Home > Archive > 2020 > Volume 10 Number 2 (Feb. 2020) >
IJMLC 2020 Vol.10(2): 220-226 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2020.10.2.923

The CAN FD Vehicle Network System with Machine Learning and Scheduling Algorithms

Yung-Hoh Sheu, Cheng-Yo Huang, Chen-Yu Yang, and Yi-Hong Lin

Abstract—The controller area network with flexible datarate (CAN FD) inherits the primary features of a controller area network (CAN); thus, exploring the possibility of establishing a hybrid CAN and CAN FD network is essential. To develop the CAN FD network effectively, this study proposed a machine learning K-means data clustering method. The K-means method algorithms, the squared Euclidean distance was used to cluster CAN FD data. The results showed that the proposed system was compatible with current CAN vehicle networks. Experiments on processing five data quantities of CAN FD data verified that the K-means algorithms could effectively reduce the data loss rate of the CAN FD network by changing the priority of various CAN FD data according to the clustering result. Specifically, given CAN FD arbitration phase rate = 1 Mbps, for the data phase rate = 2 and 4 Mbps, the data loss rates were reduced by 7.49% and 8.34%, respectively, by using the squared Euclidean distance algorithm.

Index Terms—Controller area network, controller area network with flexible data-rate, machine learning, K-means.

All authors are with the Department of Computer Science and Information Engineering, National Formosa University, Huwei, Yunlin, Taiwan (e-mail: yhsheu@nfu.edu.tw; 10763104@gm.nfu.edu.tw, 10563113@gm.nfu.edu.tw, 10763105@gm.nfu.edu.tw).


Cite: Yung-Hoh Sheu, Cheng-Yo Huang, Chen-Yu Yang, and Yi-Hong Lin, "The CAN FD Vehicle Network System with Machine Learning and Scheduling Algorithms," International Journal of Machine Learning and Computing vol. 10, no. 2, pp. 220-226, 2020.

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).


General Information

  • E-ISSN: 2972-368X
  • Abbreviated Title: Int. J. Mach. Learn.
  • Frequency: Quaterly
  • DOI: 10.18178/IJML
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals LibraryCNKI.
  • E-mail: ijml@ejournal.net

Article Metrics in Dimensions