mdh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A machine learning approach to classify pedestrians’ events based on IMU and GPS
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.ORCID iD: 0000-0003-3802-4721
Mälardalen University.
Mälardalen University.
Mälardalen University.
Show others and affiliations
2019 (English)In: International Journal of Artificial Intelligence, ISSN 0974-0635, E-ISSN 0974-0635, Vol. 17, no 2, p. 154-167Article in journal (Refereed) Published
Abstract [en]

This paper investigates and implements six Machine Learning (ML) algorithms, i.e. Artificial Neural Network (ANN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Extra Tree (ET), and Gradient Boosted Trees (GBT) to classify different Pedestrians’ events based on Inertial Measurement Unit (IMU) and Global Positioning System (GPS) signals. Pedestrians’ events are pedestrian movements as the first step of H2020 project called SimuSafe1 with a goal to reduce traffic fatalities by doing risk assessments of the pedestrians. The movements the MLs’ models are attempting to classify are standing, walking, and running. Data, i.e. IMU, GPS sensor signals and other contextual information are collected by a smartphone through a controlled procedure. The smartphone is placed in five different positions onto the body of participants, i.e. arm, chest, ear, hand and pocket. The recordings are filtered, trimmed, and labeled. Next, samples are generated from small overlapping sections from which time and frequency domain features are extracted. Three different experiments are conducted to evaluate the performances in term of accuracy of the MLs’ models in different circumstances. The best performing MLs’ models determined by the average accuracy across all experiments is Extra Tree (ET) with a classification accuracy of 91%. 

Place, publisher, year, edition, pages
CESER Publications , 2019. Vol. 17, no 2, p. 154-167
Keywords [en]
Artificial Neural Network (ANN), Classification, Decision Tree (DT), Extra Tree (ET), Gradient Boosted Trees (GBT), Machine Learning (ML), Pedestrians’ event, Random Forest (RF), Support Vector Machine (SVM)
National Category
Bioinformatics (Computational Biology) Signal Processing
Identifiers
URN: urn:nbn:se:mdh:diva-45833Scopus ID: 2-s2.0-85073358186OAI: oai:DiVA.org:mdh-45833DiVA, id: diva2:1365520
Available from: 2019-10-25 Created: 2019-10-25 Last updated: 2019-12-16Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Scopushttp://www.ceser.in/ceserp/index.php/ijai/article/view/6260/6207

Authority records BETA

Ahmed, Mobyen Uddin

Search in DiVA

By author/editor
Ahmed, Mobyen UddinBrickman, StaffanDengg, AlexanderFasth, NiklasMihajlovic, MarkoNorman, Jacob
By organisation
Embedded SystemsMälardalen University
In the same journal
International Journal of Artificial Intelligence
Bioinformatics (Computational Biology)Signal Processing

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 136 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf