: 40.4%  ±  14%. Using t-SNE, visualizing the features extracted by the CNN pipelines further revealed that the C-CNN method likely learned both the amplitude and phase related information from the SSVEP data for classification, resulting in superior performance than the M-CNN methods. The results suggested that UI-C-CNN method proposed in this study offers a good balance between performance and cost of training data. SIGNIFICANCE:The proposed C-CNN based method is a suitable candidate for SSVEP-based BCIs and provides an improved performance in both UD and UI training scenarios.

journal_name

J Neural Eng

authors

Ravi A,Beni NH,Manuel J,Jiang N

doi

10.1088/1741-2552/ab6a67

subject

Has Abstract

pub_date

2020-04-08 00:00:00

pages

026028

issue

2

eissn

1741-2560

issn

1741-2552

journal_volume

17

pub_type

杂志文章
  • In vivo feasibility of epiretinal stimulation using ultrananocrystalline diamond electrodes.

    abstract:OBJECTIVE:Due to their increased proximity to retinal ganglion cells (RGCs), epiretinal visual prostheses present the opportunity for eliciting phosphenes with low thresholds through direct RGC activation. This study characterised the in vivo performance of a novel prototype monolithic epiretinal prosthesis, containing...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/aba560

    authors: Shivdasani MN,Evans M,Burns O,Yeoh J,Allen PJ,Nayagam DAX,Villalobos J,Abbott CJ,Luu CD,Opie NL,Sabu A,Saunders AL,McPhedran M,Cardamone L,McGowan C,Maxim V,Williams RA,Fox KE,Cicione R,Garrett DJ,Ahnood A,Ganes

    更新日期:2020-08-05 00:00:00

  • Dual stream neural networks for brain signal classification.

    abstract::In this paper we propose a dual stream neural network (DSNN) for classifying arbitrary collections of functional neuroimaging signals for the purpose of brain computer interfaces (BCIs). In the DSNN the first stream is an end-to-end classifier taking raw time-dependent signals as input and generating feature identific...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/abc903

    authors: Kuang D,Michoski C

    更新日期:2020-11-10 00:00:00

  • On robust parameter estimation in brain-computer interfacing.

    abstract:OBJECTIVE:The reliable estimation of parameters such as mean or covariance matrix from noisy and high-dimensional observations is a prerequisite for successful application of signal processing and machine learning algorithms in brain-computer interfacing (BCI). This challenging task becomes significantly more difficult...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/aa8232

    authors: Samek W,Nakajima S,Kawanabe M,Müller KR

    更新日期:2017-12-01 00:00:00

  • Decoding spoken English from intracortical electrode arrays in dorsal precentral gyrus.

    abstract:OBJECTIVE:To evaluate the potential of intracortical electrode array signals for brain-computer interfaces (BCIs) to restore lost speech, we measured the performance of decoders trained to discriminate a comprehensive basis set of 39 English phonemes and to synthesize speech sounds via a neural pattern matching method....

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/abbfef

    authors: Wilson GH,Stavisky SD,Willett FR,Avansino DT,Kelemen JN,Hochberg LR,Henderson JM,Druckmann S,Shenoy KV

    更新日期:2020-11-25 00:00:00

  • Neuromusculoskeletal model self-calibration for on-line sequential bayesian moment estimation.

    abstract:OBJECTIVE:Neuromusculoskeletal models involve many subject-specific physiological parameters that need to be adjusted to adequately represent muscle properties. Traditionally, neuromusculoskeletal models have been calibrated with a forward-inverse dynamic optimization which is time-consuming and unfeasible for rehabili...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/aa58f5

    authors: Bueno DR,Montano L

    更新日期:2017-04-01 00:00:00

  • Exploring non-stationarity patterns in schizophrenia: neural reorganization abnormalities in the alpha band.

    abstract:OBJECTIVE:The aim of this paper was to characterize brain non-stationarity during an auditory oddball task in schizophrenia (SCH). The level of non-stationarity was measured in the baseline and response windows of relevant tones in SCH patients and healthy controls. APPROACH:Event-related potentials were recorded from...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/aa6e05

    authors: Núñez P,Poza J,Bachiller A,Gomez-Pilar J,Lubeiro A,Molina V,Hornero R

    更新日期:2017-08-01 00:00:00

  • Decoding overt shifts of attention in depth through pupillary and cortical frequency tagging.

