Nonparametric Nearest Neighbor Random Process Clustering

TL;DR

This paper introduces two nonparametric clustering algorithms for stationary ergodic random process observations, demonstrating their effectiveness in noisy conditions and with overlapping spectral densities, supported by theoretical analysis and experiments.

Contribution

It proposes a novel spectral clustering algorithm (NNPC) for process clustering and analyzes its performance alongside a modified k-means approach, both without prior model knowledge.

Findings

Both algorithms succeed with high probability under noise.

Performance degrades gracefully with spectral overlap and noise.

Longer observations improve clustering accuracy.

Abstract

We consider the problem of clustering noisy finite-length observations of stationary ergodic random processes according to their nonparametric generative models without prior knowledge of the model statistics and the number of generative models. Two algorithms, both using the L1-distance between estimated power spectral densities (PSDs) as a measure of dissimilarity, are analyzed. The first algorithm, termed nearest neighbor process clustering (NNPC), to the best of our knowledge, is new and relies on partitioning the nearest neighbor graph of the observations via spectral clustering. The second algorithm, simply referred to as k-means (KM), consists of a single k-means iteration with farthest point initialization and was considered before in the literature, albeit with a different measure of dissimilarity and with asymptotic performance results only. We show that both NNPC and KM succeed with high probability under noise and even when the generative process PSDs overlap significantly, all provided that the observation length is sufficiently large. Our results quantify the tradeoff between the overlap of the generative process PSDs, the noise variance, and the observation length. Finally, we present numerical performance results for synthetic and real data.