Search

With the rapid expansion of sensor technologies and wireless network infrastructure, research and development of traffic associated applications, such as real-time traffic maps, on-demand travel route reference and traffic forecasting are gaining much more attention than ever before. In this paper, we elaborate on our traffic prediction application, which is based on traffic data collected through Google Map API. Our application is a desktop-based application that predicts traffic congestion state using Estimated Time of Arrival (ETA). In addition to ETA, the prediction system takes into account various features such as weather, time period, special conditions, holidays, etc. The label of the classifier is identified as one of the five traffic states i.e. smooth, slightly congested, congested, highly congested or blockage. The results demonstrate that the random forest classification algorithm has the highest prediction accuracy of 92 percent followed by XGBoost and KNN respectively.

Automation of transportation and vehicular systems is one of the key steps towards achieving vision of digital transformation and smart cities. Intelligent transportation systems, congestion avoidance/prediction systems and automated route planning systems depend upon traffic data mostly collected through Global Positioning System (GPS) installed in trackers, navigators and even in mobile phones. Data collected from GPS systems has erratic traces which need to be resolved. In this paper, we pre-process Floating Car Data (FCD) obtained from vehicle trackers. We present a framework to synthesize tracker speed data and prepare it for visualization on Open Street Maps. The raw data passes through several corrective steps of the framework before the trajectories of individual vehicles can be plotted and visualized. These corrected speed data is than aggregated per unit time to be visualized on Open Street Maps(OSM). We have synthesized tracker speed data obtained from the Inter Junction Principal (IJP) road at the boundary of Islamabad and Rawalpindi in Pakistan. Several descriptive statistical techniques as well as Douglas-Peucker algorithm for trajectory plotting has been utilized and results have been discussed.