Active learning for anomaly detection in environmental data


Loading...

Date

2020-12

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Due to the growing amount of data from in-situ sensors in environmental monitoring, it becomes necessary to automatically detect anomalous data points. Nowadays, this is mainly performed using supervised machine learning models, which need a fully labelled data set for their training process. However, the process of labelling data is typically cumbersome and, as a result, a hindrance to the adoption of machine learning methods for automated anomaly detection. In this work, we propose to address this challenge by means of active learning. This method consists of querying the domain expert for the labels of only a selected subset of the full data set. We show that this reduces the time and costs associated to labelling while delivering the same or similar anomaly detection performances. Finally, we also show that machine learning models providing a nonlinear classification boundary are to be recommended for anomaly detection in complex environmental data sets. © 2020 The Authors

Publication status

published

Editor

Book title

Volume

134

Pages / Article No.

104869

Publisher

Elsevier

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Active learning; Anomaly detection; Machine learning; Environmental monitoring

Organisational unit

03832 - Morgenroth, Eberhard / Morgenroth, Eberhard check_circle

Notes

Funding

Related publications and datasets