Academic Journal
View in EDS

Adoption of Deep Learning Methods for SSVEP Classification in XR-Based Wearable Brain-Computer Interfaces.

Bibliographic Details
Title: Adoption of Deep Learning Methods for SSVEP Classification in XR-Based Wearable Brain-Computer Interfaces.
Authors: Angrisani L; Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio n. 21, 80125 Naples, Italy., De Benedetto E; Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio n. 21, 80125 Naples, Italy., De Maria A; Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio n. 21, 80125 Naples, Italy., Duraccio L; Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio n. 21, 80125 Naples, Italy., Tedesco A; Department of Public Health, University of Naples Federico II, Via Pansini, 80131 Naples, Italy.
Source: Sensors (Basel, Switzerland) [Sensors (Basel)] 2026 Aug 12; Vol. 26 (16). Date of Electronic Publication: 2026 Aug 12.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: MDPI Country of Publication: Switzerland NLM ID: 101204366 Publication Model: Electronic Cited Medium: Internet ISSN: 1424-8220 (Electronic) Linking ISSN: 14248220 NLM ISO Abbreviation: Sensors (Basel) Subsets: MEDLINE
Imprint Name(s): Original Publication: Basel, Switzerland : MDPI, c2000-
MeSH Terms: Evoked Potentials, Visual*/physiology , Brain-Computer Interfaces* , Deep Learning* , Wearable Electronic Devices*, Humans ; Electroencephalography ; Algorithms ; Signal Processing, Computer-Assisted
Abstract: This paper addresses steady-state visually evoked potential (SSVEP) classification in wearable extended-reality (XR) brain-computer interfaces (BCIs), with a threefold objective. First, it investigates the effectiveness of deep learning (DL)-based SSVEP classification under XR stimulation, where platform-dependent rendering, optical see-through visualization, reduced luminance contrast, and interaction with the real environment may degrade the quality of the elicited EEG response. Second, a metrology-based performance assessment is proposed according to the Guide to the Expression of Uncertainty in Measurement (GUM), with classification accuracy and information transfer rate (ITR) expressed as best estimates with associated standard uncertainties. Finally, EEG channel reduction is analyzed toward lightweight XR-SSVEP implementations. As a representative SSVEP-specific DL model, the SSVEP time-frequency fusion network (SSVEP-TFFNet) is evaluated on an open XR benchmark dataset comprising 30 subjects and 1200 trials acquired using Microsoft HoloLens 2. A subject-independent comparison with filter-bank canonical correlation analysis (FBCCA) is performed, while intra- and inter-subject variability are incorporated into the uncertainty evaluation. Results show that SSVEP-TFFNet outperforms FBCCA under the considered XR conditions. Moreover, reduced 6- and 4-channel configurations preserve performance close to the full 8-channel montage. These findings provide evidence of the potential of suitably selected DL models for XR-based SSVEP classification and support uncertainty-aware, reduced-electrode wearable implementations.
References: Front Neurorobot. 2020 Jun 03;14:25. (PMID: 32581758)
Sensors (Basel). 2024 Nov 03;24(21):. (PMID: 39517980)
J Neural Eng. 2011 Jun;8(3):036027. (PMID: 21566275)
Front Neurosci. 2025 Sep 29;19:1679451. (PMID: 41089660)
Comput Biol Med. 2022 Feb;141:105042. (PMID: 34802710)
Brain Sci. 2020 Sep 28;10(10):. (PMID: 32998379)
Sensors (Basel). 2026 Jan 23;26(3):. (PMID: 41682282)
IEEE Trans Vis Comput Graph. 2020 Mar;26(3):1608-1621. (PMID: 30295623)
J Neural Eng. 2015 Aug;12(4):046008. (PMID: 26035476)
IEEE Trans Biomed Eng. 2011 Jan;58(1):200-6. (PMID: 20729160)
Exp Brain Res. 2001 Apr;137(3-4):346-53. (PMID: 11355381)
J Neural Eng. 2022 May 13;19(3):. (PMID: 35477130)
IEEE Trans Neural Syst Rehabil Eng. 2006 Jun;14(2):234-9. (PMID: 16792302)
Brain Inform. 2023 Aug 4;10(1):20. (PMID: 37540385)
J Neural Eng. 2020 Feb 18;17(1):016066. (PMID: 31614342)
Sensors (Basel). 2023 Jun 28;23(13):. (PMID: 37447849)
Contributed Indexing: Keywords: augmented reality; brain–computer interface (BCI); deep learning; extended reality (XR); measurement; steady-state visually evoked potential (SSVEP); uncertainty; wearable systems
Entry Date(s): Date Created: 20260827 Date Completed: 20260827 Latest Revision: 20260829
Update Code: 20260829
PubMed Central ID: PMC13517239
DOI: 10.3390/s26165102
PMID: 42655412
Database: MEDLINE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=14248220&ISBN=&volume=26&issue=16&date=20260812&spage=&pages=&title=Sensors (Basel, Switzerland)&atitle=Adoption%20of%20Deep%20Learning%20Methods%20for%20SSVEP%20Classification%20in%20XR-Based%20Wearable%20Brain-Computer%20Interfaces.&aulast=Angrisani%20L&id=DOI:10.3390/s26165102
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42655412
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Adoption of Deep Learning Methods for SSVEP Classification in XR-Based Wearable Brain-Computer Interfaces.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Angrisani+L%22">Angrisani L</searchLink>; Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio n. 21, 80125 Naples, Italy.<br /><searchLink fieldCode="AU" term="%22De+Benedetto+E%22">De Benedetto E</searchLink>; Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio n. 21, 80125 Naples, Italy.<br /><searchLink fieldCode="AU" term="%22De+Maria+A%22">De Maria A</searchLink>; Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio n. 21, 80125 Naples, Italy.<br /><searchLink fieldCode="AU" term="%22Duraccio+L%22">Duraccio L</searchLink>; Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio n. 21, 80125 Naples, Italy.<br /><searchLink fieldCode="AU" term="%22Tedesco+A%22">Tedesco A</searchLink>; Department of Public Health, University of Naples Federico II, Via Pansini, 80131 Naples, Italy.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22101204366%22">Sensors (Basel, Switzerland)</searchLink> [Sensors (Basel)] 2026 Aug 12; Vol. 26 (16). <i>Date of Electronic Publication: </i>2026 Aug 12.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22MDPI%22">MDPI </searchLink><i>Country of Publication: </i>Switzerland <i>NLM ID: </i>101204366 <i>Publication Model: </i>Electronic <i>Cited Medium: </i>Internet <i>ISSN: </i>1424-8220 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2214248220%22">14248220 </searchLink><i>NLM ISO Abbreviation: </i>Sensors (Basel) <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Original Publication</i>: Basel, Switzerland : MDPI, c2000-
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Evoked+Potentials%2C+Visual%22">Evoked Potentials, Visual*</searchLink>/<searchLink fieldCode="MM" term="%22Evoked+Potentials%2C+Visual+physiology%22">physiology</searchLink> <br /><searchLink fieldCode="MM" term="%22Brain-Computer+Interfaces%22">Brain-Computer Interfaces*</searchLink> <br /><searchLink fieldCode="MM" term="%22Deep+Learning%22">Deep Learning*</searchLink> <br /><searchLink fieldCode="MM" term="%22Wearable+Electronic+Devices%22">Wearable Electronic Devices*</searchLink><br /><searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Electroencephalography%22">Electroencephalography</searchLink> ; <searchLink fieldCode="MH" term="%22Algorithms%22">Algorithms</searchLink> ; <searchLink fieldCode="MH" term="%22Signal+Processing%2C+Computer-Assisted%22">Signal Processing, Computer-Assisted</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This paper addresses steady-state visually evoked potential (SSVEP) classification in wearable extended-reality (XR) brain-computer interfaces (BCIs), with a threefold objective. First, it investigates the effectiveness of deep learning (DL)-based SSVEP classification under XR stimulation, where platform-dependent rendering, optical see-through visualization, reduced luminance contrast, and interaction with the real environment may degrade the quality of the elicited EEG response. Second, a metrology-based performance assessment is proposed according to the Guide to the Expression of Uncertainty in Measurement (GUM), with classification accuracy and information transfer rate (ITR) expressed as best estimates with associated standard uncertainties. Finally, EEG channel reduction is analyzed toward lightweight XR-SSVEP implementations. As a representative SSVEP-specific DL model, the SSVEP time-frequency fusion network (SSVEP-TFFNet) is evaluated on an open XR benchmark dataset comprising 30 subjects and 1200 trials acquired using Microsoft HoloLens 2. A subject-independent comparison with filter-bank canonical correlation analysis (FBCCA) is performed, while intra- and inter-subject variability are incorporated into the uncertainty evaluation. Results show that SSVEP-TFFNet outperforms FBCCA under the considered XR conditions. Moreover, reduced 6- and 4-channel configurations preserve performance close to the full 8-channel montage. These findings provide evidence of the potential of suitably selected DL models for XR-based SSVEP classification and support uncertainty-aware, reduced-electrode wearable implementations.
