Tracking Time Evolving Data Streams for Short-Term Traffic Forecasting

Abstract

Data streams have arisen as a relevant topic during the last few years as an efficient method for extracting knowledge from big data. In the robust layered ensemble model (RLEM) proposed in this paper for shortterm traffic flow forecasting, incoming traffic flow data of all connected road links are organized in chunks corresponding to an optimal time lag. The RLEM model is composed of two layers. In the first layer, we cluster the chunks by using the Graded Possibilistic c-Means method. The second layer is made up by an ensemble of forecasters, each of them trained for short-term traffic flow forecasting on the chunks belonging to a specific cluster. In the operational phase, as a new chunk of traffic flow data presented as input to the RLEM, its memberships to all clusters are evaluated, and if it is not recognized as an outlier, the outputs of all forecasters are combined in an ensemble, obtaining in this a way a forecasting of traffic flow for a short-term time horizon. The proposed RLEM model is evaluated on a synthetic data set, on a traffic flow data simulator and on two real-world traffic flow data sets. The model gives an accurate forecasting of the traffic flow rates with outlier detection and shows a good adaptation to nonstationary traffic regimes. Given its characteristics of outlier detection, accuracy, and robustness, RLEM can be fruitfully integrated in traffic flow management systems.

Statistical Analysis and Prediction of Parking Behavior

“…Predicting parking behavior makes a lot of sense. Several related works have been developed in recent years [1,18,21,29]. These studies proposed models to predict parking space availability and occupancy, which partially depicts parking behavior.…”

Why High-Performance Modelling and Simulation for Big Data Applications Matters

“…learning) methods, provides a complementary approach. With the availability of smart sensing technologies, like automatic vehicle counting from standard surveillance cameras, it is possible to devise decentralised solutions that measure the current situation of traffic flow on each road, perform local communication between nodes, and forecast the conditions for the immediate future using machine learning algorithms [160]. These may be augmented with evaluations of unexpectedness and per-node traffic jam prediction.…”

Clustering of nonstationary data streams: A survey of fuzzy partitional methods

“…Another application can be in short‐term road traffic forecasting (Abdullatif, Masulli, & Rovetta, ). The forecast of vehicle flow and density on a given road in the next few minutes can be based on a model of traffic conditions that represents different situations (different times of the day, different days of the week) as individual clusters.…”