Xiaosi Zeng

Development of Recurrent Neural Network Considering Temporal-Spatial Input Dynamics for Freeway Travel Time Modeling

This article discusses how the artificial neural network (ANN) is one advance approach to freeway travel time prediction. Various studies using different inputs have not come to consensus on the effects of input selections. In addition, very little discussion has been made on the temporal–spatial aspect of the ANN travel time prediction process. In this study, the authors employ an ANN ensemble technique to analyze the effects of various input settings on the ANN prediction performances. Volume, occupancy, and speed are used as inputs to predict travel times. The predictions are then compared against the travel times collected from the toll collection system in Houston, Texas. The results show speed or occupancy measured at the segment of interest may be used as the sole input to produce acceptable predictions, but all three variables together tend to yield the best prediction results. The inclusion of inputs from both upstream and downstream segments is statistically better than using only the inputs from current segment. It also appears that the magnitude of prevailing segment travel time can be used as a guideline to set up temporal input delays for better prediction accuracies. The evaluation of spatiotemporal input interactions reveals that past information on downstream and current segments is useful in improving prediction accuracy whereas past inputs from the upstream location do not provide as much constructive information. Finally, a variant of the state-space model (SSNN), namely time-delayed state-space neural network (TDSSNN), is proposed and compared against other popular ANN models. The comparison shows that the TDSSNN outperforms other networks and remains very comparable with the SSNN. Future research is needed to analyze TDSSNNs ability in corridor prediction settings.

Queue Length Estimation Using Connected Vehicle Technology for Adaptive Signal Control

This paper presents a mathematical model for real-time queue estimation using connected vehicle (CV) technology from wireless sensor networks. The objective is to estimate the queue length for queue-based adaptive signal control. The proposed model can be applied without signal timing, traffic volume, or queue characteristics as basic inputs. The model is also developed so that it can work with both fixed-time signals and actuated signals. Furthermore, a discrete wavelet transform (DWT) is applied to the queue estimation algorithm in this paper for the first time. The purpose of the DWT is to enhance the proposed queue estimation to be more accurate and consistent regardless of the randomness in the penetration ratio. Experimental results are provided to validate the proposed model in both pretimed control and actuated control with a microscopic simulator, i.e., VISSIM. The results indicate that the proposed algorithm is able to estimate the queue length from VISSIM in the test case with pretimed signal control reasonably well. The results in actuated control cases, which have not been studied previously, showed that the proposed algorithm remains as accurate as the pretimed control cases. The accuracy of the proposed queue estimation algorithm is obtained without relying on basic inputs that other models typically require but are often impractical to obtain. Therefore, it is expected that the proposed queue estimation model is applicable for adaptive signal control using CV technology in practice.

Person-Based Adaptive Priority Signal Control with Connected-Vehicle Information

The goal for transit signal priority (TSP) strategies is to improve the efficiency of urban transportation systems by promoting fast passage of system users. However, because conventional vehicle detection technologies require TSP strategies to be vehicle based, TSP may not lead to optimal results for person delay. This paper proposes a signal control model called PAPSCCI (person-based adaptive signal priority control with connected-vehicle information). First, by using vehicle speed and location information available from connected-vehicle technologies, the model explicitly computes individual vehicle delay. In this way the model avoids assumptions about vehicle arrivals, which often are inevitable in a delay calculation derived from a queuing model. Furthermore, in the model approach, the computation of delays for private vehicles is no different from that for public buses except in the priority level and unifies the two types of vehicles. With onboard passenger information, the PAPSCCI model computes person delay for every vehicle running through the intersection and offers a more accurate basis for person delay minimization. The performance of the PAPSCCI model is evaluated in a traffic simulation environment. Compared with the optimized timing from SYNCHRO, the PAPSCCI model produces 39%, 49%, and 30% decreases in bus passenger delays for one, two, and three conflicting bus routes, respectively. In addition, general automobiles experience about an 8% to 11% decrease in person delays, showing the potential of PAPSCCI as a general adaptive signal control model. Finally, a penetration rate study shows that the PAPSCCI model can consistently perform reasonably well even when only about 30% of vehicles are equipped with connected-vehicle technology.

Component GARCH Models to Account for Seasonal Patterns and Uncertainties in Travel-Time Prediction

Uncertainty is often associated with travel-time prediction. Traditional point prediction methods only provide point values that are unable to offer enough information on the reliability of prediction results. The recent development of statistical volatility models has given us an effective way to capture uncertainties in data. Generalized autoregressive conditional heteroskedasticity (GARCH) models have been widely used in transportation systems as a way to account for this uncertainty by providing more accurate prediction intervals. However, a GARCH model arguably does not consider the trend and seasonality in data. If there is a trend or seasonality, the performance of the GARCH model may be affected. In the context of travel-time prediction, this paper proposes two component GARCH models that are able to model trend and seasonal components through decomposition. The travel-time data obtained along a freeway corridor in Houston, TX, USA, were used to empirically test the performance of the proposed models. The study results indicate that the proposed models perform well when capturing uncertainties associated with travel-time prediction.