Artículos
URI permanente para esta colección
Examinar
Examinando Artículos por Autor "Ariza-Jiménez L."
Mostrando 1 - 2 de 2
Resultados por página
Opciones de ordenación
Ítem An Entropy-Based Graph Construction Method for Representing and Clustering Biological Data(SPRINGER, 2019-10-01) Ariza-Jiménez L.; Pinel N.; Villa L.F.; Quintero O.L.; Universidad EAFIT. Escuela de Ciencias; Modelado MatemáticoUnsupervised learning methods are commonly used to perform the non-trivial task of uncovering structure in biological data. However, conventional approaches rely on methods that make assumptions about data distribution and reduce the dimensionality of the input data. Here we propose the incorporation of entropy related measures into the process of constructing graph-based representations for biological datasets in order to uncover their inner structure. Experimental results demonstrated the potential of the proposed entropy-based graph data representation to cope with biological applications related to unsupervised learning problems, such as metagenomic binning and neuronal spike sorting, in which it is necessary to organize data into unknown and meaningful groups. © 2020, Springer Nature Switzerland AG.Ítem Memberships Networks for High-Dimensional Fuzzy Clustering Visualization(Springer Verlag, 2019-01-01) Ariza-Jiménez L.; Villa L.F.; Quintero O.L.; Universidad EAFIT. Escuela de Ciencias; Modelado MatemáticoVisualizing the cluster structure of high-dimensional data is a non-trivial task that must be able to deal with the large dimensionality of the input data. Unlike hard clustering structures, visualization of fuzzy clusterings is not as straightforward because soft clustering algorithms yield more complex clustering structures. Here is introduced the concept of membership networks, an undirected weighted network constructed based on the fuzzy partition matrix that represents a fuzzy clustering. This simple network-based method allows understanding visually how elements involved in this kind of complex data clustering structures interact with each other, without relying on a visualization of the input data themselves. Experiment results demonstrated the usefulness of the proposed method for the exploration and analysis of clustering structures on the Iris flower data set and two large and unlabeled financial datasets, which describes the financial profile of customers of a local bank. © 2019, Springer Nature Switzerland AG.