Road link traffic speed pattern mining in probe vehicle data via soft computing techniques

This paper develops two soft computing models, i.e., the multilayer feedforward network (MFN) based model and the adaptive-network-based fuzzy inference system (ANFIS) based model, to mine the traffic speed patterns/trends for a road link using the sparse historical probe vehicles (PVs) data at the same link. The two models and an additional naive arithmetical average model are tested on the field datasets obtained in some Beijing (China)'s urban expressways. The results illustrate that the soft computing based models have higher robustness to the problem of missing data and their generalization capabilities are better than the arithmetic average model. Comprehensively considering all the performance metrics suggest that the ANFIS offers the best model of traffic trends in studied links. Furthermore, the traffic trends produced by ANFIS provide us the opportunities to identify some meaningful hidden traffic speed patterns. The missing data's influence on the mined traffic speed patterns is also investigated. It is found that the reliability of mined traffic speed patterns decreases with the increasing of the missing data's percentage. Nevertheless, ANFIS based model shows great robustness to the missing data problem.

Figure optionsDownload as PowerPoint slideHighlights
• The problem of mining traffic speed trends in sparse probe vehicles data is put forward.
• One average model and two soft computing models are developed to tackle the problem.
• ANFIS is the best model considering the robustness, smoothness and consistency.
• Some valuable hidden traffic speed patterns are identified by ANFIS model.
• ANFIS model shows great robustness to the missing data problem.