Academic Journal
View in EDS

Unsupervised Dynamic Time Warping Clustering for Robust Functional Network Identification in fNIRS Motor Tasks.

Bibliographic Details
Title: Unsupervised Dynamic Time Warping Clustering for Robust Functional Network Identification in fNIRS Motor Tasks.
Authors: Althobaiti M; Biomedical Engineering Department, College of Engineering, Imam Abdulrahman Bin Faisal University, Dammam 31441, Saudi Arabia.
Source: Sensors (Basel, Switzerland) [Sensors (Basel)] 2026 Mar 15; Vol. 26 (6). Date of Electronic Publication: 2026 Mar 15.
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: Brain-Computer Interfaces* , Clustering Algorithms*, Spectroscopy, Near-Infrared/methods ; Humans ; Algorithms ; Cluster Analysis ; Signal Processing, Computer-Assisted
Abstract: Functional near-infrared spectroscopy (fNIRS) is a valuable non-invasive modality for brain-computer interfaces (BCIs), but robust signal interpretation is challenged by the significant temporal variability of the hemodynamic response. Standard linear methods, such as Pearson correlation, often fail to capture functional connectivity when signals exhibit temporal jitter. This study validates an unsupervised Dynamic Time Warping (DTW) clustering framework to robustly identify motor networks from fNIRS data by accommodating non-linear temporal shifts. We analyzed a public fNIRS dataset (N = 30) across right-hand (RHT), left-hand (LHT), and foot tapping (FT) tasks. A robust preprocessing pipeline was implemented, including Wavelet Motion Correction and Common Average Referencing (CAR) to remove artifacts and global systemic noise. The core method involved computing Z-score normalized DTW distance matrices, followed by hierarchical clustering. To validate the framework, we benchmarked it against a standard Pearson Correlation method. Results show that the unsupervised DTW framework achieved a network identification accuracy of 53.17%, significantly outperforming the standard Pearson correlation benchmark (48.06%) with a statistically significant difference (p < 0.05). The framework successfully detected distinct, somatotopically correct modulations: superior-medial activation during foot tapping and lateralized activation during hand tapping. These findings demonstrate that unsupervised DTW clustering is a robust, data-driven approach that outperforms conventional linear methods in capturing functional networks during motor tasks, showing significant potential for next-generation asynchronous BCIs.
Contributed Indexing: Keywords: Dynamic Time Warping; brain-computer interface; fNIRS; functional connectivity; motor cortex
Entry Date(s): Date Created: 20260328 Date Completed: 20260713 Latest Revision: 20260714
Update Code: 20260715
PubMed Central ID: PMC13030481
DOI: 10.3390/s26061848
PMID: 41902016
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=6&date=20260315&spage=&pages=&title=Sensors (Basel, Switzerland)&atitle=Unsupervised%20Dynamic%20Time%20Warping%20Clustering%20for%20Robust%20Functional%20Network%20Identification%20in%20fNIRS%20Motor%20Tasks.&aulast=Althobaiti%20M&id=DOI:10.3390/s26061848
    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: 41902016
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Unsupervised Dynamic Time Warping Clustering for Robust Functional Network Identification in fNIRS Motor Tasks.
– Name: Author
  Label: Authors
  Group: Au
  Data: &lt;searchLink fieldCode=&quot;AU&quot; term=&quot;%22Althobaiti+M%22&quot;&gt;Althobaiti M&lt;/searchLink&gt;; Biomedical Engineering Department, College of Engineering, Imam Abdulrahman Bin Faisal University, Dammam 31441, Saudi Arabia.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: &lt;searchLink fieldCode=&quot;JN&quot; term=&quot;%22101204366%22&quot;&gt;Sensors (Basel, Switzerland)&lt;/searchLink&gt; [Sensors (Basel)] 2026 Mar 15; Vol. 26 (6). &lt;i&gt;Date of Electronic Publication: &lt;/i&gt;2026 Mar 15.
