When to Classify Events in Open Times Series?

Youssef Achenchabe, Alexis Bondu, Cornuéjols Antoine, Lemaire Vincent
Proceedings of The 14th Asian Conference on Machine Learning, PMLR 189:1-16, 2023.

Abstract

In numerous applications, for instance in predictive maintenance, there is a pression to predict events ahead of time with as much accuracy as possible while not delaying the decision unduly. This translates in the optimization of a trade-off between earliness and accuracy of the decisions, that has been the subject of research for time series of finite length and with a unique label. And this has led to powerful algorithms for Early Classification of Time Series (ECTS). This paper, for the first time, investigates such a trade-off when events of different classes occur in a streaming fashion, with no predefined end. In the Early Classification in Open Time Series problem (ECOTS), the task is to predict events, i.e. their class and time interval, at the moment that optimizes the accuracy vs. earliness trade-off. Interestingly, we find that ECTS algorithms can be sensibly adapted in a principled way to this new problem. We illustrate our methodology by transforming two state-of-the-art ECTS algorithms for the ECOTS scenario.Among the wide variety of applications that this new approach opens up, we develop here a predictive maintenance use case that optimizes alarm triggering times, thus demonstrating the power of this new approach.

Cite this Paper

BibTeX
@InProceedings{pmlr-v189-achenchabe23a, title = {When to Classify Events in Open Times Series?}, author = {Achenchabe, Youssef and Bondu, Alexis and Antoine, Cornu\'ejols and Vincent, Lemaire}, booktitle = {Proceedings of The 14th Asian Conference on Machine Learning}, pages = {1--16}, year = {2023}, editor = {Khan, Emtiyaz and Gonen, Mehmet}, volume = {189}, series = {Proceedings of Machine Learning Research}, month = {12--14 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v189/achenchabe23a/achenchabe23a.pdf}, url = {https://proceedings.mlr.press/v189/achenchabe23a.html}, abstract = {In numerous applications, for instance in predictive maintenance, there is a pression to predict events ahead of time with as much accuracy as possible while not delaying the decision unduly. This translates in the optimization of a trade-off between earliness and accuracy of the decisions, that has been the subject of research for time series of finite length and with a unique label. And this has led to powerful algorithms for Early Classification of Time Series (ECTS). This paper, for the first time, investigates such a trade-off when events of different classes occur in a streaming fashion, with no predefined end. In the Early Classification in Open Time Series problem (ECOTS), the task is to predict events, i.e. their class and time interval, at the moment that optimizes the accuracy vs. earliness trade-off. Interestingly, we find that ECTS algorithms can be sensibly adapted in a principled way to this new problem. We illustrate our methodology by transforming two state-of-the-art ECTS algorithms for the ECOTS scenario.Among the wide variety of applications that this new approach opens up, we develop here a predictive maintenance use case that optimizes alarm triggering times, thus demonstrating the power of this new approach. } }
Endnote
%0 Conference Paper %T When to Classify Events in Open Times Series? %A Youssef Achenchabe %A Alexis Bondu %A Cornuéjols Antoine %A Lemaire Vincent %B Proceedings of The 14th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Emtiyaz Khan %E Mehmet Gonen %F pmlr-v189-achenchabe23a %I PMLR %P 1--16 %U https://proceedings.mlr.press/v189/achenchabe23a.html %V 189 %X In numerous applications, for instance in predictive maintenance, there is a pression to predict events ahead of time with as much accuracy as possible while not delaying the decision unduly. This translates in the optimization of a trade-off between earliness and accuracy of the decisions, that has been the subject of research for time series of finite length and with a unique label. And this has led to powerful algorithms for Early Classification of Time Series (ECTS). This paper, for the first time, investigates such a trade-off when events of different classes occur in a streaming fashion, with no predefined end. In the Early Classification in Open Time Series problem (ECOTS), the task is to predict events, i.e. their class and time interval, at the moment that optimizes the accuracy vs. earliness trade-off. Interestingly, we find that ECTS algorithms can be sensibly adapted in a principled way to this new problem. We illustrate our methodology by transforming two state-of-the-art ECTS algorithms for the ECOTS scenario.Among the wide variety of applications that this new approach opens up, we develop here a predictive maintenance use case that optimizes alarm triggering times, thus demonstrating the power of this new approach.
APA
Achenchabe, Y., Bondu, A., Antoine, C. & Vincent, L.. (2023). When to Classify Events in Open Times Series?. Proceedings of The 14th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 189:1-16 Available from https://proceedings.mlr.press/v189/achenchabe23a.html.

Related Material