Publications:APPES Maps as Tools for Quantifying Performance of Truck Drivers

Revision as of 21:41, 30 September 2016 by Slawek (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Do not edit this section

Keep all hand-made modifications below

Title APPES Maps as Tools for Quantifying Performance of Truck Drivers
Author Iulian Carpatorea and Sławomir Nowaczyk and Thorsteinn Rögnvaldsson and Marcus Elmer
Year 2014
PublicationType Conference Paper
HostPublication Proceedings of the 2014 International Conference on Data Mining, DMIN'14
Conference The 10th International Conference on Data Mining, DMIN´14, July 21-24, Las Vegas, Nevada, USA
Diva url
Abstract Understanding and quantifying drivers’ influenceon fuel consumption is an important and challenging problem.A number of commonly used approaches are based on collectionofAccelerator Pedal Position - Engine Speed(APPES) maps. Upuntil now, however, most publicly available results are basedon limited amounts of data collected in experiments performedunder well-controlled conditions. Before APPES maps can beconsidered a reliable solution, there is a need to evaluate theusefulness of those models on a larger and more representativedata.In this paper we present analysis of APPES maps that werecollected, under actual operating conditions, on more than1200 trips performed by a fleet of 5 Volvo trucks owned bya commercial transporter in Europe. We use Gaussian MixtureModels to identify areas of those maps that correspond todifferent types of driver behaviour, and investigate how theparameters of those models relate to variables of interest suchas vehicle weight or fuel consumption.