Takáč, ZdenkoFerrero Jaurrieta, MikelHoranská, LubomíraKrivonakova, NadaPereira Dimuro, GraçalizBustince Sola, Humberto2022-09-222023-02-112021Takac, Z.; Ferrero-Jaurrieta, M.; Horanska, L.; Krivonakova, N.; DImuro, G. P.; Bustince, H.. (2021). Enhancing LSTM for sequential image classification by modifying data aggregation. 1 IEEE; (p. 1-6).978-1-6654-4231-210.1109/ICECET52533.2021.9698795https://academica-e.unavarra.es/handle/2454/44090Recurrent Neural Networks (RNN) model sequential information and are commonly used for the analysis of time series. The most usual operation to fuse information in RNNs is the sum. In this work, we use a RNN extended type, Long Short-Term Memory (LSTM) and we use it for image classification, to which we give a sequential interpretation. Since the data used may not be independent to each other, we modify the sum operator of an LSTM unit using the n-dimensional Choquet integral, which considers possible data coalitions. We compare our methods to those based on usual aggregation functions, using the datasets Fashion-MNIST and MNIST.application/pdfeng© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other work.Long short-term MemoryRecurrent neural networkSequential image classificationAggregation functionsChoquet integralinfo:eu-repo/semantics/conferenceObject2022-09-22Acceso abierto / Sarbide irekiainfo:eu-repo/semantics/openAccess