会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 2. 发明授权
    • Method for monitoring the condition of traffic for a traffic network comprising effective narrow points
    • 用于监视包括有效窄点的交通网络的业务状况的方法
    • US06813555B1
    • 2004-11-02
    • US10088024
    • 2002-07-19
    • Boris Kerner
    • Boris Kerner
    • G06G776
    • G06T9/004G08G1/0104
    • In a method for monitoring traffic conditions in a traffic network with effective bottlenecks, the traffic state is classified, taking account of recorded measured traffic data for one or more traffic parameters, including information on the traffic intensity or the average vehicle speed, into in each case one of a plurality of state phases which comprise at least the state phases of free traffic and synchronized traffic. In the case of an edge at an effective bottleneck, between downstream free traffic and upstream synchronized traffic, the traffic state upstream thereof is classified as a pattern, representative of the respective bottleneck, of dense traffic which includes one or more different consecutive upstream, of different state phase composition; and an associated profile of the traffic parameters is taken into account for the state phase determination.
    • 在用于监视具有有效瓶颈的交通网络中的交通状况的方法中,考虑将包括关于交通强度或平均车速的信息的一个或多个交通参数的记录的测量交通数据分类为每个 至少包括自由话务和同步业务的状态阶段的多个状态阶​​段中的一种情况。 在有效瓶颈的边缘处于下游自由流量与上行同步流量之间的情况下,其上游的流量状态被分类为表示包括一个或多个不同连续上游的密集流量的相应瓶颈的模式 不同状态相组成; 并且在状态相位确定时考虑交通参数的相关轮廓。
    • 5. 发明授权
    • Method and system for mapping traffic congestion
    • 用于映射交通拥堵的方法和系统
    • US06542808B2
    • 2003-04-01
    • US09998061
    • 2001-11-30
    • Josef Mintz
    • Josef Mintz
    • G06G776
    • G08G1/0133G08G1/0112H04W4/04
    • System and method for mapping parameters of a queue of a road congestion. Length of the road congestion, motion rate and average arrival rate to the road congestion may be used to determine an expected delay in traveling as well as trends, using special radio systems and also existing radio networks such as Public Land Mobile Networks (PLMN) and Private/Public Data Networks (PDN). The mapping is performed relative to a front end of a queue of a road congestion. The mapping system may construct snapshots of mapping samples received from a small percentage of pre-designated probes. The mapping samples are received in response to predefined broadcast control messages. The determination of the length of a road congestion may be based on a direct approach, in dynamic conditions that include variations in the arrival rate of vehicles to the road congestion and the departure rate of vehicles from the congestion over time.
    • 用于映射道路拥塞队列参数的系统和方法。 道路拥堵的长度,运动速率和道路拥堵的平均到达率可以用于使用专用无线电系统以及诸如公共陆地移动网络(PLMN)和现有的无线电网络来确定旅行中的预期延迟以及趋势。 私有/公共数据网络(PDN)。 相对于道路拥塞的队列的前端进行映射。 映射系统可以构建从小部分预先指定的探测器接收到的样本的映射快照。 响应于预定义的广播控制消息接收映射样本。 确定道路拥堵的长度可以基于直接方法,其包括车辆对道路拥堵的到达速率的变化以及车辆随着时间的拥塞而离开的动态条件。
    • 7. 发明授权
    • Automatic freeway incident detection system and method using artificial neural network and genetic algorithms
    • 自动高速公路事件检测系统和使用人工神经网络和遗传算法的方法
    • US06470261B1
    • 2002-10-22
    • US09743992
    • 2001-01-16
    • Yew Liam NgKim Chwee Ng
    • Yew Liam NgKim Chwee Ng
    • G06G776
    • G06K9/00785G06N3/086
    • Design of a neural network for automatic detection of incidents on a freeway is described. A neural network is trained using a combination of both back-propagation and genetic algorithm-based methods for optimizing the design of the neural network. The back-propagation and genetic algorithm work together in a collaborative manner in the neural network design. The training starts with incremental learning based on the instantaneous error and the global total error is accumulated for batch updating at the end of the training data being presented to the neural network. The genetic algorithm directly evaluates the performance of multiple sets of neural networks in parallel and then use the analyzed results to breed new neural networks that tend to be better suited to the problems at hand.
    • 描述了用于自动检测高速公路事件的神经网络的设计。 使用反向传播和基于遗传算法的方法的组合来训练神经网络以优化神经网络的设计。 反向传播和遗传算法在神经网络设计中以协作的方式一起工作。 训练从基于瞬时误差的增量学习开始,并且在向神经网络呈现的训练数据结束时累积用于批量更新的全局总误差。 遗传算法直接评估多组神经网络的并行性能,然后使用分析结果来培育更适合手头问题的新型神经网络。