Learning Time Series Detection Models from Temporally Imprecise Labels

Roy Adams, Ben Marlin
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, PMLR 54:157-165, 2017.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v54-adams17a, title = {{Learning Time Series Detection Models from Temporally Imprecise Labels}}, author = {Adams, Roy and Marlin, Ben}, booktitle = {Proceedings of the 20th International Conference on Artificial Intelligence and Statistics}, pages = {157--165}, year = {2017}, editor = {Singh, Aarti and Zhu, Jerry}, volume = {54}, series = {Proceedings of Machine Learning Research}, month = {20--22 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v54/adams17a/adams17a.pdf}, url = {https://proceedings.mlr.press/v54/adams17a.html}, 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.} }
Endnote
%0 Conference Paper %T Learning Time Series Detection Models from Temporally Imprecise Labels %A Roy Adams %A Ben Marlin %B Proceedings of the 20th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2017 %E Aarti Singh %E Jerry Zhu %F pmlr-v54-adams17a %I PMLR %P 157--165 %U https://proceedings.mlr.press/v54/adams17a.html %V 54 %X 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.
APA
Adams, R. & Marlin, B.. (2017). Learning Time Series Detection Models from Temporally Imprecise Labels. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 54:157-165 Available from https://proceedings.mlr.press/v54/adams17a.html.

Related Material