Saved in:
Bibliographic Details
Main Authors: Salles, Rebecca, Lima, Janio, Reis, Michel, Coutinho, Rafaelli, Pacitti, Esther, Masseglia, Florent, Akbarinia, Reza, Chen, Chao, Garibaldi, Jonathan, Porto, Fabio, Ogasawara, Eduardo
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2304.00439
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916497579835392
author Salles, Rebecca
Lima, Janio
Reis, Michel
Coutinho, Rafaelli
Pacitti, Esther
Masseglia, Florent
Akbarinia, Reza
Chen, Chao
Garibaldi, Jonathan
Porto, Fabio
Ogasawara, Eduardo
author_facet Salles, Rebecca
Lima, Janio
Reis, Michel
Coutinho, Rafaelli
Pacitti, Esther
Masseglia, Florent
Akbarinia, Reza
Chen, Chao
Garibaldi, Jonathan
Porto, Fabio
Ogasawara, Eduardo
contents Time series event detection methods are evaluated mainly by standard classification metrics that focus solely on detection accuracy. However, inaccuracy in detecting an event can often result from its preceding or delayed effects reflected in neighboring detections. These detections are valuable to trigger necessary actions or help mitigate unwelcome consequences. In this context, current metrics are insufficient and inadequate for the context of event detection. There is a demand for metrics that incorporate both the concept of time and temporal tolerance for neighboring detections. This paper introduces SoftED metrics, a new set of metrics designed for soft evaluating event detection methods. They enable the evaluation of both detection accuracy and the degree to which their detections represent events. They improved event detection evaluation by associating events and their representative detections, incorporating temporal tolerance in over 36\% of experiments compared to the usual classification metrics. SoftED metrics were validated by domain specialists that indicated their contribution to detection evaluation and method selection.
format Preprint
id arxiv_https___arxiv_org_abs_2304_00439
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SoftED: Metrics for Soft Evaluation of Time Series Event Detection
Salles, Rebecca
Lima, Janio
Reis, Michel
Coutinho, Rafaelli
Pacitti, Esther
Masseglia, Florent
Akbarinia, Reza
Chen, Chao
Garibaldi, Jonathan
Porto, Fabio
Ogasawara, Eduardo
Machine Learning
Time series event detection methods are evaluated mainly by standard classification metrics that focus solely on detection accuracy. However, inaccuracy in detecting an event can often result from its preceding or delayed effects reflected in neighboring detections. These detections are valuable to trigger necessary actions or help mitigate unwelcome consequences. In this context, current metrics are insufficient and inadequate for the context of event detection. There is a demand for metrics that incorporate both the concept of time and temporal tolerance for neighboring detections. This paper introduces SoftED metrics, a new set of metrics designed for soft evaluating event detection methods. They enable the evaluation of both detection accuracy and the degree to which their detections represent events. They improved event detection evaluation by associating events and their representative detections, incorporating temporal tolerance in over 36\% of experiments compared to the usual classification metrics. SoftED metrics were validated by domain specialists that indicated their contribution to detection evaluation and method selection.
title SoftED: Metrics for Soft Evaluation of Time Series Event Detection
topic Machine Learning
url https://arxiv.org/abs/2304.00439