Abstract: A neural network database is disclosed. A learning task to teach a single model to answer any query is formulated. The example neural network database learns existing patterns between query input and output and by exploits the query and data distributions through a decision tree having multiple neural network leaf nodes representing partitions of the queries from the database. The neural network architecture is used to answer different query types efficiently. A generic neural network database framework can learn to answer different query types such as distance to nearest neighbor queries and range aggregate queries. The example neural database answers these two query types with orders of magnitude improvement in query time over the state-of-the-art competitions, and by constructing a model that takes only a fraction of data size.

Abstract: A method for traffic prediction of a road network includes receiving past traffic information corresponding to multiple locations on the road network. The method further includes determining, by a processor and based on the past traffic information, temporal characteristics of the past traffic information corresponding to changes of characteristics over time and spatial characteristics of the past traffic information corresponding to interactions between locations on the road network. The method further includes predicting predicted traffic information corresponding to a later time based on the determined temporal and spatial characteristics of the past traffic information. The method further includes receiving detected additional traffic information corresponding to the later time.

Abstract: Methods, systems, and apparatus for matching a driver associated with a driver timetable and a rider associated with a ride request including a detected rider location and a rider destination. The system includes a synchronizing server configured to transmit the ride request to a driver device. The driver device is configured to determine a driver value associated with incorporating the ride request into the driver timetable. The driver device is also configured to communicate, to the synchronizing server, the driver value. The synchronizing server is also configured to receive one or more other values from one or more other driver devices. The synchronizing server is also configured to determine a prime value from the one or more values, the prime value being the driver value. The synchronizing server is also configured to communicate, to the driver device, an indication to incorporate the ride request into the driver timetable.

Abstract: A method for traffic prediction of a road network includes receiving past traffic information corresponding to multiple locations on the road network. The method further includes determining, by a processor and based on the past traffic information, temporal characteristics of the past traffic information corresponding to changes of characteristics over time and spatial characteristics of in the past traffic information corresponding to interactions between locations on the road network. The method further includes predicting predicted traffic information corresponding to a later time based on the determined temporal and spatial characteristics of the past traffic information. The method further includes receiving detected additional traffic information corresponding to the later time.

Abstract: Systems and techniques for enhancing accuracy of traffic prediction include a system of one or more computers operable to receive a request relating to traffic prediction, compare a first prediction error for a first (moving average) traffic prediction model with a second prediction error for a second (historical average) traffic prediction model, calculated using a historical data set selected from previously recorded traffic data in accordance with a day and time associated with the request, select use of the first model or the second model based on the comparison of prediction errors, and provide an output for use in traffic prediction, wherein the output comes from applying the first traffic prediction model when the first prediction error is less than the second prediction error, and the output comes from applying the second traffic prediction model when the first prediction error is not less than the second prediction error.

Abstract: 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.

Abstract: 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%.

Abstract: 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%.

Abstract: 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.

Abstract: 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.

Abstract: A method for processing geospatial datasets corresponding to geospatial objects, the method having the steps of extracting geospatial attributes from the geospatial datasets, locating extracted geospatial attributes corresponding to a particular geospatial object at a particular point in time, and generating output indicative of the particular geospatial object at the particular point in time utilizing the located geospatial attributes.

Abstract: Spatial crowdsourcing systems and methods assign spatial tasks to be performed by human workers. The systems and methods can verify the validity of the results provided by workers. Every worker can have a reputation score stating the probability that the worker performs a task correctly. Every spatial task can have a confidence threshold determining the minimum quality of the accepted level of its result. To satisfy this threshold, a task may be assigned redundantly to multiple workers. A reputation score can be associated to every worker, which represents the probability that a worker performs a task correctly. A task may be assigned to a subset of workers whose aggregate reputation score satisfies the confidence of the task.

Abstract: 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%.

Abstract: Methods and systems for reconstructing data are disclosed. One method includes receiving a selection of one or more input data streams at a data processing framework, and receiving a definition of one or more analytics components at the data processing framework. The method further includes applying a dynamic principal component analysis to the one or more input data streams, and detecting a fault in the one or more input data streams based at least in part on a prediction error and a variation in principal component subspace generated based on the dynamic principal component analysis. The method also includes reconstructing data at the fault within the one or more input data streams based on data collected prior to occurrence of the fault.

Abstract: Methods for locating a feature on geospatial imagery and systems for performing those methods are disclosed. An accuracy level of each of a plurality of geospatial vector datasets available in a database can be determined. Each of the plurality of geospatial vector datasets corresponds to the same spatial region as the geospatial imagery. The geospatial vector dataset having the highest accuracy level may be selected. When the selected geospatial vector dataset and the geospatial imagery are misaligned, the selected geospatial vector dataset is aligned to the geospatial imagery. The location of the feature on the geospatial imagery is then determined based on the selected geospatial vector dataset and outputted via a display device.

Abstract: A method, computer program, and system for linking content to individual image features are provided. A section of an image is identified. A plurality of features associated with the section of the image is determined. Each of the plurality of features corresponds to at least one position within the section of the image. Content associated with the plurality of features is retrieved from a content repository. The content is linked to the plurality of features based on at least one rule. The content is then presented.

Abstract: 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.

Abstract: 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.

Abstract: Document relevance is determined with respect to a region of interest (ROI). A set of location references may be associated with a set of documents. The system selects location references associated with an ROI and then selects documents corresponding to the selected location references. The selected documents can be reported or processed further. A document-location reference index can be accessed when the present system is ‘online’ and processing a request for documents relevant to an ROI. The document-location reference index may be generated and updated while the present system is ‘offline’ and not processing a request for documents. The resulting relevant documents may be provided to a user in response to a document search associated with the ROI or along with an advertisement associated with the ROI.

Abstract: 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.