mdh.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Data Analysis on Powered Two Wheelers Riders’ Behaviour using Machine Learning
Mälardalens högskola, Akademin för innovation, design och teknik, Inbyggda system.ORCID-id: 0000-0003-3802-4721
UPE-IFSTTAR/TS2/SIMU&MOTO, F-77447 Marne la Vallée Cedex, France.
Visa övriga samt affilieringar
2019 (Engelska)Ingår i: First International Conference on Advances in Signal Processing and Artificial Intelligence ASPAI' 2019, Barcelona, Spain, 2019Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Analyzing powered two-wheeler rider behavior, i.e. classification of riding patterns based on 3-D accelerometer/gyroscope sensors mounted on motorcycles is challenging. This paper presents machine learning approach to classify four different riding events performed by powered two wheeler riders’ as a step towards increasing traffic safety. Three machine learning algorithms, Random Forest (RF), Support Vector Machine (SVM) and Artificial Neural Network (ANN) have been used to classify riding patterns. The classification is conducted based on features extracted in time and frequency domains from accelerometer/gyroscope sensors signals. A comparison result between different filter frequencies, window sizes, features sets, as well as machine learning algorithms is presented. According to the results, the Random Forest method performs most consistently through the different data sets and scores best.

Ort, förlag, år, upplaga, sidor
Barcelona, Spain, 2019.
Nyckelord [en]
machine learning, Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN), powered two-wheeler, classification of riding patterns, accelerometer/gyroscope.
Nationell ämneskategori
Teknik och teknologier Datorsystem
Identifikatorer
URN: urn:nbn:se:mdh:diva-43909OAI: oai:DiVA.org:mdh-43909DiVA, id: diva2:1325085
Konferens
First International Conference on Advances in Signal Processing and Artificial Intelligence ASPAI' 2019, 20 Mar 2019, Barcelona, Spain
Projekt
BRAINSAFEDRIVE: A Technology to detect Mental States During Drive for improving the Safety of the roadTillgänglig från: 2019-06-14 Skapad: 2019-06-14 Senast uppdaterad: 2019-06-14Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Personposter BETA

Ahmed, Mobyen Uddin

Sök vidare i DiVA

Av författaren/redaktören
Ahmed, Mobyen Uddin
Av organisationen
Inbyggda system
Teknik och teknologierDatorsystem

Sök vidare utanför DiVA

GoogleGoogle Scholar

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 97 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf