A Robust Principal Component Analysis for Outlier Identification in Messy Microcalorimeter Data

Published

November 12, 2019

Author(s)

Joseph W. Fowler, Bradley K. Alpert, Young I. Joe, Galen C. O'Neil, Daniel S. Swetz, Joel N. Ullom

Abstract

A principal component analysis (PCA) of clean microcalorimeter pulse records can be a first step beyond statistically optimal linear filtering of pulses toward a fully nonlinear analysis. For PCA to be practical on spectrometers with hundreds of sensors, an automated identification of clean pulses is required. Robust forms of PCA are the subject of active research in machine learning. We examine a version known as coherence pursuit that is simple and fast and well matched to the automatic identification of outlier records, as needed for microcalorimeter pulse analysis.

Citation

Journal of Low Temperature Physics

Volume

199

Issue

3-4

Pub Type

Journals

Download Paper

DOI Link

Keywords

outlier identification, microcalorimeter, principal component analysis, PCA, pulse records, spectrometers, clean pulses, machine learning

Citation

Fowler, J. , Alpert, B. , Joe, Y. , O'Neil, G. , Swetz, D. and Ullom, J. (2019), A Robust Principal Component Analysis for Outlier Identification in Messy Microcalorimeter Data, Journal of Low Temperature Physics, [online], https://doi.org/10.1007/s10909-019-02248-w (Accessed October 8, 2025)