Travel time prediction model of freeway based on gradient boosting decision tree

To investigate the travel time prediction method of the freeway, a model based on the gradient boosting decision tree (GBDT) is proposed. Eleven variables (namely, travel time in current period T i , traffic flow in current period Q i , speed in current period V i , density in current period K i , the number of vehicles in current period N i , occupancy in current period R i , traffic state parameter in current period X i , travel time in previous time period T i -1 , etc.) are selected to predict the travel time for 10 min ahead in the proposed model. Data obtained from VISSIM simulation is used to train and test the model. The results demonstrate that the prediction error of the GBDT model is smaller than those of the back propagation (BP) neural network model and the support vector machine (SVM) model. Travel time in current period T i is the most important variable among all variables in the GBDT model. The GBDT model can produce more accurate prediction results and mine the hidden nonlinear relationships deeply between variables and the predicted travel time.

A PSO-SVM Model for Short-Term Travel Time Prediction Based on Bluetooth Technology

The accurate prediction of travel time along roadway provides valuable traffic information for travelers and traffic managers. Aiming at short-term travel time forecasting on urban arterials,a prediction model( PSOSVM) combining support vector machine( SVM) and particle swarm optimization( PSO) is developed. Travel time data collected with Bluetooth devices are used to calibrate the proposed model. Field experiments show that the PSO-SVM model 's error indicators are lower than the single SVM model and the BP neural network( BPNN) model. Particularly,the mean-absolute percentage error( MAPE) of PSO-SVM is only 9. 453 4 %which is less than that of the single SVM model( 12. 230 2 %) and the BPNN model( 15. 314 7 %). The results indicate that the proposed PSO-SVM model is feasible and more effective than other models for shortterm travel time prediction on urban arterials.

Trip-oriented travel time prediction （TOTTP） with historical vehicle trajectories

Accurate travel time prediction is undoubtedlyof importance to both traffic managers and travelers. Inhighly-urbanized areas, trip-oriented travel time prediction（TOTTP） is valuable to travelers rather than trafficmanagers as the former usually expect to know the traveltime of a trip which may cross over multiple road sections.There are two obstacles to the development of TOTTP,including traffic complexity and traffic data coverage. Withlarge scale historical vehicle trajectory data and meteorol-ogy data, this research develops a BPNN-based approachthrough integrating multiple factors affecting trip traveltime into a BPNN model to predict trip-oriented travel timefor OD pairs in urban network. Results of experimentsdemonstrate that it helps discover the dominate trends oftravel time changes daily and weekly, and the impact ofweather conditions is non-trivial.

Prediction based traffic management in a metropolitan area

In recent years,modern metropolitan areas are the main indicators of economic growth of nation.In metropolitan areas,number and frequency of vehicles have increased tremendously,and they create issues,like traffic congestion,accidents,environmental pollution,economical losses and unnecessary waste of fuel.In this paper,we propose traffic management system based on the prediction information to reduce the above mentioned issues in a metropolitan area.The proposed traffic management system makes use of static and mobile agents,where the static agent available at region creates and dispatches mobile agents to zones in a metropolitan area.The migrated mobile agents use emergent intelligence technique to collect and share traffic flow parameters(speed and density),historical data,resource information,spatio-temporal data and so on,and are analyzes the static agent.The emergent intelligence technique at static agent uses analyzed,historical and spatio-temporal data for monitoring and predicting the expected patterns of traffic density(commuters and vehicles)and travel times in each zone and region.The static agent optimizes predicted and analyzed data for choosing optimal routes to divert the traffic,in order to ensure smooth traffic flow and reduce frequency of occurrence of traffic congestion,reduce traffic density and travel time.The performance analysis is performed in realistic scenario by integrating NS2,SUMO,OpenStreatMap(OSM)and MOVE tool.The effectiveness of the proposed approach has been compared with the existing approach.

User preference-based intelligent road route recommendation using SARSA and dynamic programming

Traffic congestion is one of the main challenges in transportation engineering. It directly impactsthe economy by increasing travel time and affecting the environment by excessive fuel consumptionand emission. Road route recommendation to overcome the congestion by alternativeroute suggestions has gained high importance. The existing route recommendation systems areproposed using the reinforcement learning algorithm (Q-learning). The techniques suggestedin this paper are state-action-reward-state-action (SARSA) algorithm and dynamic programming(DP) to guide the commuters to reach the destination with an optimal solution. The algorithmconsiders travel time, cost, flexibility, and traffic intensity as the user preference attributes torecommend an optimal route. The recommended system is implemented by building a roadnetwork graph. We assign values to each user preference attribute along the edges, which cantake high(1) or low(0) values. By considering these values, the system recommends the route.The proposed system performance is evaluated based on computation time, cumulative reward,and accuracy. The results show that DP outperforms the SARSA algorithm.