A Combination of PSO and SVM for Road Icing Forecast

The road icing is an adverse weather condition lead to dangerous driving conditions with consequential effects on road transportation. A numerical road icing predication approach is employed for automatic prediction of road icing conditions in three cities of Hubei Province, viz., Wuhan, Shiyan and Xianning. The approach is derived from the support vector machine (SVM). To improve the classification accuracy for road icing prediction, a modified particle swarm optimization (PSO) is employed to simultaneously optimize the SVM kernel function parameter and the penalty parameter. The modified PSO is derived from the genetic PSO, and employs the crossover operator and the mutation operator derived from the differential evolution to enhance searching performance. With the data from 1980 to 2006, using the proposed approach, the road icing models for the three cities in Hubei province are created, which have been used for the prediction from 2007 to 2008. The results have shown feasibility and effectiveness of the forecast approach.