Bayesian network for red-light-running prediction at signalized intersections

Abstract

Red-light-running (RLR) is an important reason for the large number of intersection-related fatalities, injuries, and other losses. The accurate RLR prediction can effectively reduce crashes caused by RLR behavior. The RLR prediction is usually composed of two parts: the vehicle’s stop-or-go behavior and the arrival time when the vehicle reaches the stop line. Previous stop-or-go prediction models are usually based on embedded traffic sensors using machine learning algorithms. While based on the continuous trajectories collected by radar sensors, RLR prediction can be conducted more effectively. In this paper, a probabilistic stop-or-go prediction model based on the Bayesian network (BN) is proposed for RLR prediction. We extend the deterministic output into the probabilistic output, which provides decision-makers with greater autonomy. The causality of BN improves the interpretability of the prediction model. The BN model is calibrated and tested by the continuous trajectories data measured by radar sensors installed at a signalized intersection. We not only consider the movement measurements of individual vehicles (e.g., speed and acceleration), but also take into account the car-following behavior. As a comparison, different machine learning models and the model based on the inductive loop detection (ILD) are adopted. The results show that the proposed BN model has a high prediction accuracy and performs better in the feature interpretation. This paper provides a new way for probabilistic RLR prediction based on continuous trajectories, which will significantly improve traffic safety of signalized intersections.     

瞬态瑞雷波在地层勘探中的应用

根据瞬态瑞雷波的传播特性和测试原理,使用振动及动态信号采集分析系统采集分析了测试工点的瑞雷波信号,并得到了测试工点的地层分布情况和各层的物理特性.     

强夯施工对环境振动的影响分析

利用强夯法加固软弱地基时,其夯击能将以波的形式向外扩散,进而导致周围环境的振动.本文以半无限弹性体理论为基础,考察了瑞利波的径向振动量和竖向振动量沿地基深度的衰减特性,认为竖向振动量是引发环境安全的主要因素;通过现场实测,研究了强夯引起的自由场地地面振动加速度及振动速度随距离的衰减规律,并对隔振沟的隔振效果进行了测试研究.     

Using a SVM to evaluate damage to vibration isolators in an elastic raft system

Predicting damage to vibration isolators in a raft experiencing heavy shock loadings from explosions is an important task when designing a raft system. It is also vital to be able to research the vulnerability of heavily shocked floating rafts unreliable, especially when the allowable values The conventional approach to prediction has been or ultimate values of vibration isolators of supposedly uniform standard in a raft actually have differing and uncertain values due to defective workmanship. A new model for predicting damage to vibration isolators in a shocked floating raft system is presented in this paper. It is based on a support vector machine（SVM）, which uses Artificial Intelligence to characterize complicated nonlinear mapping between the impacting environment and damage to the vibration isolators. The effectiveness of the new method for predicting damage was illustrated by numerical simulations, and shown to be effective when relevant parameters of the model were chosen reasonably. The effect determining parameters, including kernel function and penalty factors, has on prediction results is also discussed. It can be concluded that the SVM will probably become a valid tool to study damage or vulnerability in a shocked raft system.     

基于同方差的递增时间序列自回归预测的改善方法

提出了"利用反双曲正弦函数变换提高数据列光滑程度"的新结论,获得了递增时间序列改善的自回归预测新方法。     

石首长江公路大桥斜拉索杠杆质量阻尼器应用研究

石首长江公路大桥主桥为主跨820 m的双塔六跨连续不对称空间双索面混合梁斜拉桥,最长斜拉索长约440 m,在外部激励作用下极易发生面内、外振动.针对石首长江公路大桥斜拉索的振动特性,在常规阻尼器的基础上进行构造优化设计,研发了一种双杆倒Y形连接杆斜拉索杠杆质量阻尼器,具有景观协调性好、横向连接刚度大、减振效果好等优点....     

动态管理模式下路侧停车泊位占有率预测方法

城市停车已逐步实现信息化和动态化管理,本文对动态管理模式下大范围路侧泊位占有率预测方法进行研究.在收集美国旧金山492万条停车交易数据的基础上,利用可同时提取数据空间关联和时序趋势特征的卷积长短时记忆神经网络(Convolutional LSTM Network,ConvLSTM),分别构建考虑停车费率和时限动态变化的有政策模型,和没有动态管理信息输入的无政策模型.结果显示,有政策模型的训练效率和预测精度会显著提升.在政策平稳阶段,两种模型均能够有效预测泊位占有率;在政策发生变化时段,无政策模型的预测误差出现激增,但有政策模型的预测误差依然保持平稳,表明本文提出的方法能够很好地应对动态管理模式下停车需求的变化.     

道路网短期交通流预测方法比较

介绍了用于短期交通流预测的两大类模型:统计预测算法和人工神经网络模型.对其中各种模型的特征进行了比较,将历史平均模型、求和自回归滑动平均模型(ARIMA)、非参数回归模型、径向基函数(RBF)神经网络模型与贝叶斯组合神经网络模型,应用于一个真实路网的短期流量预测,比较了各模型的预测结果.结果表明,组合神经网络模型预测误差最小,可靠性最高,是一种对短期交通流预测的有效方法.     

双索悬索桥自振特性分析

以黄河大峡水库下游某双索悬索桥为工程背景,引入只受拉三维拉索单元,采用考虑几何非线性的子空间迭代法对其自振特性进行了分析,理论值与实测值能较好的吻合,说明了该空间非线性有限元分析方法的正确性;进而与相同跨径和结构参数的单索悬索桥的自振频率、振型进行了对比分析,结果表明双索悬索桥能有效提高桥梁一阶竖弯振动频率,为双索悬索桥结构设计理论提供了动力性能方面的依据.     

接触网检测车振动补偿研究

针对接触检测车实际工况,分析了检测车车体振动的动力学特性,建立了基于运动规律的数学模型,论述了训练样本得出检测车拉出值振动补偿函数的原理和方法。