Abstract Intelligent traffic lights are an important part of intelligent transportation systems. In this paper, the Bayesian network theory is used to establish a traffic light independent intelligent decision model based on dynamic Bayesian network. According to the real-time dynamic information of traffic conditions, the proposed dynamic Bayesian network approximate reasoning algorithm is used to realize online reasoning and determine the best traffic light time. The algorithm combines the time window with the improved forward-backward algorithm. By adjusting the time window width of the algorithm, the evidence information can be used to maximize online reasoning. Compared with the existing time window based on interface algorithm, it's proved that the reasoning algorithm proposed is more efficient. The research results of this paper have important practical significance in solving the traffic congestion problem and reducing the waiting time of people at the intersection of traffic lights.

中文翻译：

---

基于动态贝叶斯推理的智能交通灯控制系统研究

摘要 智能交通灯是智能交通系统的重要组成部分。本文利用贝叶斯网络理论建立了基于动态贝叶斯网络的交通灯独立智能决策模型。根据交通状况的实时动态信息，采用所提出的动态贝叶斯网络近似推理算法实现在线推理，确定最佳红绿灯时间。该算法将时间窗口与改进的前向后向算法相结合。通过调整算法的时间窗宽度，可以利用证据信息最大化在线推理。与现有的基于接口算法的时间窗相比，证明了所提出的推理算法更加高效。