    abstract:OBJECTIVE:We have recently developed a prototype of a novel human-computer interface for assistive communication based on voluntary shifts of attention (gaze) from a far target to a near target associated with a decrease of pupil size (Pupillary Accommodative Response, PAR), an automatic vegetative response that can be...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/ab8e8f

    authors: de'Sperati C,Roatta S,Zovetti N,Baroni T

    更新日期:2020-04-29 00:00:00

  • Intraneural sensory feedback restores grip force control and motor coordination while using a prosthetic hand.

    abstract:OBJECTIVE:Tactile afferents in the human hand provide fundamental information about hand-environment interactions, which is used by the brain to adapt the motor output to the physical properties of the object being manipulated. A hand amputation disrupts both afferent and efferent pathways from/to the hand, completely ...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章,随机对照试验

    doi:10.1088/1741-2552/ab059b

    authors: Clemente F,Valle G,Controzzi M,Strauss I,Iberite F,Stieglitz T,Granata G,Rossini PM,Petrini F,Micera S,Cipriani C

    更新日期:2019-04-01 00:00:00

  • Dilation of the oropharynx via selective stimulation of the hypoglossal nerve.

    abstract::The functional effects of selective hypoglossal nerve (HG) stimulation with a multi-contact peripheral nerve electrode were assessed using images of the upper airways and the tongue in anesthetized beagles. A biphasic pulse train of 50 Hz frequency and 2 s duration was applied through each one of the tripolar contact ...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2560/2/4/002

    authors: Huang J,Sahin M,Durand DM

    更新日期:2005-12-01 00:00:00

  • Consistency of quantitative electroencephalography features in a large clinical data set.

    abstract:OBJECTIVE:Despite their increasing use and public health importance, little is known about the consistency and variability of the quantitative features of baseline electroencephalography (EEG) measurements in healthy individuals and populations. This study aims to investigate population consistency of EEG features. AP...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/ab4af3

    authors: Nahmias DO,Kontson KL,Soltysik DA,Civillico EF

    更新日期:2019-11-12 00:00:00

  • Intraspinal stimulation with a silicon-based 3D chronic microelectrode array for bladder voiding in cats.

    abstract:OBJECTIVE:Bladder dysfunction is a significant and largely unaddressed problem for people living with spinal cord injury. Intermittent catheterization does not provide volitional control of micturition and has numerous side effects. Targeted electrical microstimulation of the spinal cord has been previously explored fo...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/abca13

    authors: Pikov V,McCreery DB,Han M

    更新日期:2020-11-12 00:00:00

  • The statistical distribution of noisy transmission in human sensors.

    abstract:OBJECTIVE:Brains, like other physical devices, are inherently noisy. This source of variability is large, to the extent that internal noise often impacts human sensory processing more than externally induced (stimulus-driven) perturbations. Despite the fundamental nature of this phenomenon, its statistical distribution...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章,随机对照试验

    doi:10.1088/1741-2560/10/1/016014

    authors: Neri P

    更新日期:2013-02-01 00:00:00

  • Early seizure detection for closed loop direct neurostimulation devices in epilepsy.

    abstract::Current treatment concepts for epilepsy are based on continuous drug delivery or electrical stimulation to prevent the occurrence of seizures, exposing the brain and body to a mostly unneeded risk of adverse effects. To address the infrequent occurrence and short duration of epileptic seizures, intelligent implantable...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章,评审

    doi:10.1088/1741-2552/ab094a

    authors: Dümpelmann M

    更新日期:2019-08-01 00:00:00

  • Concurrent control of a brain-computer interface and natural overt movements.

    abstract:OBJECTIVE:A primary control signal in brain-computer interfaces (BCIs) have been cortical signals related to movement. However, in cases where natural motor function remains, BCI control signals may interfere with other possibly simultaneous activity for useful ongoing movement. We sought to determine if the brain coul...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/aadf3d

    authors: Bashford L,Wu J,Sarma D,Collins K,Rao RPN,Ojemann JG,Mehring C

    更新日期:2018-12-01 00:00:00

  • Applying dynamic data collection to improve dry electrode system performance for a P300-based brain-computer interface.

    abstract:OBJECTIVE:Dry electrodes have an advantage over gel-based 'wet' electrodes by providing quicker set-up time for electroencephalography recording; however, the potentially poorer contact can result in noisier recordings. We examine the impact that this may have on brain-computer interface communication and potential app...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2560/13/6/066018

    authors: Clements JM,Sellers EW,Ryan DB,Caves K,Collins LM,Throckmorton CS

    更新日期:2016-12-01 00:00:00

  • Remapping cortical modulation for electrocorticographic brain-computer interfaces: a somatotopy-based approach in individuals with upper-limb paralysis.

