Intelligent Trip Modeling for the Prediction of an Origin–Destination Traveling Speed Profile

Abstract

Accurate prediction of the traffic information in real time such as flow, density, speed, and travel time has important applications in many areas, including intelligent traffic control systems, optimizing vehicle operations, and the routing selection for individual drivers on the road. This is also a challenging problem due to dynamic changes of traffic states by many uncertain factors along a traveling route. In this paper, we present an Intelligent Trip Modeling System (ITMS) that was developed using machine learning to predict the traveling speed profile for a selected route based on the traffic information available at the trip starting time. The ITMS contains neural networks to predict short-term traffic speed based on the traveling day of the week, the traffic congestion levels at the sensor locations along the route, and the traveling time and distances to reach individual sensor locations. The ITMS was trained and evaluated by using ten months of traffic data provided by the California Freeway Performance Measurement System along a California Interstate I-405 route that is 26 mi long and contains 52 traffic sensors. The ITMS was also evaluated by the traffic data acquired from a 32-mi-long freeway section in the state of Michigan. Experimental results show that the proposed system, i.e., ITMS, has the capability of providing accurate predictions of dynamic traffic changes and traveling speed at the beginning of a trip and can generalize well to prediction of speed profiles on the freeway routes other than the routes the system was trained on.

The Driver Behaviour and Impact of Speed on Road Safety on the Motorways in Croatia

“…Mehar et al (2014) conducted a research of capacity of four-lane motorway for mixed traffic conditions by VISSIM simulation tool, to check, according to real measuring, the applicability of simulation [15]. The prediction of flow, density and the speed of traffic flow have wide application in many areas, using neural networks, developed by Park et al (2014) in the paper "Intelligent Trip Modelling for the Prediction of an Origin-Destination Travelling Speed Profile" [16]. The paper by Hooper et al (2014) determined the relationship between traffic flow and precipitation based on research done on the motorways in England [17].…”

“…Based on the distribution shown in Figure 3 the values of standard deviation were obtained (σ) 16.76, the arithmetic mean (MEAN) is 142.87, mode is 146.44 and median is 143.23. Looking at the resulting parameters of the normal distribution it can be seen that by excluding freight vehicles the average speed has increased from 139.01 to 142.87 km/h and the dispersion of speed (σ) has decreased from 21.41 to 16.76.…”

Neural Networks in Transportation Research – Recent Applications

“…The trained NN is capable of generating values of O-D matrices for almost real-time traffic management. In [13] a solution, which uses congestion detector values, vehicle positions and time of travel for short-term prediction of travel speed, is proposed. The travel speed on a given route is determined using multiple NNs working with traffic sensor data.…”

Speed Profile Prediction in Intelligent Transport Systems Exemplified by Vehicle to Vehicle Interactions

“…The time-lag recurrent network to predict the spot speed and travel time at four sensor locations for up to 15 min prediction is presented in paper [4]. In paper [13] an Intelligent Traffic Modeling System (ITMS) was developed to predict the speed profile from the origin to the destination of a given route.…”