This study investigated the challenges of calibration of the PARAMICS microscopic simulation model for the local traffic conditions in the Kingdom of Saudi Arabia. It proposed an adaptive neuro-fuzzy inference system (ANFIS) based calibration protocol for the PARAMICS model. The developed ANFIS model performs adequately in modeling the queue length as a function of two key calibration parameters, namely mean headway time and mean reaction time. The selected values of the calibration parameters obtained through the ANFIS modeling approach were used as the input parameters for the PARAMICS model. The error indices such as mean absolute errors and mean absolute percentage errors of the developed ANFIS model in predicting the queue lengths varied between 1.11 and 1.24, and between 3.44 and 4.06, respectively. The conformance of the PARAMICS output and the measured queue length indicates the validity of the proposed calibration protocol.
Bibliographical noteFunding Information:
The authors wish to acknowledge the financial support provided by the Deanship of Scientific Research (DSR) of King Fahd University of Petroleum and Minerals, Saudi Arabia in carrying out this research under the project titled "PARAMICS Model Development for Local Traffic Conditions in Saudi Arabia" (Project No. IN111047).
© 2016, National Research Council of Canada. All rights reserved.
- Adaptive neuro-fuzzy inference system (ANFIS)
- Microscopic model calibration
- Microscopic simulation model
- PARAMICS model
- Saudi Arabia
ASJC Scopus subject areas
- Civil and Structural Engineering
- Environmental Science (all)