funLOCI: a local clustering algorithm for functional data
Nowadays, more and more problems are dealing with data with one infinite continuous dimension: functional data. In this paper, we introduce the funLOCI algorithm which allows to identify functional local clusters or functional loci, i.e., subsets/groups of functions exhibiting similar behaviour across the same continuous subset of the domain. The definition of functional local clusters leverages ideas from multivariate and functional clustering and biclustering and it is based on an additive model which takes into account the shape of the curves. funLOCI is a three-step algorithm based on divisive hierarchical clustering. The use of dendrograms allows to visualize and to guide the searching procedure and the cutting thresholds selection. To deal with the large quantity of local clusters, an extra step is implemented to reduce the number of results to the minimum.
Code (1)
Tasks
ClusteringSimilar Papers 제목 키워드 기반
The functional mean-shift algorithm for mode hunting and clustering in infinite dimensions
We introduce the functional mean-shift algorithm, an iterative algorithm for estimating the local modes of a surrogate density from functional data. We show that the algorithm can be used for cluster analysis of function…
ClusteringSpike SortingAlgorithm-Agnostic Explainability for Unsupervised Clustering
Supervised machine learning explainability has developed rapidly in recent years. However, clustering explainability has lagged behind. Here, we demonstrate the first adaptation of model-agnostic explainability methods t…
BIG-bench Machine LearningClusteringExplainable artificial intelligenceFeature ImportanceNonlinear subspace clustering by functional link neural networks
Nonlinear subspace clustering based on a feed-forward neural network has been demonstrated to provide better clustering accuracy than some advanced subspace clustering algorithms. While this approach demonstrates impress…
ClusteringComputational EfficiencyCluster Analysis on Locally Asymptotically Self-similar Processes with Known Number of Clusters
We conduct cluster analysis on a class of locally asymptotically self-similar stochastic processes, which includes multifractional Brownian motion as a representative. When the true number of clusters is supposed to be k…
ClusteringFunctional Parcellation of fMRI data using multistage k-means clustering
Purpose: Functional Magnetic Resonance Imaging (fMRI) data acquired through resting-state studies have been used to obtain information about the spontaneous activations inside the brain. One of the approaches for analysi…
Clustering