Robust clustering for functional data based on trimming and constraints

TL;DR

This paper introduces a robust clustering method for functional data that combines trimming and variance constraints to handle contamination and avoid spurious clusters, validated through simulations and real data application.

Contribution

It presents a novel model-based clustering approach for functional data that enhances robustness against contamination and prevents spurious results.

Findings

Effective in reducing the influence of contaminated observations.

Successfully applied to real-world functional data.

Outperforms traditional methods in robustness and accuracy.

Abstract

Many clustering algorithms when the data are curves or functions have been recently proposed. However, the presence of contamination in the sample of curves can influence the performance of most of them. In this work we propose a robust, model-based clustering method based on an approximation to the "density function" for functional data. The robustness results from the joint application of trimming, for reducing the effect of contaminated observations, and constraints on the variances, for avoiding spurious clusters in the solution. The proposed method has been evaluated through a simulation study. Finally, an application to a real data problem is given.