To improve the traffic efficiency of city-wide road networks, we propose a traffic signal control framework that prioritizes the optimal control policies on critical nodes in road networks. In this framework, we first use a data-driven approach to discover the critical nodes. Critical nodes are identified as nodes that would cause a dramatic reduction in the traffic efficiency of the road network if they were to fail. This approach models the dynamic of road networks using a tripartite graph based on the vehicle trajectories and can accurately identify the city-wide critical nodes from a global perspective. Second, for the discovered critical nodes, we introduce a novel traffic signal control approach based on deep reinforcement learning; this approach can learn the optimal policy via constantly interacting with the road network in an iterative mode. We conduct several experiments with a transportation simulator; the results of experiments show that the proposed framework reduces the average delay and travel time compared to the baseline methods.

In order to prevent the backward flow of piezoelectric pumps, this paper presents a single-active-chamber piezoelectric membrane pump with multiple passive check valves. Under the condition of a fixed total number of passive check valves, by means of changing the inlet valves and outlet valves’ configuration, the pumping characteristics in terms of flow rate and backpressure are experimentally investigated. Like the maximum flow rate and backpressure, the testing results show that the optimal frequencies are significantly affected by changes in the number inlet valves and outlet valves. The variation ratios of the maximum flow rate and the maximum backpressure are up to 66% and less than 20%, respectively. Furthermore, the piezoelectric pump generally demonstrates very similar flow rate and backpressure characteristics when the number of inlet valves in one kind of configuration is the same as that of outlet valves in another configuration. The comparison indicates that the backflow from the pumping chamber to inlet is basically the same as the backflow from the outlet to the pumping chamber. No matter whether the number of inlet valves or the number of outlet valves is increased, the backflow can be effectively reduced. In addition, the backpressure fluctuation can be significantly suppressed with an increase of either inlet valves or outlet valves. It also means that the pump can prevent the backflow more effectively at the cost of power consumption. The pump is very suitable for conditions where more accurate flow rates are needed and wear and fatigue of check valves often occur.

Bicycle is a man-powered, relatively low speed agile and vulnerable traffic mode. The paper presents a fuzzy logic based behavioural model to describe cyclist path planning behaviours at unsignalized intersections in mixed traffic flow situations (with many conflicts among motorcars, non-motor vehicles and pedestrians). Field data were collected for fuzzy logic modelling and for model calibration and validation, and the simulation results are promising. The model could be used in mixed traffic flow simulation and path planning models for personal mobility vehicles (PMVs).