Search: onr:"swepub:oai:lup.lub.lu.se:afff622f-9e04-4125-9b13-d8d00df2fa3b" >
The value of human ...
The value of human data annotation for machine learning based anomaly detection in environmental systems
-
- Russo, Stefania (author)
- Eawag: Swiss Federal Institute of Aquatic Science and Technology
-
- Besmer, Michael D. (author)
- onCyt Microbiology AG
-
- Blumensaat, Frank (author)
- Eawag: Swiss Federal Institute of Aquatic Science and Technology
-
show more...
-
- Bouffard, Damien (author)
- Eawag: Swiss Federal Institute of Aquatic Science and Technology
-
- Disch, Andy (author)
- Eawag: Swiss Federal Institute of Aquatic Science and Technology
-
- Hammes, Frederik (author)
- Eawag: Swiss Federal Institute of Aquatic Science and Technology
-
- Hess, Angelika (author)
- Eawag: Swiss Federal Institute of Aquatic Science and Technology
-
- Lürig, Moritz (author)
- Lund University,Lunds universitet,Evolutionär ekologi,Biologiska institutionen,Naturvetenskapliga fakulteten,Evolutionary ecology,Department of Biology,Faculty of Science,Eawag: Swiss Federal Institute of Aquatic Science and Technology
-
- Matthews, Blake (author)
- Eawag: Swiss Federal Institute of Aquatic Science and Technology
-
- Minaudo, Camille (author)
- Physics of Aquatic Systems Laboratory (APHYS), Lausanne
-
- Morgenroth, Eberhard (author)
- Eawag: Swiss Federal Institute of Aquatic Science and Technology
-
- Tran-Khac, Viet (author)
- University of Savoy Mont Blanc
-
- Villez, Kris (author)
- Eawag: Swiss Federal Institute of Aquatic Science and Technology
-
show less...
-
(creator_code:org_t)
- Elsevier BV, 2021
- 2021
- English.
-
In: Water Research. - : Elsevier BV. - 0043-1354. ; 206
- Related links:
-
http://dx.doi.org/10... (free)
-
show more...
-
https://doi.org/10.1...
-
https://lup.lub.lu.s...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Anomaly detection is the process of identifying unexpected data samples in datasets. Automated anomaly detection is either performed using supervised machine learning models, which require a labelled dataset for their calibration, or unsupervised models, which do not require labels. While academic research has produced a vast array of tools and machine learning models for automated anomaly detection, the research community focused on environmental systems still lacks a comparative analysis that is simultaneously comprehensive, objective, and systematic. This knowledge gap is addressed for the first time in this study, where 15 different supervised and unsupervised anomaly detection models are evaluated on 5 different environmental datasets from engineered and natural aquatic systems. To this end, anomaly detection performance, labelling efforts, as well as the impact of model and algorithm tuning are taken into account. As a result, our analysis reveals the relative strengths and weaknesses of the different approaches in an objective manner without bias for any particular paradigm in machine learning. Most importantly, our results show that expert-based data annotation is extremely valuable for anomaly detection based on machine learning.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
- NATURVETENSKAP -- Biologi -- Bioinformatik och systembiologi (hsv//swe)
- NATURAL SCIENCES -- Biological Sciences -- Bioinformatics and Systems Biology (hsv//eng)
Keyword
- Anomaly detection
- Environmental systems
- Labels
- Machine learning
Publication and Content Type
- art (subject category)
- ref (subject category)
Find in a library
To the university's database
- By the author/editor
-
Russo, Stefania
-
Besmer, Michael ...
-
Blumensaat, Fran ...
-
Bouffard, Damien
-
Disch, Andy
-
Hammes, Frederik
-
show more...
-
Hess, Angelika
-
Lürig, Moritz
-
Matthews, Blake
-
Minaudo, Camille
-
Morgenroth, Eber ...
-
Tran-Khac, Viet
-
Villez, Kris
-
show less...
- About the subject
-
- NATURAL SCIENCES
-
NATURAL SCIENCES
-
and Computer and Inf ...
-
- NATURAL SCIENCES
-
NATURAL SCIENCES
-
and Biological Scien ...
-
and Bioinformatics a ...
- Articles in the publication
-
Water Research
- By the university
-
Lund University