du.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Evaluation of Supervised Machine LearningAlgorithms for Detecting Anomalies in Vehicle’s Off-Board Sensor Data
Högskolan Dalarna, Akademin Industri och samhälle, Mikrodataanalys.
2018 (engelsk)Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
Abstract [en]

A diesel particulate filter (DPF) is designed to physically remove diesel particulate matter or soot from the exhaust gas of a diesel engine. Frequently replacing DPF is a waste of resource and waiting for full utilization is risky and very costly, so, what is the optimal time/milage to change DPF? Answering this question is very difficult without knowing when the DPF is changed in a vehicle.

We are finding the answer with supervised machine learning algorithms for detecting anomalies in vehicles off-board sensor data (operational data of vehicles). Filter change is considered an anomaly because it is rare as compared to normal data.

Non-sequential machine learning algorithms for anomaly detection like oneclass support vector machine (OC-SVM), k-nearest neighbor (K-NN), and random forest (RF) are applied for the first time on DPF dataset. The dataset is unbalanced, and accuracy is found misleading as a performance measure for the algorithms. Precision, recall, and F1-score are found good measure for the performance of the machine learning algorithms when the data is unbalanced. RF gave highest F1-score of 0.55 than K-NN (0.52) and OCSVM (0.51). It means that RF perform better than K-NN and OC-SVM but after further investigation it is concluded that the results are not satisfactory. However, a sequential approach should have been tried which could yield better result.

sted, utgiver, år, opplag, sider
2018.
Emneord [en]
Anomaly detection, rule-based, one class support vector machine, k-nearest neighbor, random forest, confusion matrix, accuracy, precision, recall, F1-score
HSV kategori
Identifikatorer
URN: urn:nbn:se:du-28962OAI: oai:DiVA.org:du-28962DiVA, id: diva2:1266683
Tilgjengelig fra: 2018-11-29 Laget: 2018-11-29

Open Access i DiVA

fulltext(1543 kB)51 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 1543 kBChecksum SHA-512
afa37ba56e7ca9d933a81f5a6b1d410690345dd060c04a5084c83d818ed0f88586aee117f832dc8e92dbd5d8b319f507ef38d3b22cbb4f14f62c81aa7d9e98f9
Type fulltextMimetype application/pdf

Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 51 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 86 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf