Mostrar el registro sencillo del ítem

Pseudoinverse learning of Fuzzy Cognitive Maps for multivariate time series forecasting

dc.contributor.authorVanhoenshoven F.
dc.contributor.authorNápoles G.
dc.contributor.authorFroelich W.
dc.contributor.authorSalmeron J.L.
dc.contributor.authorVanhoof K.
dc.date.accessioned2020-09-02T22:29:55Z
dc.date.available2020-09-02T22:29:55Z
dc.date.issued2020
dc.identifier10.1016/j.asoc.2020.106461
dc.identifier.citation95, , -
dc.identifier.issn15684946
dc.identifier.urihttps://hdl.handle.net/20.500.12728/6516
dc.descriptionForecasting multivariate time series is an important problem considered in many real-world scenarios. To deal with that problem, several forecasting models have already been proposed, where Fuzzy Cognitive Maps (FCMs) are proved to be a suitable alternative. The key limitation of the existing FCM-based forecasting models is the lack of time-efficient learning algorithms. In this paper, we plug that gap by proposing a new FCM learning algorithm which is based on Moore–Penrose inverse. Moreover, we propose an innovative approach that equips FCM with long-term, multistep prediction capabilities. A huge advantage of our method is the lack of parameters which in the case of competitive approaches require laborious adjustment or tuning. The other added value of our method is the reduction of the processing time required to train FCM. The performed experiments revealed that FCM trained using our method outperforms the best FCM-based forecasting model reported in the literature. © 2020 Elsevier B.V.
dc.language.isoen
dc.publisherElsevier Ltd
dc.subjectForecasting
dc.subjectFuzzy Cognitive Maps
dc.subjectLearning
dc.subjectTime series
dc.subjectCognitive systems
dc.subjectForecasting
dc.subjectFuzzy rules
dc.subjectInverse problems
dc.subjectTime series
dc.subjectForecasting modeling
dc.subjectForecasting models
dc.subjectFuzzy cognitive map
dc.subjectFuzzy cognitive maps (FCMs)
dc.subjectInnovative approaches
dc.subjectMulti-step prediction
dc.subjectMultivariate time series
dc.subjectReal-world scenario
dc.subjectLearning algorithms
dc.titlePseudoinverse learning of Fuzzy Cognitive Maps for multivariate time series forecasting
dc.typeArticle


Ficheros en el ítem

Thumbnail
Nombre:
item_2-s2.0-85087905122.pdf
Tamaño:
2.560Kb
Formato:
PDF
Ver/

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem