EEGdenoiseNet/datacite.yml

# Metadata for DOI registration according to DataCite Metadata Schema 4.1.
# For detailed schema description see https://doi.org/10.5438/0014

## Required fields

# The main researchers involved. Include digital identifier (e.g., ORCID)
# if possible, including the prefix to indicate its type.
authors:
  -
    firstname: "Haoming"
    lastname: "Zhang"
    affiliation: "Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen 518055, P.R. China"
  -
    firstname: "Mingqi"
    lastname: "Zhao"
    affiliation: "Movement Control and Neuroplasticity Research Group, KU Leuven, Leuven 3001, Belgium"
  -
    firstname: "Chen"
    lastname: "Wei"
    affiliation: "Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen 518055, P.R. China"
  -
    firstname: "Dante"
    lastname: "Mantini"
    affiliation: "Movement Control and Neuroplasticity Research Group, KU Leuven, Leuven 3001, Belgium"
  -
    firstname: "Zherui"
    lastname: "Li"
    affiliation: "Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen 518055, P.R. China"
  -
    firstname: "Quanying"
    lastname: "Liu"
    affiliation: "Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen 518055, P.R. China"

# A title to describe the published resource.
title: "EEGdenoiseNet: A benchmark dataset for deep learning solutions of EEG denoising"

# Additional information about the resource, e.g., a brief abstract.
description: |
  Deep learning networks are increasingly attracting attention in various fields, including electroencephalography (EEG) signal processing. These models provided comparable performance with that of traditional techniques. At present, however, lacks of well-structured and standardized datasets with specific benchmark limit the development of deep learning solutions for EEG denoising. Here, we present EEGdenoiseNet, a benchmark EEG dataset that is suited for training and testing deep learning-based denoising models, as well as for performance comparisons across models. EEGdenoiseNet contains 4514 clean EEG epochs, 3400 ocular artifact epochs and 5598 muscular artifact epochs, allowing users to synthesize noisy EEG epochs with the ground-truth clean EEG. We used EEGdenoiseNet to evaluate denoising performance of four classical networks (a fully-connected network, a simple and a complex convolution network, and a recurrent neural network). Our analysis suggested that deep learning methods have great potential for EEG denoising even under high noise contamination. Through EEGdenoiseNet, we hope to accelerate the development of the emerging field of deep learning-based EEG denoising.

# Lit of keywords the resource should be associated with.
# Give as many keywords as possible, to make the resource findable.
keywords:
  - Neuroscience
  - EEG
  - Artifact removal
  - Deep Learning Network

# License information for this resource. Please provide the license name and/or a link to the license.
# Please add also a corresponding LICENSE file to the repository.
license:
  name: "Creative Commons CC0 1.0 Public Domain Dedication"
  url: "https://creativecommons.org/publicdomain/zero/1.0/"


# Related publications. reftype might be: IsSupplementTo, IsDescribedBy, IsReferencedBy.
# Please provide digital identifier (e.g., DOI) if possible.
# Add a prefix to the ID, separated by a colon, to indicate the source.
# Supported sources are: DOI, arXiv, PMID
# In the citation field, please provide the full reference, including title, authors, journal etc.



# Resource type. Default is Dataset, other possible values are Software, DataPaper, Image, Text.
resourcetype: Dataset

# Do not edit or remove the following line
templateversion: 1.2