Traffic Signal Timing via Deep Reinforcement Learning

In this paper, we propose a set of algorithms to design signal timing plans via deep reinforcement learning. The core idea of this approach is to set up a deep neural network (DNN) to learn the Q-function of reinforcement learning from the sampled traffic state/control inputs and the corresponding traffic system performance output. Based on the obtained DNN, we can find the appropriate signal timing policies by implicitly modeling the control actions and the change of system states. We explain the possible benefits and implementation tricks of this new approach. The relationships between this new approach and some existing approaches are also carefully discussed. © 2014 Chinese Association of Automation.

Artificial Bee Colony Algorithm-based Parameter Estimation of Fractional-order Chaotic System with Time Delay

It is an important issue to estimate parameters of fractional-order chaotic systems in nonlinear science, which has received increasing interest in recent years. In this paper, time delay and fractional order as well as system's parameters are concerned by treating the time delay and fractional order as additional parameters. The parameter estimation is converted into a multi-dimensional optimization problem. A new scheme based on artificial bee colony ABC algorithm is proposed to solve the optimization problem. Numerical experiments are performed on two typical time-delay fractional-order chaotic systems to verify the effectiveness of the proposed method. © 2014 Chinese Association of Automation.

An improved smoke-wire flow visualization technique using capacitor as power source

An improved smoke-wire flow visualization technique using a large capacitor as the power source was proposed. Electric current discharged from capacitors was used to heat a fine metal wire suspended in the flow field. The oil droplets attached to the wire were vaporized and smoke filaments followed the flow motions. A digital camera was used to record the images of the smoke filaments. The actions of discharging and camera shutter were triggered by signals from a microcontroller to ensure the accurate timing. Clear images of the streaklines were captured at a freestream velocity up to 12.9 m/s, much higher than the limits of the existing techniques.