Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published April 14, 2022 | Version v2
Preprint Open

ODIN TS: a tool for the black-box evaluation of time series analytics

Description

Abstract. The increasing availability of time series datasets enabled by the diffusion of IoT architectures and the progress in the analysis of temporal data fostered by Deep Learning methods are boosting the interest in anomaly detection and predictive maintenance applications. 
The analysis of performance for these tasks relies on standard metrics applied to the entire dataset. Such indicators provide a global performance assessment but might not help a deep understanding of the model weaknesses.
A complementary diagnostic approach exploits error categorization and ad-hoc visualizations. In this paper we present ODIN, an open source diagnosis framework for time series analysis that lets developers compute performance metrics, disaggregated by different criteria, and visualize diagnosis reports. ODIN is agnostic to the training platform and can be extended with application- and domain-specific meta-annotations and metrics with almost no coding. We show ODIN at work through two time series analytics examples.

Notes

This preprint has not undergone peer review (when applicable) or any post-submission improvements or corrections. The Version of Record of this contribution is published in Contribution to Statistics (Springer), and a link to the final publication will be published when available.

Files

ODIN TS_a tool for the black box evaluation of time series analytics.pdf

Files (478.6 kB)

Additional details

Funding

PRECEPT – A novel decentralized edge-enabled PREsCriptivE and ProacTive framework for increased energy efficiency and well-being in residential buildings 958284
European Commission