Public transport Bus Arrival Time Prediction with Seasonal and Special Emphasis on Weather Compensation changes using RNN

Abstract: Intelligent Transportation Systems is an application of current information and communications technologies to the transportation area. Bus arrival times are influenced by various factors, (e.g. weather conditions, traffic congestion and natural disasters etc) resulting delay in predefined schedule and inconvenience for passengers due to waiting times for buses. In this research, a set of ANN models, predicting bus arrival times based on seasonal changes, are developed through mining historical data for Jaipur – Delhi route, India. The results obtained are accurate, reduce average waiting and help in developed models which can be used to estimate bus arrival times. Recurrent neural network (RNN) techniques are applied to build an arrival time estimation model. The model exhibits a functional relation between real-time traffic data as the input variables and the predicted bus travel time according to weather conditions as the output variable.