High-Speed Data-Driven Methodology for Real-Time Traffic Flow Predictions: Practical Applications of ITS

Abstract

Despite the achievements of academic research on data-driven k-nearest neighbour nonparametric regression (KNN-NPR), the low-speed computational capability of the KNN-NPR method, which can occur during searches involving enormous amounts of historical data, remains a major obstacle to improvements of real-system applications. To overcome this critical issue successfully, a high-speed KNN-NPR framework, capable of generating short-term traffic volume predictions, is proposed in this study. The proposed method is based on a two-step search algorithm, which has the two roles of building promising candidates for input data during nonprediction times and identifying decision-making input data for instantaneous predictions at the prediction point. To prove the efficacy of the proposed model, an experimental test was conducted with large-size traffic volume data. It was found that the performance of the model not only at least equals that of linear-search-based KNN-NPR in terms of prediction accuracy, but also shows a substantially reduced execution time in approximating real-time applications. This result suggests that the proposed algorithm can be also effectively employed as a preprocess to select useful past cases for advanced learning-based forecasting models.