Intelligent Passenger Frequency Prediction System for Transportation Sustainability Using Convolutional Neural Network and Kalman Filter Algorithm

Abstract

The prediction of passenger flow operation is very significant to study due to the challenges of student transportation between inter-campuses of the Fed eral University of Technology Minna (FUTMinna), Nigeria. However, the prevailing technique of passenger flow estimation is non-parametric which depends on the fixed planning and is easily affected by noise. In this research, we proposed the use of a Convolutional Neural Network and Kalman Filter (CNN-KF) with an Auto-Regressive Integrated Moving Average (ARIMA) model for learning and prediction purposes of the passenger flow frequency on the inter-campuses arterial route. The passengers’ frequency of arrival at the bus terminals are obtained and enumerated through the closed-circuit television (CCTV) and demonstrated using the Markovian Queueing Systems Model (MQSM). The autocorrelation coefficient functions (ACF) and partial autocorrelation coefficient functions (PACF) are used to examine the stationary data with different features. The performance of the models was analyzed and evaluated in describing the passenger flow frequency at each terminal using the Mean Absolute Percentage Error (MAPE) and Mean Squared Error (MSE) values. The CNN-Kalman-filter model was fitted into the series and the MAPE values are below 10%, more than 80% percent of the time reflecting the abnormal fluctuations of passenger flow accuracy than ARIMA. The Mean Square Error (MSE) shows that the CNN-Kalman Filter model has the overall best performance with 83.33% of the time better than the ARIMA model and provides high accuracy in forecasting.