Abstract: Methods and systems for reinforcement learning with dynamic agent grouping include gathering information at a first agent using one or more sensors. Shared information is received at the first agent from a second agent. An agent model is trained at the first agent using the gathered information and the shared information. A contribution of the shared information is weighted according to a degree of similarity between the first agent and the second agent. An action is generated using the trained agent model responsive to the gathered information.

Abstract: A method and system obtaining positioning data from an object traveling on a plurality of routes; mapping the data into a plurality of points on a digital map; identifying points that are unmatched to the stored route trajectory; obtaining candidate transition points from the unmatched points; aggregating the candidate transition points by applying a clustering algorithm; selecting a first cluster of points and a plurality of second clusters of points, determining a confidence level that the first cluster of points are transition points indicating a transition between the routes, classifying the first cluster of points as a first plurality of traveling points having a first direction in response to the confidence being below a threshold confidence and automatically adjusting the stored route trajectory to indicate that the first cluster of points are on the route trajectory.

Abstract: This disclosure provides embodiments for context based vehicular traffic prediction. A trained neural network modeling a relationship between historical traffic data and associated historical contextual data for a roadway link is obtained. Expected contextual data for a future time period for the roadway link is acquired. Predicted traffic data for the future time period for the roadway link is generated with the trained neural network based on the expected contextual data.

Abstract: Techniques facilitating resolution-based spatial computing are provided. In one example, a computer-implemented method comprises traversing, by a device operatively coupled to a processor, a data structure corresponding to a land area for a location having an index; and determining, by the device, whether the location is at least partially within the land area based on a result of the traversing. In some embodiments, the traversing comprises: obtaining a threshold number of levels based at least in part on a resolution parameter; scanning a first level of the data structure for a node having an index corresponding to the index of the location; and iterating the scanning for respective subsequent levels of the data structure based on the scanning returning a node having subordinate nodes and a number of levels for which the scanning and iterating have been performed being less than the threshold number of levels.

Abstract: A mechanism is provided for controlling the internal air-quality of a vehicle, including configuring a control policy that controls an internal air-quality of a vehicle and performing an action dictated by the control policy according to a window status of the vehicle.

Abstract: A method and/or system for managing a database that stores space-time context objects is provided. The system receives a query range in a multi-dimensional space. The system maps the query range into a set of fragments of a space-filling curve that fills the multi-dimensional space in all dimensions of the multi-dimensional space. The system uses each mapped fragment in the set of mapped fragments as a key to query the database for space-time context objects that are mapped to the space-filling curve. The system queries the database by identifying one or more context objects that intersect the mapped fragment at the space-filling curve.

Abstract: Blockchain based IoT data management can include receiving IoT data are with one or more processing units. At least one aggregation pattern of the IoT data can be determined by one or more processing units. The IoT data can be hashed, based upon the at least one aggregation pattern to obtain hash values of the IoT data by one or more processing units. The hash values can be sent to a blockchain system for storing by one or more processing units.

Abstract: Multi-level objectives improve efficiency of multi-objective automated machine learning. A hyperband framework is established with a kernel density estimator to shrink the search space based on evaluation of lower-level objectives. A Gaussian prior assumption directly shrinks the search space to find a main objective.

Abstract: A method for optimizing a neural network architecture by estimating an inference time for each operator in the neural network architecture is provided. The method may include determining a benchmark time for at least one single-path architecture out of a plurality of single-path architectures associated with the neural network by sampling the at least one single-path architecture from the neural network, wherein the at least one single-path architecture comprises one or more operators. The method may further include, based on the benchmark time for the at least one single-path architecture, determining an estimated inference time for an operator, wherein determining the estimated inference time for the operator comprises, applying an operator function, wherein the operator function comprises a function based on a difference between the benchmark time associated with the at least one single-path architecture and the estimated latency of the neural network.

Abstract: A method, system, and computer program product for obtaining a first route traversed by a target object, performing at least one prediction for a second route to be traversed by the target object based on the first route, the at least one prediction being performed with at least one of an object-specific prediction model, an object group-specific prediction model, and an object-independent prediction model, and determining, according to a decision rule, a prediction result of the second route based on the at least one prediction.

Abstract: A computer-implemented method is presented for inferring passenger routes in a subway system. The method includes identifying, via an imaging device, a target passenger within the subway system, employing an exiting flow extractor to determine passenger exiting waves, employing an exiting wave identifier to mark an exiting wave of the passenger exiting waves including the target passenger, employing a supporting evidence backtracer to determine an entrance gate for each of the passengers in the marked exiting wave including the target passenger, determining a route probability for each of the passengers in the marked exiting wave including the target passenger via voting or distribution estimation processing, and employing a most probable route inferer to infer a route of the target passenger based on an aggregate route probability for all the passengers in the marked exiting wave.

Abstract: Techniques are provided for blockchain based a data transformation. According to one aspect, a series of Internet of Things (IoT) data is received by one or more processing units. And at least one reference data set to the received series of IoT data are attached by one or more processing units. The received series of IoT data attached are processed, by one or more processing units, with at least one transformation module to obtain a processing result of the at least one reference data set. A hash value of the processing result is calculated by one or more processing units. The hash value of the processing result and a hash value of an expected result stored in a blockchain system are compared. In respond to the hash value of the processing result being not matched with the hash value of the expected result, the decision of the at least one transformation module having been tampered with is determined by one or more processing units.

Abstract: Embodiments of the present invention may be directed toward a method, a system, and a computer program product of adaptive calibration of sensors through cognitive learning. In an exemplary embodiment, the method, the system, and the computer program product include (1) in response to receiving a data from at least one calibration sensor and data from an itinerant sensor, comparing the data from the at least one calibration sensor and the data from the itinerant sensor, (2) in response to the comparing, determining, by one or more processors, the accuracy of the itinerant sensor, (3) generating, by the one or more processors, one or more calibration parameters based on the determining and based on a machine learning associated with preexisting sensor information, and (4) executing, by the one or more processors, the one or more calibration parameters.

Abstract: A system, method and computer program product for retrieving trajectory data from huge datasets. In the method, there is received, at a processor device, a user query including a request for displaying trajectory data at a user device. From the user query, a query type and a current map visualization scale setting (mapscale) for visualizing the trajectory data on the user device display is determined. Then, responsive to a user query type and the determined mapscale setting, a corresponding reference level is selected. Based on the selected reference level, there is accessed from a memory storage device a data set of compressed trajectory data. This compressed trajectory data set is communicated to the user device, for presentation on the user device display. In one aspect, the system and method is adaptive, enabling storage and retrieval of trajectory data according to various degrees of visualization or granularity.

Abstract: Embodiments of the present disclosure relate to attention-based neural language processing. In an embodiment, a method is disclosed. According to the method, a sentence graph is generated from a sentence containing words. The sentence graph comprises nodes representing words and edges connecting the nodes, at least one of the edges being constructed to indicate a syntactic relationship between words represented by nodes connected therebetween. Word representations for the words are determined based on the sentence graph by applying an attention mechanism on respective ones of the nodes and respective sets of neighbor nodes for the nodes. A set of neighbor nodes for a node has edges connected to the node. A sentence representation for the sentence is determined based on the word representations for use in a natural language processing task related to the sentence. In other embodiments, a system and a computer program product are disclosed.

Abstract: A computer-implemented method for implementing separated attention on like and dislike items for personalized ranking includes performing an element-wise product on a user embedding and a final like item embedding to generate a first vector. The method further includes performing an element-wise product on the user embedding and a final dislike item embedding to generate a second vector. The method further includes computing a probability that the user prefers the like item to the dislike item based on the first and second vectors, and generating one or more item recommendations including one or more electronic images for the user using the probability.

Abstract: Systems and methods for estimating battery-powered driving distance for a vehicle, including training a relative model for a battery using input historical battery temperature data and historical battery-external factors, and predicting a future battery temperature based on the relative model and one or more of current or future battery-external factors. A battery power capacity is determined using the predicted future battery temperature and input manufacturer specifications for the battery, and a remaining battery powered driving distance is calculated based on input vehicle power consumption data and the determined battery power capacity.

Abstract: A mechanism is provided for controlling the internal air-quality of a vehicle, including configuring a control policy that controls an internal air-quality of a vehicle and performing an action dictated by the control policy according to a window status of the vehicle.

Abstract: A computer-implemented method is presented for implementing multi-aspect sentiment analysis by collaborative attention allocation. The method includes extracting a sequence of word vectors from a sentence received from a data stream, feeding the sequence of word vectors to long short-term memory (LSTM) neural networks to generate a sequence of hidden states corresponding to the sequence of word vectors, generating a plurality of aspect embedding vectors for each aspect, employing an attention mechanism to determine attention weight vectors concurrently for all aspects, and outputting predicted sentiments for each aspect of the sentence to a user interface of a computing device.

Abstract: Techniques facilitating resolution-based spatial computing are provided. In one example, a computer-implemented method comprises traversing, by a device operatively coupled to a processor, a data structure corresponding to a land area for a location having an index; and determining, by the device, whether the location is at least partially within the land area based on a result of the traversing. In some embodiments, the traversing comprises: obtaining a threshold number of levels based at least in part on a resolution parameter; scanning a first level of the data structure for a node having an index corresponding to the index of the location; and iterating the scanning for respective subsequent levels of the data structure based on the scanning returning a node having subordinate nodes and a number of levels for which the scanning and iterating have been performed being less than the threshold number of levels.