专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20140114556A1 TRAFFIC PREDICTION USING REAL-WORLD TRANSPORTATION DATA 有权
标题翻译：使用实际运输数据的交通预测
公开(公告)号：US20140114556A1
公开(公告)日：2014-04-24
申请号：US14060360
申请日：2013-10-22
申请人： Bei Pan , Ugur Demiryurek , Cyrus Shahabi
发明人： Bei Pan , Ugur Demiryurek , Cyrus Shahabi
IPC分类号： G08G1/00
CPC分类号： G06N5/04 , G08G1/00 , G08G1/0112 , G08G1/0129 , G08G1/0141
摘要： Real-time high-fidelity spatiotemporal data on transportation networks can be used to learn about traffic behavior at different times and locations, potentially resulting in major savings in time and fuel. Real-world data collected from transportation networks can be used to incorporate the data's intrinsic behavior into a time-series mining technique to enhance its accuracy for traffic prediction. For example, the spatiotemporal behaviors of rush hours and events can be used to perform a more accurate prediction of both short-term and long-term average speed on road-segments, even in the presence of infrequent events (e.g., accidents). Taking historical rush-hour behavior into account can improve the accuracy of traditional predictors by up to 67% and 78% in short-term and long-term predictions, respectively. Moreover, the impact of an accident can be incorporated to improve the prediction accuracy by up to 91%.
摘要翻译：运输网络上的实时高保真时空数据可用于了解不同时间和地点的交通行为，有可能大大节省时间和燃料。从运输网络收集的现实数据可用于将数据的内在行为纳入时间序列挖掘技术，以提高其对流量预测的准确性。例如，高峰时段和事件的时空行为可以用于对路段上的短期和长期平均速度进行更准确的预测，即使在出现偶然事件（例如事故）的情况下也是如此。考虑到历史高峰时期的行为，可以将传统预测指标的准确度分别提高67％和78％，在短期和长期预测中。此外，可以引入事故的影响，将预测精度提高高达91％。

2. 发明授权

US09286793B2 Traffic prediction using real-world transportation data 有权
标题翻译：使用现实世界交通数据的交通预测
公开(公告)号：US09286793B2
公开(公告)日：2016-03-15
申请号：US14060360
申请日：2013-10-22
申请人： Bei Pan , Ugur Demiryurek , Cyrus Shahabi
发明人： Bei Pan , Ugur Demiryurek , Cyrus Shahabi
IPC分类号： G08G1/00 , G08G1/01
CPC分类号： G06N5/04 , G08G1/00 , G08G1/0112 , G08G1/0129 , G08G1/0141
摘要： Real-time high-fidelity spatiotemporal data on transportation networks can be used to learn about traffic behavior at different times and locations, potentially resulting in major savings in time and fuel. Real-world data collected from transportation networks can be used to incorporate the data's intrinsic behavior into a time-series mining technique to enhance its accuracy for traffic prediction. For example, the spatiotemporal behaviors of rush hours and events can be used to perform a more accurate prediction of both short-term and long-term average speed on road-segments, even in the presence of infrequent events (e.g., accidents). Taking historical rush-hour behavior into account can improve the accuracy of traditional predictors by up to 67% and 78% in short-term and long-term predictions, respectively. Moreover, the impact of an accident can be incorporated to improve the prediction accuracy by up to 91%.
摘要翻译：运输网络上的实时高保真时空数据可用于了解不同时间和地点的交通行为，有可能大大节省时间和燃料。从运输网络收集的现实数据可用于将数据的内在行为纳入时间序列挖掘技术，以提高其对流量预测的准确性。例如，高峰时段和事件的时空行为可以用于对路段上的短期和长期平均速度进行更准确的预测，即使在出现偶然事件（例如事故）的情况下也是如此。考虑到历史高峰时期的行为，可以将传统预测指标的准确度分别提高67％和78％，在短期和长期预测中。此外，可以引入事故的影响，将预测精度提高高达91％。

