Flow-aware WPT k-nearest neighbours regression for short-term traffic prediction

摘要: Robust and accurate traffic prediction is critical in modern intelligent transportation systems (ITS). One widely used method for short-term k-nearest neighbours (kNN). However, choosing the right parameter values kNN problematic. Although many studies have investigated this problem, they did not consider all parameters of at same time. This paper aims to improve accuracy by tuning simultaneously concerning dynamic characteristics. We propose weighted tuples (WPT) calculate average dynamically according flow rate. Comprehensive experiments are conducted on one-year real-world data. The results show that flow-aware WPT performs better than manually tuned as well benchmark methods such extreme gradient boosting (XGB) seasonal autoregressive integrated moving (SARIMA). Thus, it recommended use regarding