On Strategies Improving Accuracy of Speed Prediction from Floating Car Data (FCD)

Download

On Strategies Improving Accuracy of Speed Prediction from Floating Car Data (FCD).pdf

Date

2021-09-08

Author

Tüydeş Yaman, Hediye
Kocamaz, Korhan
Tuncay, Kağan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

177
views

118
downloads

For smart mobility, speed data extracted from Floating Car Data (FCD) plays an important role in speed predictionaccuracy. However, there are reliability issues for commercial FCD due to processing of individual vehicletracking data, and imposed temporal averaging to compress data size. Furthermore, spatial discretizationsignificantly affects the accuracy of the prediction due to uneven segment lengths and highly variable dataavailability in the network. In this study, these issues are examined in detail, and several strategies to improveaverage speed prediction are proposed. An extensive FCD data from a 75-km long corridor is utilized in thecalculations. Firstly, for data reliability, several filters are applied to clean data, then, a robust algorithm is appliedto smoothen the speed data. Secondly, to investigate and reduce prediction errors due to spatial segmentation, anumber of segmentation approaches are developed, and their effects on the average speed prediction are assessed.Finally, several autoregressive prediction models are implemented and a comprehensive comparison of results ispresented.

Subject Keywords

Floating Car Data, Data filtering, Data smoothening, Autoregressive prediction models

URI

https://ace2020.org/en/
https://hdl.handle.net/11511/93511

Conference Name

https://ace2020.org/en/

Collections

Department of Civil Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

A method to estimate traffic penetration rates of commercial floating car data using speed information Altintasi, Oruc; Tüydeş Yaman, Hediye; Tuncay, Kağan (2022-08-05) Floating Car Data (FCD) are being increasingly used as an alternative traffic data source due to its lower cost and high coverage area. FCD can be obtained by tracking vehicle trajectories individually or by processing multiple tracks anonymously to produce average speed information commercially. For commercial FCD, the spatio-temporal distribution of these vehicles in actual traffic, traffic Penetration Rate (PR) is the most important factor affecting the accuracy of speed estimations, despite the high num...
An Analytical Approach for the Calculation of Flux-Linkage Including End-Effect for SR Motors Özlü Ertan, Hatice Gülçin (2008-06-13) The accuracy of flux linkage-current-position curves has vital importance for designing SR motors. Analytical prediction of these curves is very difficult and as shown in this paper 2D approach leads to erroneous prediction of the flux linkage curves and hence significant errors in performance prediction of SR motors. This paper makes an important contribution to the design process by developing an approach for the analytical calculation of flux linkage-current-position curves including the end effect. As s...
A comparative study on tightly coupled visual aided inertial navigation systems for unmanned aerial vehicles İnce, Talha; Saranlı, Afşar; Department of Electrical and Electronics Engineering (2018) An Inertial Navigation System (INS) is a combination of hardware (accelerometers and gyroscopes) and algorithms to calculate the position, orientation and velocity of a mobile platform. Because of the need to integrate the measurements over time, INS is subjected to cumulative error characteristics, hence cannot provide an accurate navigation solution over long durations. Global Positioning System (GPS) is often used for long time-long distance problems aiding INS. GPS relies on external signals received fr...
Design optimization of variable frequency driven three-phase induction motors Ertan, B; Leblebicioğlu, Mehmet Kemal; Simsir, B; Hamarat, S; Cekic, A; Pirgaip, M (1998-01-01) An approach to optimize the design of three-phase induction motors for a wide speed range drive is considered. Two operating points in the speed range are taken into consideration. The problem is handled as a constrained optimization problem. An accurate model for the motor in terms of its dimensions has been developed which predicts the motor performance based on about 60 parameters of motor geometry.
Design and analysis of ultrashort femtosecond laser amplifiers Doğan, Ersin; Bilikmen, Kadri Sinan; Department of Physics (2006) This thesis presents a compact femtosecond laser amplifier design for optical preamplifiers and power amplifiers consist of theoretical perspective, simulations to analyze and optimize beam performance. The propagation through optical media is simulated for every optical component such as mirrors and nonlinear crystal separately and suggested realignment of these components required increasing amplifier performance. Finally Gaussian beam propagation and aberration compensation has been conducted.

Citation Formats

H. Tüydeş Yaman, K. Kocamaz, and K. Tuncay, “On Strategies Improving Accuracy of Speed Prediction from Floating Car Data (FCD),” İstanbul, Türkiye, 2021, vol. 1, Accessed: 00, 2021. [Online]. Available: https://ace2020.org/en/.