– 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: &lt;i&gt;Publisher: &lt;/i&gt;&lt;searchLink fieldCode=&quot;PB&quot; term=&quot;%22MDPI%22&quot;&gt;MDPI &lt;/searchLink&gt;&lt;i&gt;Country of Publication: &lt;/i&gt;Switzerland &lt;i&gt;NLM ID: &lt;/i&gt;101204366 &lt;i&gt;Publication Model: &lt;/i&gt;Electronic &lt;i&gt;Cited Medium: &lt;/i&gt;Internet &lt;i&gt;ISSN: &lt;/i&gt;1424-8220 (Electronic) &lt;i&gt;Linking ISSN: &lt;/i&gt;&lt;searchLink fieldCode=&quot;IS&quot; term=&quot;%2214248220%22&quot;&gt;14248220 &lt;/searchLink&gt;&lt;i&gt;NLM ISO Abbreviation: &lt;/i&gt;Sensors (Basel) &lt;i&gt;Subsets: &lt;/i&gt;MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: &lt;i&gt;Original Publication&lt;/i&gt;: Basel, Switzerland : MDPI, c2000-
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: &lt;searchLink fieldCode=&quot;MM&quot; term=&quot;%22Brain-Computer+Interfaces%22&quot;&gt;Brain-Computer Interfaces*&lt;/searchLink&gt; &lt;br /&gt;&lt;searchLink fieldCode=&quot;MM&quot; term=&quot;%22Clustering+Algorithms%22&quot;&gt;Clustering Algorithms*&lt;/searchLink&gt;&lt;br /&gt;&lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Spectroscopy%2C+Near-Infrared%22&quot;&gt;Spectroscopy, Near-Infrared&lt;/searchLink&gt;/&lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Spectroscopy%2C+Near-Infrared+methods%22&quot;&gt;methods&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Humans%22&quot;&gt;Humans&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Algorithms%22&quot;&gt;Algorithms&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Cluster+Analysis%22&quot;&gt;Cluster Analysis&lt;/searchLink&gt; ; &lt;searchLink fieldCode=&quot;MH&quot; term=&quot;%22Signal+Processing%2C+Computer-Assisted%22&quot;&gt;Signal Processing, Computer-Assisted&lt;/searchLink&gt;
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Functional near-infrared spectroscopy (fNIRS) is a valuable non-invasive modality for brain-computer interfaces (BCIs), but robust signal interpretation is challenged by the significant temporal variability of the hemodynamic response. Standard linear methods, such as Pearson correlation, often fail to capture functional connectivity when signals exhibit temporal jitter. This study validates an unsupervised Dynamic Time Warping (DTW) clustering framework to robustly identify motor networks from fNIRS data by accommodating non-linear temporal shifts. We analyzed a public fNIRS dataset (N = 30) across right-hand (RHT), left-hand (LHT), and foot tapping (FT) tasks. A robust preprocessing pipeline was implemented, including Wavelet Motion Correction and Common Average Referencing (CAR) to remove artifacts and global systemic noise. The core method involved computing Z-score normalized DTW distance matrices, followed by hierarchical clustering. To validate the framework, we benchmarked it against a standard Pearson Correlation method. Results show that the unsupervised DTW framework achieved a network identification accuracy of 53.17%, significantly outperforming the standard Pearson correlation benchmark (48.06%) with a statistically significant difference (p &amp;lt; 0.05). The framework successfully detected distinct, somatotopically correct modulations: superior-medial activation during foot tapping and lateralized activation during hand tapping. These findings demonstrate that unsupervised DTW clustering is a robust, data-driven approach that outperforms conventional linear methods in capturing functional networks during motor tasks, showing significant potential for next-generation asynchronous BCIs.
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: &lt;i&gt;Keywords: &lt;/i&gt;Dynamic Time Warping; brain-computer interface; fNIRS; functional connectivity; motor cortex
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: &lt;i&gt;Date Created: &lt;/i&gt;20260328 &lt;i&gt;Date Completed: &lt;/i&gt;20260713 &lt;i&gt;Latest Revision: &lt;/i&gt;20260714
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260715
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13030481
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.3390/s26061848
– Name: AN
  Label: PMID
  Group: ID
  Data: 41902016
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=41902016
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/s26061848
    Languages:
      – Code: eng
        Text: English
    Subjects:
      – SubjectFull: Spectroscopy, Near-Infrared methods
        Type: general
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Algorithms
        Type: general
      – SubjectFull: Cluster Analysis
        Type: general
      – SubjectFull: Signal Processing, Computer-Assisted
        Type: general
      – SubjectFull: Brain-Computer Interfaces
        Type: general
      – SubjectFull: Clustering Algorithms
        Type: general
    Titles:
      – TitleFull: Unsupervised Dynamic Time Warping Clustering for Robust Functional Network Identification in fNIRS Motor Tasks.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Althobaiti M
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 03
              Text: 2026 Mar 15
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1424-8220
          Numbering:
            – Type: volume
              Value: 26
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Sensors (Basel, Switzerland)
              Type: main
ResultId 1