North-West University (NWU)

Neural models to implement environmentally friendly best fleet management practices Fuel cost is of critical importance to the profitability of road transport operators.  In addition, the transport industry is a primary contributor towards harmful emissions.  Earlier studies identified fuel economy as an important contributor towards fuel cost and found that truck driver behaviour is an important determinant for this phenomenon.  We used a representative data set to extract regression and neural models for fuel economy and used these models to remove the impact of factors not controlled by the driver, allowing us to measure driver performance more accurately.  All models extracted demonstrated significant out-of-sample predictive ability.  Neural models for fuel economy outperformed regression models.  We verified the significance of compensating for factors not controlled by the driver by demonstrating large differences in driver fuel economy ranking before and after compensating for route inclination and payload.