    abstract:OBJECTIVE:Brain-computer interface (BCI) technology aims to provide individuals with paralysis a means to restore function. Electrocorticography (ECoG) uses disc electrodes placed on either the surface of the dura or the cortex to record field potential activity. ECoG has been proposed as a viable neural recording moda...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/aa9bfb

    authors: Degenhart AD,Hiremath SV,Yang Y,Foldes S,Collinger JL,Boninger M,Tyler-Kabara EC,Wang W

    更新日期:2018-04-01 00:00:00

  • An intra-operative feature-based classification of microelectrode recordings to support the subthalamic nucleus functional identification during deep brain stimulation surgery.

    abstract:OBJECTIVE:The Subthalamic Nucleus (STN) is the most selected target for the placement of the Deep Brain Stimulation (DBS) electrode to treat Parkinson's disease. Its identification is a delicate and challenging task which is based on the interpretation of the STN functional activity acquired through microelectrode reco...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/abcb15

    authors: Coelli S,Levi V,Del Vecchio Del Vecchio J,Mailland E,Rinaldo S,Eleopra R,Bianchi AM

    更新日期:2020-11-17 00:00:00

  • Achieving a hybrid brain-computer interface with tactile selective attention and motor imagery.

    abstract:OBJECTIVE:We propose a new hybrid brain-computer interface (BCI) system that integrates two different EEG tasks: tactile selective attention (TSA) using a vibro-tactile stimulator on the left/right finger and motor imagery (MI) of left/right hand movement. Event-related desynchronization (ERD) from the MI task and stea...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章,随机对照试验

    doi:10.1088/1741-2560/11/6/066004

    authors: Ahn S,Ahn M,Cho H,Chan Jun S

    更新日期:2014-12-01 00:00:00

  • Computationally inexpensive enhanced growing neural gas algorithm for real-time adaptive neural spike clustering.

    abstract:OBJECTIVE:Real-time closed-loop neural feedback control requires the analysis of action potential traces within several milliseconds after they have been recorded from the brain. The current generation of spike clustering algorithms were mostly designed for off-line use and also require a significant amount of computat...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/ab208c

    authors: Mohammadi Z,Kincaid JM,Pun SH,Klug A,Liu C,Lei TC

    更新日期:2019-07-30 00:00:00

  • Neural engineering: the process, applications, and its role in the future of medicine.

    abstract:OBJECTIVE:Recent advances in neural engineering have restored mobility to people with paralysis, relieved symptoms of movement disorders, reduced chronic pain, restored the sense of hearing, and provided sensory perception to individuals with sensory deficits. APPROACH:This progress was enabled by the team-based, inte...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章,评审

    doi:10.1088/1741-2552/ab4869

    authors: Ereifej ES,Shell CE,Schofield JS,Charkhkar H,Cuberovic I,Dorval AD,Graczyk EL,Kozai TDY,Otto KJ,Tyler DJ,Welle CG,Widge AS,Zariffa J,Moritz CT,Bourbeau DJ,Marasco PD

    更新日期:2019-11-12 00:00:00

  • Common time-frequency analysis of local field potential and pyramidal cell activity in seizure-like events of the rat hippocampus.

    abstract::To study cell-field dynamics, physiologists simultaneously record local field potentials and the activity of individual cells from animals performing cognitive tasks, during various brain states or under pathological conditions. However, apart from spike shape and spike timing analyses, few studies have focused on elu...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2560/8/4/046024

    authors: Cotic M,Chiu AW,Jahromi SS,Carlen PL,Bardakjian BL

    更新日期:2011-08-01 00:00:00

  • Direct activation of zebrafish neurons by ultrasonic stimulation revealed by whole CNS calcium imaging.

    abstract:OBJECTIVE:Ultrasounds (US) use in neural engineering is so far mainly limited to ablation through high intensity focused ultrasound, but interesting preliminary results show that low intensity low frequency ultrasound could be used instead to modulate neural activity. However, the extent of this modulatory ability of U...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/abae8b

    authors: Meneghetti N,Dedola F,Gavryusev V,Sancataldo G,Turrini L,de Vito G,Tiso N,Vanzi F,Carpaneto J,Cutrone A,Pavone FS,Micera S,Mazzoni A

    更新日期:2020-10-14 00:00:00

  • Stem cells from human exfoliated deciduous teeth differentiate toward neural cells in a medium dynamically cultured with Schwann cells in a series of polydimethylsiloxanes scaffolds.

