Näytä suppeat kuvailutiedot

dc.contributor.authorHu, Guoqiang
dc.contributor.authorZhou, Tianyi
dc.contributor.authorLuo, Siwen
dc.contributor.authorMahini, Reza
dc.contributor.authorXu, Jing
dc.contributor.authorChang, Yi
dc.contributor.authorCong, Fengyu
dc.date.accessioned2020-08-05T05:14:06Z
dc.date.available2020-08-05T05:14:06Z
dc.date.issued2020
dc.identifier.citationHu, G., Zhou, T., Luo, S., Mahini, R., Xu, J., Chang, Y., & Cong, F. (2020). Assessment of nonnegative matrix factorization algorithms for electroencephalography spectral analysis. <i>Biomedical Engineering Online</i>, <i>19</i>, Article 61. <a href="https://doi.org/10.1186/s12938-020-00796-x" target="_blank">https://doi.org/10.1186/s12938-020-00796-x</a>
dc.identifier.otherCONVID_41682898
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/71329
dc.description.abstractBackground Nonnegative matrix factorization (NMF) has been successfully used for electroencephalography (EEG) spectral analysis. Since NMF was proposed in the 1990s, many adaptive algorithms have been developed. However, the performance of their use in EEG data analysis has not been fully compared. Here, we provide a comparison of four NMF algorithms in terms of accuracy of estimation, stability (repeatability of the results) and time complexity of algorithms with simulated data. In the practical application of NMF algorithms, stability plays an important role, which was an emphasis in the comparison. A Hierarchical clustering algorithm was implemented to evaluate the stability of NMF algorithms. Results In simulation-based comprehensive analysis of fit, stability, accuracy of estimation and time complexity, hierarchical alternating least squares (HALS) low-rank NMF algorithm (lraNMF_HALS) outperformed the other three NMF algorithms. In the application of lraNMF_HALS for real resting-state EEG data analysis, stable and interpretable features were extracted. Conclusion Based on the results of assessment, our recommendation is to use lraNMF_HALS, providing the most accurate and robust estimation.en
dc.format.mimetypeapplication/pdf
dc.languageeng
dc.language.isoeng
dc.publisherBioMed Central
dc.relation.ispartofseriesBiomedical Engineering Online
dc.rightsCC BY 4.0
dc.subject.othernonnegative matrix factorization
dc.subject.otherstability
dc.subject.otherclustering
dc.subject.otherEEG
dc.titleAssessment of nonnegative matrix factorization algorithms for electroencephalography spectral analysis
dc.typearticle
dc.identifier.urnURN:NBN:fi:jyu-202008055474
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.contributor.oppiaineTietotekniikkafi
dc.contributor.oppiaineMathematical Information Technologyen
dc.type.urihttp://purl.org/eprint/type/JournalArticle
dc.type.coarhttp://purl.org/coar/resource_type/c_2df8fbb1
dc.description.reviewstatuspeerReviewed
dc.relation.issn1475-925X
dc.relation.volume19
dc.type.versionpublishedVersion
dc.rights.copyright© The Author(s) 2020
dc.rights.accesslevelopenAccessfi
dc.subject.ysospektrianalyysi
dc.subject.ysoalgoritmit
dc.subject.ysoEEG
dc.subject.ysoklusterit
dc.subject.ysostabiilius (muuttumattomuus)
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p23978
jyx.subject.urihttp://www.yso.fi/onto/yso/p14524
jyx.subject.urihttp://www.yso.fi/onto/yso/p3328
jyx.subject.urihttp://www.yso.fi/onto/yso/p18755
jyx.subject.urihttp://www.yso.fi/onto/yso/p38304
dc.rights.urlhttps://creativecommons.org/licenses/by/4.0/
dc.relation.doi10.1186/s12938-020-00796-x
jyx.fundinginformationThis work was supported by National Natural Science Foundation of China (Grant Nos. 91748105 & 81471742) and the Fundamental Research Funds for the Central Universities [DUT2019] in Dalian University of Technology in China. This work was also supported by China Scholarship Council (No. 201806060038) and Natural Science Foundation of Liaoning Province (2019-MS-099).
dc.type.okmA1


Aineistoon kuuluvat tiedostot

Thumbnail

Aineisto kuuluu seuraaviin kokoelmiin

Näytä suppeat kuvailutiedot

CC BY 4.0
Ellei muuten mainita, aineiston lisenssi on CC BY 4.0