3. 发明申请

US20120283948A1 Hierarchical and Exact Fastest Path Computation in Time-dependent Spatial Networks 有权
标题翻译：时间依赖空间网络中的分层和精确最快路径计算
公开(公告)号：US20120283948A1
公开(公告)日：2012-11-08
申请号：US13455035
申请日：2012-04-24
申请人： Ugur Demiryurek , Cyrus Shahabi
发明人： Ugur Demiryurek , Cyrus Shahabi
IPC分类号： G01C21/34
CPC分类号： G01C21/3446 , G01C21/3492
摘要： With real-world spatial networks the edge travel-times are time-dependent, where the arrival-time to an edge determines the actual travel-time on the edge. To speed up the path computation, exact and approximate techniques for computation of the fastest path in time-dependent spatial networks are presented. An exact fastest path computation technique based on a time-dependent A* search can significantly improve the computation time and storage complexity of existing approaches. Moreover, for applications with which approximate fastest path is acceptable, the approximate fastest path computation technique can improve the computation time by an order of magnitude while maintaining high accuracy (e.g., with only 7% increase in travel-time of the computed path on average). With experiments using real data-sets (including a variety of large spatial networks with real traffic data) the efficacy of the disclosed techniques for online fastest path computation is demonstrated.
摘要翻译：利用现实世界的空间网络，边缘旅行时间是时间依赖的，其中到达边缘的到达时间确定边缘上的实际旅行时间。为了加快路径计算，提出了用于计算时间依赖空间网络中最快路径的精确和近似技术。基于时间依赖的A *搜索的确切最快的路径计算技术可以显着提高现有方法的计算时间和存储复杂性。此外，对于近似最快路径可接受的应用，近似最快路径计算技术可以将计算时间提高一个数量级，同时保持高精度（例如，平均计算路径的行进时间仅增加7％）。通过使用实际数据集（包括具有实际流量数据的各种大型空间网络）的实验，证明了所公开的在线最快路径计算技术的功效。

4. 发明申请

US20150248450A1 THROWAWAY SPATIAL INDEX STRUCTURE FOR DYNAMIC POINT DATA 有权
标题翻译：用于动态点数据的THROWAWAY空间索引结构
公开(公告)号：US20150248450A1
公开(公告)日：2015-09-03
申请号：US14482805
申请日：2014-09-10
申请人： Afsin Akdogan , Cyrus Shahabi , Ugur Demiryurek
发明人： Afsin Akdogan , Cyrus Shahabi , Ugur Demiryurek
IPC分类号： G06F17/30
CPC分类号： G06F17/30327 , G06F17/30241
摘要： The present disclosure relates to a short-lived throwaway index structure for generating an index from scratch in a short period of time rather than updating an index with every location change of moving objects. Rapid index construction results from the generation of Voronoi diagrams in parallel using multiple cloud servers simultaneously.
摘要翻译：本公开涉及一种用于在短时间内从头开始生成索引而不是按照移动对象的每个位置改变更新索引的短命丢弃索引结构。同时使用多个云服务器并行生成Voronoi图的快速索引构建。

