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

arXiv: https://arxiv.org/abs/2506.22861 · HTML: https://mlsanity.com/paper/2506.22861/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 49 references that are in the map.
- First posted on arXiv 28 Jun 2025.

## Builds on (most cited first, 7 of 7)

- [Multi-channel EEG recordings during a sustained-attention driving task](https://mlsanity.com/paper/1809.06534/) (2018)
- [Spectral Dependence](https://mlsanity.com/paper/2103.17240/) (2021)
- [Quantile-based fuzzy C-means clustering of multivariate time series: Robust techniques](https://mlsanity.com/paper/2109.11027/) (2021)
- [Detecting Anomalous Cryptocurrency Transactions: an AML/CFT Application of Machine Learning-based Forensics](https://mlsanity.com/paper/2206.04803/) (2022)
- [FCPCA: Fuzzy clustering of high-dimensional time series based on common principal component analysis](https://mlsanity.com/paper/2505.07276/) (2025)
- [KenCoh: A Ranked-Based Canonical Coherence](https://mlsanity.com/paper/2412.10521/) (2024)
- [Wavelet Canonical Coherence for Nonstationary Signals](https://mlsanity.com/paper/2505.14253/) (2025)

## Abstract (arXiv)

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.