http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
( Si Shen ),( Guojiang Shen ),( Yang Shen ),( Duanyang Liu ),( Xi Yang ),( Xiangjie Kong ) 한국인터넷정보학회 2020 KSII Transactions on Internet and Information Syst Vol.14 No.11
Advanced traffic signal timing method plays very important role in reducing road congestion and air pollution. Reinforcement learning is considered as superior approach to build traffic light timing scheme by many recent studies. It fulfills real adaptive control by the means of taking real-time traffic information as state, and adjusting traffic light scheme as action. However, existing works behave inefficient in complex intersections and they are lack of feasibility because most of them adopt traffic light scheme whose phase sequence is flexible. To address these issues, a novel adaptive traffic signal timing scheme is proposed. It's based on actor-critic reinforcement learning algorithm, and advanced techniques proximal policy optimization and generalized advantage estimation are integrated. In particular, a new kind of reward function and a simplified form of state representation are carefully defined, and they facilitate to improve the learning efficiency and reduce the computational complexity, respectively. Meanwhile, a fixed phase sequence signal scheme is derived, and constraint on the variations of successive phase durations is introduced, which enhances its feasibility and robustness in field applications. The proposed scheme is verified through field-data-based experiments in both medium and high traffic density scenarios. Simulation results exhibit remarkable improvement in traffic performance as well as the learning efficiency comparing with the existing reinforcement learning-based methods such as 3DQN and DDQN.
Xiangjie Kong,Guojiang Shen,Feng Xia,Chuang Lin 제어·로봇·시스템학회 2011 International Journal of Control, Automation, and Vol.9 No.1
This paper presents a new two-direction green wave intelligent control strategy to solve the coordina-tion control problem of urban arterial traffic. The whole control structure includes two layers - the coordination layer and the control layer. Public cycle time, splits, inbound offset and outbound offset are calculated in the coordination layer. Public cycle time is adjusted by fuzzy neural networks (FNN) according to the traffic flow saturation degree of the key intersection. Splits are calculated based on historical and real-time traffic information. Offsets are calculated by the real-time average speeds. The control layer determines phase composition and adjusts splits at the end of each cycle. The target of this control strategy is to maximize the possibility for vehicles in each direction along the arterial road to pass the local intersection without stop while the utility efficiency of the green signal time is at relatively high level. The actual application results show the proposed method can decrease the average travel time and average number of stops, and increase the average travel speed for vehicles on the arterial road effectively.
Crowd Activity Classification Using Category Constrained Correlated Topic Model
( Xianping Huang ),( Wanliang Wang ),( Guojiang Shen ),( Xiaoqing Feng ),( Xiangjie Kong ) 한국인터넷정보학회 2016 KSII Transactions on Internet and Information Syst Vol.10 No.11
Automatic analysis and understanding of human activities is a challenging task in computer vision, especially for the surveillance scenarios which typically contains crowds, complex motions and occlusions. To address these issues, a Bag-of-words representation of videos is developed by leveraging information including crowd positions, motion directions and velocities. We infer the crowd activity in a motion field using Category Constrained Correlated Topic Model (CC-CTM) with latent topics. We represent each video by a mixture of learned motion patterns, and predict the associated activity by training a SVM classifier. The experiment dataset we constructed are from Crowd_PETS09 bench dataset and UCF_Crowds dataset, including 2000 documents. Experimental results demonstrate that accuracy reaches 90%, and the proposed approach outperforms the state-of-the-arts by a large margin.