Towards a Parameter Tuning Approach for a Map-Matching Algorithm

Carola Blazquez1, Jana Ries2, Pablo Miranda3

  • 1Universidad Andres Bello
  • 2University of Portsmouth
  • 3Pontificia Universidad Catolica de Valparaiso

Details

Category

Regular Paper

Sessions

15:48 - 17:36 | Tue 27 Jun | | TuDPl

Intelligent Vehicles and Navigation Systems

Full Text

Abstract

Map Matching Algorithms (MMA) are developed to solve spatial ambiguities that arise in the process of assigning GPS measurements onto a digital roadway network. There is a lack of systematic parameter tuning approaches for optimizing the MMA performance. Thus, a novel integrated framework is proposed for a systematic calibration of the parameters of a post-processing MMA. The calibration approach consists of an Instance-specific Parameter Tuning Strategy (IPTS) that employs Fuzzy Logic principles. The proposed fuzzy IPTS tool determines the best algorithm parameter values by using instance-specific information a priori to the execution of the MMA. A preliminary prototype of an IPTS system is designed based on real-world data, which identifies the explanatory variables that condition the MMA performance. The implementation of the fuzzy IPTS tool on real-word data yields an enhanced MMA performance in the solution quality and computational time compared to the results of the execution of the MMA with constant algorithm settings.

Additional Information

No information added

Video

No videos found