5. 发明授权

US08660789B2 Hierarchical and exact fastest path computation in time-dependent spatial networks 有权
标题翻译：时间依赖空间网络中的分层和精确最快的路径计算
公开(公告)号：US08660789B2
公开(公告)日：2014-02-25
申请号：US13455035
申请日：2012-04-24
申请人： Ugur Demiryurek , Cyrus Shahabi
发明人： Ugur Demiryurek , Cyrus Shahabi
IPC分类号： G01C21/34
CPC分类号： G01C21/3446 , G01C21/3492
摘要： With real-world spatial networks the edge travel-times are time-dependent, where the arrival-time to an edge determines the actual travel-time on the edge. To speed up the path computation, exact and approximate techniques for computation of the fastest path in time-dependent spatial networks are presented. An exact fastest path computation technique based on a time-dependent A* search can significantly improve the computation time and storage complexity of existing approaches. Moreover, for applications with which approximate fastest path is acceptable, the approximate fastest path computation technique can improve the computation time by an order of magnitude while maintaining high accuracy (e.g., with only 7% increase in travel-time of the computed path on average). With experiments using real data-sets (including a variety of large spatial networks with real traffic data) the efficacy of the disclosed techniques for online fastest path computation is demonstrated.
摘要翻译：利用现实世界的空间网络，边缘旅行时间是时间依赖的，其中到达边缘的到达时间确定边缘上的实际旅行时间。为了加快路径计算，提出了用于计算时间依赖空间网络中最快路径的精确和近似技术。基于时间依赖的A *搜索的确切最快的路径计算技术可以显着提高现有方法的计算时间和存储复杂性。此外，对于近似最快路径可接受的应用，近似最快路径计算技术可以将计算时间提高一个数量级，同时保持高精度（例如，平均计算路径的行进时间仅增加7％）。通过使用实际数据集（包括具有实际流量数据的各种大型空间网络）的实验，证明了所公开的在线最快路径计算技术的功效。

6. 发明授权

US08566030B1 Efficient K-nearest neighbor search in time-dependent spatial networks 有权
公开(公告)号：US08566030B1
公开(公告)日：2013-10-22
申请号：US13278060
申请日：2011-10-20
申请人： Ugur Demiryurek , Cyrus Shahabi , Farnoush Banaei-Kashani
发明人： Ugur Demiryurek , Cyrus Shahabi , Farnoush Banaei-Kashani
IPC分类号： G08G1/00
CPC分类号： G01C21/3476 , G01C21/3446 , G01C21/3492 , G08G1/0116 , G08G1/0129 , G08G1/096816
摘要： The class of k Nearest Neighbor (k NN) queries in spatial networks has been studied in the literature. Existing approaches for k NN search in spatial networks assume that the weight of each edge in the spatial network is constant. However, real-world edge-weights are time-dependent and vary significantly in short durations, hence invalidating the existing solutions. The problem of k NN search in time-dependent spatial networks, where the weight of each edge is a function of time, is addressed herein. Two indexing schemes (Tight Network Index and Loose Network Index) are proposed to minimize the number of candidate nearest neighbor objects and reduce the invocation of the expensive fastest-path computation in time-dependent spatial networks. We demonstrate the efficiency of our proposed solution via experimental evaluations with real-world data-sets, including a variety of large spatial networks with real traffic-data.

7. 发明授权

US09501509B2 Throwaway spatial index structure for dynamic point data 有权
标题翻译：动态点数据的空间索引结构
公开(公告)号：US09501509B2
公开(公告)日：2016-11-22
申请号：US14482805
申请日：2014-09-10
申请人： Afsin Akdogan , Cyrus Shahabi , Ugur Demiryurek
发明人： Afsin Akdogan , Cyrus Shahabi , Ugur Demiryurek
IPC分类号： G06F17/30 , G06F7/00
CPC分类号： G06F17/30327 , G06F17/30241
摘要： The present disclosure relates to a short-lived throwaway index structure for generating an index from scratch in a short period of time rather than updating an index with every location change of moving objects. Rapid index construction results from the generation of Voronoi diagrams in parallel using multiple cloud servers simultaneously.
摘要翻译：本公开涉及一种用于在短时间内从头开始生成索引而不是按照移动对象的每个位置改变更新索引的短命丢弃索引结构。同时使用多个云服务器并行生成Voronoi图的快速索引构建。

