Highway Capacity Manual改訂の動向--テイラ-教授の講演より

Since the early 1980s, short-term traffic forecasting has been an integral part of most Intelligent Transportation Systems (ITS) research and applications; most effort has gone into developing methodologies that can be used to model traffic characteristics and produce anticipated traffic conditions. Existing literature is voluminous, and has largely used single point data from motorways and has employed univariate mathematical models to predict traffic volumes or travel times. Recent developments in technology and the widespread use of powerful computers and mathematical models allow researchers an unprecedented opportunity to expand horizons and direct work in 10 challenging, yet relatively under researched, directions. It is these existing challenges that we review in this paper and offer suggestions for future work.

Short-term traffic forecasting: Where we are and where we’re going

Transportation research. part c, emerging technologies

Computer Aided Civil and Infrastructure Engineering

Short-term passenger demand forecasting is of great importance to the on-demand ride service platform, which can incentivize vacant cars moving from over-supply regions to over-demand regions. The spatial dependencies, temporal dependencies, and exogenous dependencies need to be considered simultaneously, however, which makes short-term passenger demand forecasting challenging. We propose a novel deep learning (DL) approach, named the fusion convolutional long short-term memory network (FCL-Net), to address these three dependencies within one end-to-end learning architecture. The model is stacked and fused by multiple convolutional long short-term memory (LSTM) layers, standard LSTM layers, and convolutional layers. The fusion of convolutional techniques and the LSTM network enables the proposed DL approach to better capture the spatio-temporal characteristics and correlations of explanatory variables. A tailored spatially aggregated random forest is employed to rank the importance of the explanatory variables. The ranking is then used for feature selection. The proposed DL approach is applied to the short-term forecasting of passenger demand under an on-demand ride service platform in Hangzhou, China. The experimental results, validated on the real-world data provided by DiDi Chuxing, show that the FCL-Net achieves the better predictive performance than traditional approaches including both classical time-series prediction models and state-of-art machine learning algorithms (e.g., artificial neural network, XGBoost, LSTM and CNN). Furthermore, the consideration of exogenous variables in addition to the passenger demand itself, such as the travel time rate, time-of-day, day-of-week, and weather conditions, is proven to be promising, since they reduce the root mean squared error (RMSE) by 48.3%. It is also interesting to find that the feature selection reduces 24.4% in the training time and leads to only the 1.8% loss in the forecasting accuracy measured by RMSE in the proposed model. This paper is one of the first DL studies to forecast the short-term passenger demand of an on-demand ride service platform by examining the spatio-temporal correlations.

Short-term forecasting of passenger demand under on-demand ride services: A spatio-temporal deep learning approach

Short term traffic flow forecasting has received sustained attention for its ability to provide the anticipatory traffic condition required for proactive traffic control and management. Recently, a stochastic seasonal autoregressive integrated moving average plus generalized autoregressive conditional heteroscedasticity (SARIMA + GARCH) process has gained increasing notice for its ability to jointly generate traffic flow level prediction and associated prediction interval. Considering the need for real time processing, Kalman filters have been utilized to implement this SARIMA + GARCH structure. Since conventional Kalman filters assume constant process variances, adaptive Kalman filters that can update the process variances are investigated in this paper. Empirical comparisons using real world traffic flow data aggregated at 15-min interval showed that the adaptive Kalman filter approach can generate workable level forecasts and prediction intervals; in particular, the adaptive Kalman filter approach demonstrates improved adaptability when traffic is highly volatile. Sensitivity analyses show that the performance of the adaptive Kalman filter stabilizes with the increase of its memory size. Remarks are provided on improving the performance of short term traffic flow forecasting.

Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification

The effect of limestone on the hydration and microstructural development of ultra high performance concrete (UHPC) with different levels of replacement (34%, 54% and 74% by volume) was investigated. Up to 54% replacement of cement by limestone the mixes showed better workability and higher compressive strength (170 MPa at 56 days for 54% addition) compared to a classical mix (155 MPa) with no limestone replacement. The kinetics of hydration were compared for different replacement levels using isothermal calorimetry. The phase development was quantified by X-ray diffraction with Rietveld method combined with thermal gravimetric analysis. The pore structure was examined by mercury intrusion porosimetry. The composition of hydration products was determined by scanning electron microscopy with energy dispersive X-ray analysis. The results showed that the hydration degree of the cement is increased from 39% for classical UHPC to 66% for the UHPC with 54% of limestone.

Effect of cement substitution by limestone on the hydration and microstructural development of ultra-high performance concrete (UHPC)

Effect of replacement of silica fume with calcined clay on the hydration and microstructural development of eco-UHPFRC

It is the first systematic research in the world on the composition design of epoxy asphalt concrete as paving material. Material characteristics and service performance of mixture, fatigue resistance characteristics of epoxy asphalt concrete by the fatigue test of complex beam have also been described. This research indicates that epoxy asphalt concrete is a good type of paving material. Research results have been applied successfully in the paving of steel deck of the Second Nanjing Yangtze River Bridge (SNYRB). It provides a new paving type for long-span steel bridges of China and has a bright application prospect.

Epoxy asphalt concrete paving on the deck of long-span steel bridges

Distributed tracking problem for complex dynamical networks with Lipschitz-type nonlinear dynamics under the framework of cyber-physical systems is investigated. Due to practical limitations in some circumstances, the states of the agents are usually unavailable for controllers, so distributed observers used to reconstruct the states of nodes are needed, which will be first designed. Differing from other studies of observer-based control problems for complex dynamical networks and multi-agent systems, it considers here the scenario that the communication channels for controllers and observers may be subjected to frequently malicious attacks, which will destroy the communication links and result in disconnected topologies of the communication networks. It is assumed that the impacts of attacks on different communication networks are different and independent. New security control strategies are proposed and analyzed. An algorithm to properly select the feedback gain matrices and coupling strengths is presented. By utilizing the Lyapunov stability theory, sufficient conditions are derived to check whether final consensus tracking can be achieved against such attacks. Finally, a simulation example comparing the security control and uncontrolled scenarios is demonstrated to show the effectiveness of the theoretical results.

Wei Huang

Papers

Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification

Effect of cement substitution by limestone on the hydration and microstructural development of ultra-high performance concrete (UHPC)

Effect of replacement of silica fume with calcined clay on the hydration and microstructural development of eco-UHPFRC

Epoxy asphalt concrete paving on the deck of long-span steel bridges

Distributed Observer-Based Cyber-Security Control of Complex Dynamical Networks