CoPAL: Conformal Prediction in Active Learning An Algorithm for Enhancing Remaining Useful Life Estimation in Predictive Maintenance

Zahra Kharazian, Tony Lindgren, Sindri Magnusson, Henrik Boström
Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 230:195-217, 2024.

Abstract

Active learning has received considerable attention as an approach to obtain high predictive performance while minimizing the labeling effort. A central component of the active learning framework concerns the selection of objects for labeling, which are used for iteratively updating the underlying model. In this work, an algorithm called CoPAL (Conformal Prediction for Active Learning) is proposed, which makes the selection of objects within active learning based on the uncertainty as quantified by conformal prediction. The efficacy of CoPAL is investigated by considering the task of estimating the remaining useful life (RUL) of assets in the domain of predictive maintenance (PdM). Experimental results are presented, encompassing diverse setups, including different models, sample selection criteria, conformal predictors, and datasets, using root mean squared error (RMSE) as the primary evaluation metric while also reporting prediction interval sizes over the iterations. The comprehensive analysis confirms the positive effect of using CoPAL for improving predictive performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v230-kharazian24a, title = {CoPAL: Conformal Prediction in Active Learning An Algorithm for Enhancing Remaining Useful Life Estimation in Predictive Maintenance}, author = {Kharazian, Zahra and Lindgren, Tony and Magnusson, Sindri and Bostr\"{o}m, Henrik}, booktitle = {Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {195--217}, year = {2024}, editor = {Vantini, Simone and Fontana, Matteo and Solari, Aldo and Boström, Henrik and Carlsson, Lars}, volume = {230}, series = {Proceedings of Machine Learning Research}, month = {09--11 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v230/main/assets/kharazian24a/kharazian24a.pdf}, url = {https://proceedings.mlr.press/v230/kharazian24a.html}, abstract = {Active learning has received considerable attention as an approach to obtain high predictive performance while minimizing the labeling effort. A central component of the active learning framework concerns the selection of objects for labeling, which are used for iteratively updating the underlying model. In this work, an algorithm called CoPAL (Conformal Prediction for Active Learning) is proposed, which makes the selection of objects within active learning based on the uncertainty as quantified by conformal prediction. The efficacy of CoPAL is investigated by considering the task of estimating the remaining useful life (RUL) of assets in the domain of predictive maintenance (PdM). Experimental results are presented, encompassing diverse setups, including different models, sample selection criteria, conformal predictors, and datasets, using root mean squared error (RMSE) as the primary evaluation metric while also reporting prediction interval sizes over the iterations. The comprehensive analysis confirms the positive effect of using CoPAL for improving predictive performance.} }
Endnote
%0 Conference Paper %T CoPAL: Conformal Prediction in Active Learning An Algorithm for Enhancing Remaining Useful Life Estimation in Predictive Maintenance %A Zahra Kharazian %A Tony Lindgren %A Sindri Magnusson %A Henrik Boström %B Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2024 %E Simone Vantini %E Matteo Fontana %E Aldo Solari %E Henrik Boström %E Lars Carlsson %F pmlr-v230-kharazian24a %I PMLR %P 195--217 %U https://proceedings.mlr.press/v230/kharazian24a.html %V 230 %X Active learning has received considerable attention as an approach to obtain high predictive performance while minimizing the labeling effort. A central component of the active learning framework concerns the selection of objects for labeling, which are used for iteratively updating the underlying model. In this work, an algorithm called CoPAL (Conformal Prediction for Active Learning) is proposed, which makes the selection of objects within active learning based on the uncertainty as quantified by conformal prediction. The efficacy of CoPAL is investigated by considering the task of estimating the remaining useful life (RUL) of assets in the domain of predictive maintenance (PdM). Experimental results are presented, encompassing diverse setups, including different models, sample selection criteria, conformal predictors, and datasets, using root mean squared error (RMSE) as the primary evaluation metric while also reporting prediction interval sizes over the iterations. The comprehensive analysis confirms the positive effect of using CoPAL for improving predictive performance.
APA
Kharazian, Z., Lindgren, T., Magnusson, S. & Boström, H.. (2024). CoPAL: Conformal Prediction in Active Learning An Algorithm for Enhancing Remaining Useful Life Estimation in Predictive Maintenance. Proceedings of the Thirteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 230:195-217 Available from https://proceedings.mlr.press/v230/kharazian24a.html.

Related Material