8. 发明授权

US09062985B2 Efficient K-nearest neighbor search in time-dependent spatial networks 有权
标题翻译：在时间依赖空间网络中有效的K-最近邻搜索
公开(公告)号：US09062985B2
公开(公告)日：2015-06-23
申请号：US14059212
申请日：2013-10-21
申请人： Ugur Demiryurek , Cyrus Shahabi , Farnoush Banaei-Kashani
发明人： Ugur Demiryurek , Cyrus Shahabi , Farnoush Banaei-Kashani
IPC分类号： G01C21/34 , G08G1/01 , G08G1/0968
CPC分类号： G01C21/3476 , G01C21/3446 , G01C21/3492 , G08G1/0116 , G08G1/0129 , G08G1/096816
摘要： The class of k Nearest Neighbor (k NN) queries in spatial networks has been studied in the literature. Existing approaches for k NN search in spatial networks assume that the weight of each edge in the spatial network is constant. However, real-world edge-weights are time-dependent and vary significantly in short durations, hence invalidating the existing solutions. The problem of k NN search in time-dependent spatial networks, where the weight of each edge is a function of time, is addressed herein. Two indexing schemes (Tight Network Index and Loose Network Index) are proposed to minimize the number of candidate nearest neighbor objects and reduce the invocation of the expensive fastest-path computation in time-dependent spatial networks. We demonstrate the efficiency of our proposed solution via experimental evaluations with real-world data-sets, including a variety of large spatial networks with real traffic-data.
摘要翻译：文献中已经研究了空间网络中k个最近邻（k NN）查询的类。空间网络中k NN搜索的现有方法假设空间网络中每个边缘的权重是恒定的。然而，现实世界边际权重是时间依赖性的，并且在短时间内显着变化，因此使现有解决方案无效。这里解决了时间依赖空间网络中k NN搜索的问题，其中每个边缘的权重是时间的函数。提出了两个索引方案（紧密网络索引和松散网络索引），以最小化候选最近邻居对象的数量，并减少时间依赖空间网络中昂贵的最快路径计算的调用。我们通过实际数据集的实验评估来展示我们提出的解决方案的效率，包括具有实际流量数据的各种大型空间网络。

9. 发明申请

US20140046593A1 Efficient K-Nearest Neighbor Search in Time-Dependent Spatial Networks 有权
标题翻译：在时间依赖空间网络中有效的K最近邻搜索
公开(公告)号：US20140046593A1
公开(公告)日：2014-02-13
申请号：US14059212
申请日：2013-10-21
申请人： Ugur Demiryurek , Cyrus Shahabi , Farnoush Banaei-Kashani
发明人： Ugur Demiryurek , Cyrus Shahabi , Farnoush Banaei-Kashani
IPC分类号： G01C21/34
CPC分类号： G01C21/3476 , G01C21/3446 , G01C21/3492 , G08G1/0116 , G08G1/0129 , G08G1/096816
摘要： The class of k Nearest Neighbor (k NN) queries in spatial networks has been studied in the literature. Existing approaches for k NN search in spatial networks assume that the weight of each edge in the spatial network is constant. However, real-world edge-weights are time-dependent and vary significantly in short durations, hence invalidating the existing solutions. The problem of k NN search in time-dependent spatial networks, where the weight of each edge is a function of time, is addressed herein. Two indexing schemes (Tight Network Index and Loose Network Index) are proposed to minimize the number of candidate nearest neighbor objects and reduce the invocation of the expensive fastest-path computation in time-dependent spatial networks. We demonstrate the efficiency of our proposed solution via experimental evaluations with real-world data-sets, including a variety of large spatial networks with real traffic-data.
摘要翻译：文献中已经研究了空间网络中k个最近邻（k NN）查询的类。空间网络中k NN搜索的现有方法假设空间网络中每个边缘的权重是恒定的。然而，现实世界边际权重是时间依赖性的，并且在短时间内显着变化，因此使现有解决方案无效。这里解决了时间依赖空间网络中k NN搜索的问题，其中每个边缘的权重是时间的函数。提出了两个索引方案（紧密网络索引和松散网络索引），以最小化候选最近邻居对象的数量，并减少时间依赖空间网络中昂贵的最快路径计算的调用。我们通过实际数据集的实验评估来展示我们提出的解决方案的效率，包括具有实际流量数据的各种大型空间网络。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式