Robust Spectral Fuzzy Clustering of Multivariate Time Series with Applications to Electroencephalogram

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ma, Ziling, Talento, Mara Sherlin, Sun, Ying, Ombao, Hernando
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915588017750016
author Ma, Ziling
Talento, Mara Sherlin
Sun, Ying
Ombao, Hernando
author_facet Ma, Ziling
Talento, Mara Sherlin
Sun, Ying
Ombao, Hernando
contents Clustering multivariate time series (MTS) is challenging due to non-stationary cross-dependencies, noise contamination, and gradual or overlapping state boundaries. We introduce a robust fuzzy clustering framework in the spectral domain that leverages Kendall's tau-based canonical coherence to extract frequency-specific monotonic relationships across variables. Our method takes advantage of dominant frequency-based cross-regional connectivity patterns to improve clustering accuracy while remaining resilient to outliers, making the approach broadly applicable to noisy, high-dimensional MTS. Each series is projected onto vectors generated from a spectral matrix specifically tailored to capture the underlying fuzzy partitions. Numerical experiments demonstrate the superiority of our framework over existing methods. As a flagship application, we analyze electroencephalogram recordings, where our approach uncovers frequency- and connectivity-specific markers of latent cognitive states such as alertness and drowsiness, revealing discriminative patterns and ambiguous transitions.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22861
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Spectral Fuzzy Clustering of Multivariate Time Series with Applications to Electroencephalogram
Ma, Ziling
Talento, Mara Sherlin
Sun, Ying
Ombao, Hernando
Applications
Methodology
Machine Learning
Clustering multivariate time series (MTS) is challenging due to non-stationary cross-dependencies, noise contamination, and gradual or overlapping state boundaries. We introduce a robust fuzzy clustering framework in the spectral domain that leverages Kendall's tau-based canonical coherence to extract frequency-specific monotonic relationships across variables. Our method takes advantage of dominant frequency-based cross-regional connectivity patterns to improve clustering accuracy while remaining resilient to outliers, making the approach broadly applicable to noisy, high-dimensional MTS. Each series is projected onto vectors generated from a spectral matrix specifically tailored to capture the underlying fuzzy partitions. Numerical experiments demonstrate the superiority of our framework over existing methods. As a flagship application, we analyze electroencephalogram recordings, where our approach uncovers frequency- and connectivity-specific markers of latent cognitive states such as alertness and drowsiness, revealing discriminative patterns and ambiguous transitions.
title Robust Spectral Fuzzy Clustering of Multivariate Time Series with Applications to Electroencephalogram
topic Applications
Methodology
Machine Learning
url https://arxiv.org/abs/2506.22861