Deconvolution When Classifying Noisy Data Involving Transformations

Raymond Carroll, Aurore Delaigle, Peter Hall

Research output: Contribution to journalArticlepeer-review

5 Scopus citations


In the present study, we consider the problem of classifying spatial data distorted by a linear transformation or convolution and contaminated by additive random noise. In this setting, we show that classifier performance can be improved if we carefully invert the data before the classifier is applied. However, the inverse transformation is not constructed so as to recover the original signal, and in fact, we show that taking the latter approach is generally inadvisable. We introduce a fully data-driven procedure based on cross-validation, and use several classifiers to illustrate numerical properties of our approach. Theoretical arguments are given in support of our claims. Our procedure is applied to data generated by light detection and ranging (Lidar) technology, where we improve on earlier approaches to classifying aerosols. This article has supplementary materials online.
Original languageEnglish (US)
Pages (from-to)1166-1177
Number of pages12
JournalJournal of the American Statistical Association
Issue number499
StatePublished - Oct 8 2012
Externally publishedYes


Dive into the research topics of 'Deconvolution When Classifying Noisy Data Involving Transformations'. Together they form a unique fingerprint.

Cite this