An Automated Machine Learning Approach for Smart Waste Management Systems
Document identifier: oai:DiVA.org:ltu-77024
Access full text here:
10.1109/TII.2019.2915572Keyword: Natural Sciences,
Computer and Information Sciences,
Computer Sciences,
Naturvetenskap,
Data- och informationsvetenskap,
Datavetenskap (datalogi),
Automated machine learning (AutoML),
Classification algorithms,
Data mining,
Emptying detection,
Grid search,
Smart Waste Management,
Dependable Communication and Computation Systems,
Kommunikations- och beräkningssystemPublication year: 2019Relevant Sustainable Development Goals (SDGs):
The SDG label(s) above have been assigned by OSDG.aiAbstract: This paper presents the use of automated machine learning for solving a practical problem of a real-life Smart Waste Management system. In particular, the focus of the paper is on the problem of detection (i.e., binary classification) of emptying of a recycling container using sensor measurements. Numerous data-driven methods for solving the problem are investigated in a realistic setting where most of the events are not actual emptying. The investigated methods include the existing manually engineered model and its modification as well as conventional machines learning algorithms. The use of machine learning allows improving the classification accuracy and recall of the existing manually engineered model from $86.8\%$ and $47.9\%$ to $99.1\%$ and $98.2\%$ , respectively, when using the best performing solution. This solution uses a Random Forest classifier on a set of features based on the filling level at different given time spans. Finally, compared to the baseline existing manually engineered model, the best performing solution also improves the quality of forecasts for emptying time of recycling containers.
Authors
David Rutqvist
BnearlIT AB
Other publications
>>
Denis Kleyko
Luleå tekniska universitet; Datavetenskap; DCC
Other publications
>>
Fredrik Blomstedt
BnearlIT AB
Other publications
>>
Record metadata
Click to view metadata
header:
identifier: oai:DiVA.org:ltu-77024
datestamp: 2021-04-19T12:40:36Z
setSpec: SwePub-ltu
metadata:
mods:
@attributes:
version: 3.7
recordInfo:
recordContentSource: ltu
recordCreationDate: 2019-12-02
identifier:
http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-77024
10.1109/TII.2019.2915572
2-s2.0-85078311758
titleInfo:
@attributes:
lang: eng
title: An Automated Machine Learning Approach for Smart Waste Management Systems
abstract: This paper presents the use of automated machine learning for solving a practical problem of a real-life Smart Waste Management system. In particular the focus of the paper is on the problem of detection (i.e. binary classification) of emptying of a recycling container using sensor measurements. Numerous data-driven methods for solving the problem are investigated in a realistic setting where most of the events are not actual emptying. The investigated methods include the existing manually engineered model and its modification as well as conventional machines learning algorithms. The use of machine learning allows improving the classification accuracy and recall of the existing manually engineered model from $86.8\\%$ and $47.9\\%$ to $99.1\\%$ and $98.2\\%$ respectively when using the best performing solution. This solution uses a Random Forest classifier on a set of features based on the filling level at different given time spans. Finally compared to the baseline existing manually engineered model the best performing solution also improves the quality of forecasts for emptying time of recycling containers.
subject:
@attributes:
lang: eng
authority: uka.se
topic:
Natural Sciences
Computer and Information Sciences
Computer Sciences
@attributes:
lang: swe
authority: uka.se
topic:
Naturvetenskap
Data- och informationsvetenskap
Datavetenskap (datalogi)
@attributes:
lang: eng
topic: Automated machine learning (AutoML)
@attributes:
lang: eng
topic: classification algorithms
@attributes:
lang: eng
topic: data mining
@attributes:
lang: eng
topic: emptying detection
@attributes:
lang: eng
topic: grid search
@attributes:
lang: eng
topic: Smart Waste Management
@attributes:
lang: eng
authority: ltu
topic: Dependable Communication and Computation Systems
genre: Research subject
@attributes:
lang: swe
authority: ltu
topic: Kommunikations- och beräkningssystem
genre: Research subject
language:
languageTerm: eng
genre:
publication/journal-article
ref
note:
Published
3
Validerad;2020;Nivå 2;2020-02-27 (alebob)
name:
@attributes:
type: personal
namePart:
Rutqvist
David
role:
roleTerm: aut
affiliation: BnearlIT AB
@attributes:
type: personal
authority: ltu
namePart:
Kleyko
Denis
1990-
role:
roleTerm: aut
affiliation:
Luleå tekniska universitet
Datavetenskap
DCC
nameIdentifier:
denkle
0000-0002-6032-6155
@attributes:
type: personal
namePart:
Blomstedt
Fredrik
role:
roleTerm: aut
affiliation: BnearlIT AB
originInfo:
dateIssued: 2019
publisher: IEEE
relatedItem:
@attributes:
type: host
titleInfo:
title: IEEE Transactions on Industrial Informatics
identifier:
1551-3203
1941-0050
part:
detail:
@attributes:
type: volume
number: 16
@attributes:
type: issue
number: 1
extent:
start: 384
end: 392
physicalDescription:
form: print
typeOfResource: text