    abstract:OBJECTIVE:Schwann cells (SCs) are primary structural and functional cells in the peripheral nervous system. These cells play a crucial role in peripheral nerve regeneration by releasing neurotrophic factors. This study evaluated the neural differentiation potential effects of stem cells from human exfoliated deciduous ...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2560/13/4/046005

    authors: Su WT,Pan YJ

    更新日期:2016-08-01 00:00:00

  • Real-time, time-frequency mapping of event-related cortical activation.

    abstract::Functional mapping of eloquent cortex is a common and necessary component of neurosurgical operative planning. Current electrical stimulation-based techniques are inefficient, can evoke seizures and are prone to false-negative results. Here, we present a novel cortical mapping system that extracts event-related neural...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2560/9/4/046018

    authors: Cheung C,Chang EF

    更新日期:2012-08-01 00:00:00

  • Millimeter-scale epileptiform spike propagation patterns and their relationship to seizures.

    abstract:OBJECTIVE:Current mapping of epileptic networks in patients prior to epilepsy surgery utilizes electrode arrays with sparse spatial sampling (∼1.0 cm inter-electrode spacing). Recent research demonstrates that sub-millimeter, cortical-column-scale domains have a role in seizure generation that may be clinically signifi...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2560/13/2/026015

    authors: Vanleer AC,Blanco JA,Wagenaar JB,Viventi J,Contreras D,Litt B

    更新日期:2016-04-01 00:00:00

  • High-fidelity vibrokinetic stimulation induces sustained changes in intercortical coherence during a cinematic experience.

    abstract:OBJECTIVE:High-fidelity vibrokinetic (HFVK) technology is widely used to enhance the immersiveness of audiovisual (AV) entertainment experiences. However, despite evidence that HFVK technology does subjectively enhance AV immersion, the underlying mechanism has not been clarified. Neurophysiological studies could provi...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2552/abaca2

    authors: Boasen J,Giroux F,Duchesneau MO,Sénécal S,Léger PM,Ménard JF

    更新日期:2020-09-26 00:00:00

  • A neurorobotic platform for locomotor prosthetic development in rats and mice.

    abstract:OBJECTIVES:We aimed to develop a robotic interface capable of providing finely-tuned, multidirectional trunk assistance adjusted in real-time during unconstrained locomotion in rats and mice. APPROACH:We interfaced a large-scale robotic structure actuated in four degrees of freedom to exchangeable attachment modules e...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2560/13/2/026007

    authors: von Zitzewitz J,Asboth L,Fumeaux N,Hasse A,Baud L,Vallery H,Courtine G

    更新日期:2016-04-01 00:00:00

  • DataHigh: graphical user interface for visualizing and interacting with high-dimensional neural activity.

    abstract:OBJECTIVE:Analyzing and interpreting the activity of a heterogeneous population of neurons can be challenging, especially as the number of neurons, experimental trials, and experimental conditions increases. One approach is to extract a set of latent variables that succinctly captures the prominent co-fluctuation patte...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2560/10/6/066012

    authors: Cowley BR,Kaufman MT,Butler ZS,Churchland MM,Ryu SI,Shenoy KV,Yu BM

    更新日期:2013-12-01 00:00:00

  • Performance measurement for brain-computer or brain-machine interfaces: a tutorial.

    abstract:OBJECTIVE:Brain-computer interfaces (BCIs) have the potential to be valuable clinical tools. However, the varied nature of BCIs, combined with the large number of laboratories participating in BCI research, makes uniform performance reporting difficult. To address this situation, we present a tutorial on performance me...

    journal_title:Journal of neural engineering

    pub_type: 杂志文章

    doi:10.1088/1741-2560/11/3/035001

    authors: Thompson DE,Quitadamo LR,Mainardi L,Laghari KU,Gao S,Kindermans PJ,Simeral JD,Fazel-Rezai R,Matteucci M,Falk TH,Bianchi L,Chestek CA,Huggins JE

    更新日期:2014-06-01 00:00:00

  • Comment on 'fast attainment of computer cursor control with noninvasively acquired brain signals'.

    abstract::In a recent paper by Bradberry, Gentili and Contreras-Vidal published in Journal of Neural Engineering (2011, 8 036010), an interesting method for the control of a two-dimensional mouse cursor was proposed, which apparently attained excellent control and good speed with relatively simple techniques. We believe some of...

    journal_title:Journal of neural engineering

    pub_type: 评论,杂志文章

    doi:10.1088/1741-2560/8/5/058001

    authors: Poli R,Salvaris M

    更新日期:2011-10-01 00:00:00