A Trend-Granulation-Based Fuzzy C-Means Algorithm for Clustering Interval-Valued Time Series

Basit Öğe Kaydı
dc.contributor.authorYang, Zonglin
dc.contributor.authorYu, Fusheng
dc.contributor.authorPedrycz, Witold
dc.contributor.authorYang, Huilin
dc.contributor.authorTang, Yuqing
dc.contributor.authorOuyang, Chenxi
dc.date.accessioned2024-05-19T14:47:01Z
dc.date.available2024-05-19T14:47:01Z
dc.date.issued2024
dc.departmentİstinye Üniversitesien_US
dc.description.abstractAlong with the abundant appearance of the interval-valued time series (ITS), the study on ITS clustering, especially shape-based ITS clustering, is becoming increasingly important. As an effective approach to extracting trend information in time series, fuzzy trend granulation addresses the needs of shape-based ITS clustering. However, when extracting trend information in ITS, unequal-size granules are inevitably produced, which makes ITS clustering difficult and challenging. Facing this issue, this article aims to generalize the widely used fuzzy C-means (FCM) algorithm to a fuzzy trend-granulation-based FCM algorithm for ITS clustering. To this end, a suite of algorithms, including ITS segmenting, segment merging, and granule building algorithms, are first developed for fuzzy trend-granulation of ITS, with which the given ITS is transformed into granular ITS, which consists of double linear fuzzy information granules (DLFIGs) and may be of different lengths. With the defined distance between DLFIGs, the distance between granular ITS is further developed through the dynamic time warping (DTW) algorithm. In designing the fuzzy trend-granulation-based FCM algorithm, the key step is to design the method for updating cluster prototypes to cope with the unequal lengths of granular ITS. The weighted DTW barycenter averaging method is a previously adopted prototype updating approach with the drawback of hardly changing the lengths of prototypes, which often makes prototypes less representative. Thus, a granule splitting and merging algorithm is designed to resolve this issue. Additionally, a prototype initialization method is also proposed to improve the clustering performance. The proposed fuzzy trend-granulation-based FCM algorithm for clustering ITS, being a typical shape-based clustering algorithm, exhibits superior performance, which is validated by the ablation experiments as well as the comparative experiments.en_US
dc.description.sponsorshipNational Natural Science Foundation of Chinaen_US
dc.description.sponsorshipNo Statement Availableen_US
dc.identifier.doi10.1109/TFUZZ.2023.3321921
dc.identifier.endpage1277en_US
dc.identifier.issn1063-6706
dc.identifier.issn1941-0034
dc.identifier.issue3en_US
dc.identifier.scopus2-s2.0-85174809533en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage1263en_US
dc.identifier.urihttps://doi.org10.1109/TFUZZ.2023.3321921
dc.identifier.urihttps://hdl.handle.net/20.500.12713/5638
dc.identifier.volume32en_US
dc.identifier.wosWOS:001179721500004en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherIeee-Inst Electrical Electronics Engineers Incen_US
dc.relation.ispartofIeee Transactions on Fuzzy Systemsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240519_kaen_US
dc.subjectTime Series Analysisen_US
dc.subjectClustering Algorithmsen_US
dc.subjectMarket Researchen_US
dc.subjectPrototypesen_US
dc.subjectShapeen_US
dc.subjectMergingen_US
dc.subjectFilteringen_US
dc.subjectDynamic Time Warping (Dtw)en_US
dc.subjectFuzzy C-Means (Fcm)en_US
dc.subjectFuzzy Information Granulesen_US
dc.subjectFuzzy Trend Granulationen_US
dc.subjectInterval-Valued Time Series (Its) Clusteringen_US
dc.titleA Trend-Granulation-Based Fuzzy C-Means Algorithm for Clustering Interval-Valued Time Seriesen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu