Learning Time Series Detection Models from Temporally Imprecise Labels

TL;DR

This paper introduces a novel learning framework for time series detection using imprecise, noisy temporal labels, addressing challenges in mobile health data annotation and outperforming existing methods.

Contribution

The paper proposes a flexible framework for learning from temporally imprecise labels, accommodating various classifiers and noise models, with demonstrated improvements on real mobile health data.

Findings

Significant performance gains over baseline methods

Effective handling of noisy and imprecise temporal labels

Applicable to mobile health event detection

Abstract

In this paper, we consider a new low-quality label learning problem: learning time series detection models from temporally imprecise labels. In this problem, the data consist of a set of input time series, and supervision is provided by a sequence of noisy time stamps corresponding to the occurrence of positive class events. Such temporally imprecise labels commonly occur in areas like mobile health research where human annotators are tasked with labeling the occurrence of very short duration events. We propose a general learning framework for this problem that can accommodate different base classifiers and noise models. We present results on real mobile health data showing that the proposed framework significantly outperforms a number of alternatives including assuming that the label time stamps are noise-free, transforming the problem into the multiple instance learning framework, and learning on labels that were manually re-aligned.