Evaluation of pedestrian mid-block road crossing behaviour using artificial neural network

Abstract

Pedestrians usually cross the road at mid-block locations in India because of the ease and convenience to reach their destination as compared to intersection locations. It is important to evaluate the pedestrian gap acceptance behavior at mid-block locations because of inadequate vehicular gaps under mixed traffic condition, which translates into the pedestrian road crossing behavior. The present study examines the pedestrian gap acceptance behaviour by employing an artificial neural network (ANN) model for understanding the decision making process of pedestrians, i.e., acceptance or rejection of vehicular gaps at a mid-block location. From the results it has been found that the pedestrian rolling gap, frequency of attempt, vehicular gap size, pedestrian speed change condition and vehicle speed have major role in pedestrian gap acceptance. These results can lead to a better design of pedestrian crossing facilities where adequate gaps are not available in vehicular flow at mid-block crosswalk locations. Language: en