A General Bi-clustering Algorithm for Hilbert Data: Analysis of the Lombardy Railway Service

Keywords

Statistical learning
Sustainable mobility
Code:
21/2021
Title:
A General Bi-clustering Algorithm for Hilbert Data: Analysis of the Lombardy Railway Service
Date:
Saturday 10th April 2021
Author(s):
Torti, A.; Galvani, M.; Menafoglio, A.; Secchi, P.; Vantini S.
Download link:
Abstract:
A general and flexible bi-clustering algorithm for the analysis of Hilbert data is presented in the Object Oriented Data Analysis framework. The algorithm, called HC2 (i.e. Hilbert Cheng and Church), is a non-parametric method to bi-cluster Hilbert data indexed in a matrix structure. The Cheng and Church approach is here extended to the general case of data embedded in a Hilbert space and then applied to the analysis of the regional railway service in the Lombardy region with the aim of identifying recurrent patterns in the passengers' daily access to trains and/or stations. The analysed data, modelled as multivariate functional data and time series, allows to measure both overcrowding and travel demand, providing useful insights to best handle the service.