– Name: Ref
  Label: References
  Group: RefInfo
  Data: Front Neurorobot. 2020 Jun 03;14:25. (PMID: <searchLink fieldCode="PM" term="%2232581758%22">32581758)</searchLink><br />Sensors (Basel). 2024 Nov 03;24(21):. (PMID: <searchLink fieldCode="PM" term="%2239517980%22">39517980)</searchLink><br />J Neural Eng. 2011 Jun;8(3):036027. (PMID: <searchLink fieldCode="PM" term="%2221566275%22">21566275)</searchLink><br />Front Neurosci. 2025 Sep 29;19:1679451. (PMID: <searchLink fieldCode="PM" term="%2241089660%22">41089660)</searchLink><br />Comput Biol Med. 2022 Feb;141:105042. (PMID: <searchLink fieldCode="PM" term="%2234802710%22">34802710)</searchLink><br />Brain Sci. 2020 Sep 28;10(10):. (PMID: <searchLink fieldCode="PM" term="%2232998379%22">32998379)</searchLink><br />Sensors (Basel). 2026 Jan 23;26(3):. (PMID: <searchLink fieldCode="PM" term="%2241682282%22">41682282)</searchLink><br />IEEE Trans Vis Comput Graph. 2020 Mar;26(3):1608-1621. (PMID: <searchLink fieldCode="PM" term="%2230295623%22">30295623)</searchLink><br />J Neural Eng. 2015 Aug;12(4):046008. (PMID: <searchLink fieldCode="PM" term="%2226035476%22">26035476)</searchLink><br />IEEE Trans Biomed Eng. 2011 Jan;58(1):200-6. (PMID: <searchLink fieldCode="PM" term="%2220729160%22">20729160)</searchLink><br />Exp Brain Res. 2001 Apr;137(3-4):346-53. (PMID: <searchLink fieldCode="PM" term="%2211355381%22">11355381)</searchLink><br />J Neural Eng. 2022 May 13;19(3):. (PMID: <searchLink fieldCode="PM" term="%2235477130%22">35477130)</searchLink><br />IEEE Trans Neural Syst Rehabil Eng. 2006 Jun;14(2):234-9. (PMID: <searchLink fieldCode="PM" term="%2216792302%22">16792302)</searchLink><br />Brain Inform. 2023 Aug 4;10(1):20. (PMID: <searchLink fieldCode="PM" term="%2237540385%22">37540385)</searchLink><br />J Neural Eng. 2020 Feb 18;17(1):016066. (PMID: <searchLink fieldCode="PM" term="%2231614342%22">31614342)</searchLink><br />Sensors (Basel). 2023 Jun 28;23(13):. (PMID: <searchLink fieldCode="PM" term="%2237447849%22">37447849)</searchLink>
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>augmented reality; brain–computer interface (BCI); deep learning; extended reality (XR); measurement; steady-state visually evoked potential (SSVEP); uncertainty; wearable systems
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260827 <i>Date Completed: </i>20260827 <i>Latest Revision: </i>20260829
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260829
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13517239
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.3390/s26165102
– Name: AN
  Label: PMID
  Group: ID
  Data: 42655412
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42655412
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/s26165102
    Languages:
      – Code: eng
        Text: English
    Subjects:
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Electroencephalography
        Type: general
      – SubjectFull: Algorithms
        Type: general
      – SubjectFull: Signal Processing, Computer-Assisted
        Type: general
      – SubjectFull: Evoked Potentials, Visual physiology
        Type: general
      – SubjectFull: Brain-Computer Interfaces
        Type: general
      – SubjectFull: Deep Learning
        Type: general
      – SubjectFull: Wearable Electronic Devices
        Type: general
    Titles:
      – TitleFull: Adoption of Deep Learning Methods for SSVEP Classification in XR-Based Wearable Brain-Computer Interfaces.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Angrisani L
      – PersonEntity:
          Name:
            NameFull: De Benedetto E
      – PersonEntity:
          Name:
            NameFull: De Maria A
      – PersonEntity:
          Name:
            NameFull: Duraccio L
      – PersonEntity:
          Name:
            NameFull: Tedesco A
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 12
              M: 08
              Text: 2026 Aug 12
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1424-8220
          Numbering:
            – Type: volume
              Value: 26
            – Type: issue
              Value: 16
          Titles:
            – TitleFull: Sensors (Basel, Switzerland)
              Type: main
ResultId 1