Accurate prediction of traffic flow is an integral component in most of the Intelligent Transportation Systems (ITS) applications. The data driven approach using Box-Jenkins Autoregressive Integrated Moving Average (ARIMA) models reported in most studies demands sound database for model building. Hence, the applicability of these models remains a question in places where the data availability could be an issue. The present study tries to overcome the above issue by proposing a prediction scheme using Seasonal ARIMA (SARIMA) model for short term prediction of traffic flow using only limited input data. A 3-lane arterial roadway in Chennai, India was selected as the study stretch and limited flow data from only three consecutive days was used for the model development using SARIMA. After necessary differencing to make the input time series a stationary one, the autocorrelation function (ACF) and partial autocorrelation function (PACF) were plotted to identify the suitable order of the SARIMA model. The model parameters were found using maximum likelihood method in R. The developed model was validated by performing 24 hrs. ahead forecast and the predicted flows were compared with the actual flow values. A comparison of the proposed model with historic average and naive method was also attempted. The effect of increase in sample size of input data on prediction results was studied. Short term prediction of traffic flow during morning and evening peak periods was also attempted using both historic and real time data. The mean absolute percentage error (MAPE) between actual and predicted flow was found to be in the range of 4–10, which is acceptable in most of the ITS applications. The prediction scheme proposed in this study for traffic flow prediction could be considered in situations where database is a major constraint during model development using ARIMA.

Accurate prediction of turning volumes at urban intersections is useful in Advanced Traffic Management Systems (ATMS). Existing studies on traffic flow prediction have mostly focused on midblock sections and only limited studies were undertaken on urban intersections. In the present study, models based on Seasonal Autoregressive Integrated Moving Average (SARIMA) were developed to predict the direction-wise turning volumes at an unsignalized three-leg intersection. Preceding three days of direction-wise turning volumes were used in the model to predict the following day’s turning volumes. Short term prediction of turning volumes was also experimented using both historic (preceding three days data) and real time data on the day of prediction. The results were promising with Mean Absolute Percentage Error (MAPE) of less than 10 in majority of the cases. The prediction scheme requires only limited data as input and open source software package R for estimation of model parameters and prediction.

Disturbance to the moving traffic, such as on-street parking and bus stop on carriageway normally called as side friction in the literature, is one of the major problems that impact the vehicular speed on urban arterials in developing countries like India. Regression model to study the mode-wise vehicular speeds using side friction and other influencing variables faces the problem of multicollinearity as there is a strong correlation between the independent variables which results in high R² and high p values. Instead of dropping the highly correlated variables which is the conventional practice to deal with multicollinearity, we proposed an approach of taking a linear combination and ratio of independent variables. To test the applicability of the proposed approach, traffic data from five locations in Hyderabad and Vellore in India having a wide variety of geometric and traffic characteristics with one or more side frictions were collected and regression models were built. It was found that the proposed approach of taking linear combination and ratio worked very well as the models exhibited a high R², low p values and low variance inflation factor. The regression models also forecast speeds with good and reasonable accuracy. For better understanding of the impact of side friction, the present study proposed an index called side friction index and it was found that the number of side friction elements and their impact are directly proportional. Also, the impact is not uniform across the different vehicle types. Though the present study focussed on side friction problem, the approach that we proposed in this paper to deal with multicollinearity can be applied in other fields as well.