Comparison of Artificial Intelligence Based Roundabout Entry Capacity Models

This study focuses on the development of entry capacity models for roundabouts by using Genetic Algorithm (GA), Multi-variate Adaptive Regression spline (MARS) and Random Forest Regression (RFR) technique under heterogeneous traffic conditions. Required data were collected from 27 selected roundabouts of India by using high-definition video (HD) camera. Influence area for gap acceptance (INAGA) method is employed to find out the critical gap and follow up time. It is found from sensitivity analysis that variable like Entry width ( E w ) contributes the most while the follow-up time ( T f ) variable has less contribution in the proposed model.

[1]  Prasanta Kumar Bhuyan,et al.  Empirical capacity model for roundabouts under heterogeneous traffic flow conditions , 2017 .

[2]  Hari Krishna Gaddam,et al.  Comparative evaluation of roundabout capacities under heterogeneous traffic conditions , 2015 .

[3]  Amir Hossein Alavi,et al.  An evolutionary approach for modeling of shear strength of RC deep beams , 2013 .

[4]  Mustafa Özuysal,et al.  Capacity prediction for traffic circles: applicability of ANN , 2009 .

[5]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[6]  Sarat Kumar Das,et al.  Discussion of “Intelligent computing for modeling axial capacity of pile foundations”Appears in Canadian Geotechnical Journal, 47(2): 230–243. , 2010 .

[7]  P. Bhuyan,et al.  Development of Roundabout Entry Capacity Model Using INAGA Method for Heterogeneous Traffic Flow Conditions , 2017 .

[8]  Rajat Rastogi,et al.  Regression model for entry capacity of a roundabout under mixed traffic condition – an Indian case study , 2017 .

[9]  Satish Chandra,et al.  Estimation of critical gap on a roundabout by minimizing the sum of absolute difference in accepted gap data , 2015 .

[10]  Sambit Kumar Beura,et al.  Modeling Quality of Bicycle Accommodations on Urban Road Segments Using Functional Networks and Multivariate Adaptive Regression Spline Techniques , 2017 .

[11]  Hashem R Al-Masaeid,et al.  Capacity of Roundabouts in Jordan , 1997 .

[12]  G. De’ath,et al.  CLASSIFICATION AND REGRESSION TREES: A POWERFUL YET SIMPLE TECHNIQUE FOR ECOLOGICAL DATA ANALYSIS , 2000 .

[13]  Prasanta Kumar Bhuyan,et al.  Investigating Entry Capacity Models of Roundabouts under Heterogeneous Traffic Conditions , 2018 .

[14]  Prasanta Kumar Bhuyan,et al.  Roundabout entry capacity models: genetic programming approach , 2018 .