Abstract: A computer-implemented method is provided for image-based, self-guided object detection. The method includes receiving, by a processor device, a set of images. Each of the images has a respective grid thereon that is labeled regarding a respective object to be detected using grid level label data. The method further includes training, by the processor device, a grid-based object detector using the grid level label data. The method also includes determining, by the processor device, a respective bounding box for the respective object in each of the images, by applying local segmentation to each of the images. The method additionally includes training, by the processor device, a Region-based Convolutional Neural Network (RCNN) for joint object localization and object classification using the respective bounding box for the respective object in each of the images as an input to the RCNN.

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: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: obtaining movement path data that specifies a location of a mobile article over time within a geographical area having an infrastructure feature; determining by machine logic based on map data and based on the movement path data calibrated location data of the mobile article, wherein the determining based on map data and based on the movement path data calibrated location data of the mobile article includes using map data that specifies coordinate location data of the infrastructure feature; and providing one or more output based on the determining.

Abstract: A guide rail oiling tool includes: a sliding body, which is capped on a guide rail and slidable along the guide rail, and has an inner side surface facing a surface to be oiled of the guide rail, a shape of the inner side surface being matched with a shape of the surface to be oiled of the guide rail; an oil inlet disposed on the sliding body; and an oiling groove in communication with the oil inlet, disposed on the inner side surface of the sliding body and surrounding the surface to be oiled of the guide rail, so that the oiling groove applies oil to the surface to be oiled of the guide rail when the sliding body is sliding.

Abstract: A method for forming a semiconductor device includes providing a substrate, forming an oxide layer over the substrate, forming a plurality of first gate oxide layers by etching the oxide layer, forming a second gate oxide layer between adjacent first gate oxide layers, forming a silicon layer over the plurality of first gate oxide layers and the second gate oxide layer, and etching the plurality of first gate oxide layers, the silicon layer, and the second gate oxide layer to expose the substrate, thereby forming a plurality of gate structures. The first gate oxide layer of the plurality of first gate oxide layers has sloped sidewalls. A thickness of the second gate oxide layer is less than a thickness of the first gate oxide layer. Each gate structure includes an etched first oxide layer, a portion of the second gate oxide layer, and a portion of the silicon layer.

Abstract: A method for evaluating fraudulent data in a Usage Based Insurance (UBI) system, includes retrieving trip data for a driver from a database. A processor on a computer determines tough context incidents in the trip data. Driving behavior of the driver during said tough context incidents is compared with driving behavior of other drivers during similar tough context incidents. The trip data is identified as potentially fraudulent if the driver's driving behavior is better by a predetermined amount compared to the other drivers' driving behavior.

Abstract: A battery charger controller is configured to add a compensation current in the feedback control loop such that the output voltage varies with the output current to compensate charging cable voltage drop. In some embodiments, the output voltage is also proportional to a compensation resistor. Therefore, cable voltage drop compensation can be adjusted using a resistor that is external to the controller IC. The external resistor may be one of the feedback resistors connected at a voltage feedback pin. In another embodiment, the adjustable resistor is the resistor between the feedback resistors and the voltage feedback pin. In still another embodiment, the adjustable resistor is the resistor in parallel with a compensation capacitor. In embodiments of the invention, adjusting the resistance of the external compensation resistor can change the voltage drop compensation and allow the power supply to meet requirements of different charging cable applications.

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 computer-implemented method, computer program product, and computer processing system are provided for computing a trajectory-based Point of Interest recommendation. The method includes generating, by a processor device, a set of embeddings. Each of the embeddings in the set relates to a respective different trajectory contextual element of a user trajectory. The method further includes computing, by the processor device based on the set of embeddings, an activity representation that includes a set of POI candidate embeddings. The method also includes composing, by the processor device, a stop embedding based on the activity representation and the embeddings in the set and corresponding to a given stop in the user trajectory. The method additionally includes computing, by the processor device, the trajectory-based POI recommendation using an attention-based, user-specific, multi-stop trajectory, Recurrent Neural Network (RNN) model applied to the stop embedding.

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: A spectral computed tomography imaging system (102) includes a radiation source (112) configured to emit x-ray radiation and a detector array (114) configured to detect x-ray radiation and generate spectral data. The spectral imaging system further includes a memory (134) configured to store a virtual non-contrast image enhancing module (136) that includes computer executable instructions including a neural network trained to produce image quality enhanced virtual non-contrast images. The neural network is trained with training spectral data and training non-contrast-enhanced images generated from a non-contrast-enhanced scan. The spectral imaging system further includes a processor (132) configured to process the spectral data with the trained neural network to produce the image quality enhanced virtual non-contrast images.

Abstract: The present invention discloses a novel engine controlled by combustion reaction path, which cylinders comprise working cylinders and reforming cylinders. According to the operational condition of engine, the engine is used for compressing, heating and reforming the fuel injected from the reforming cylinder injector; by controlling the reaction boundary conditions between fuel and air, the reforming cylinder can exhaust partial intermediate products or oxidation products of the different oxidation stages; the products are then mixes with the inlet air in the pre-mixing chamber and then is introduced into the working cylinder.

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 method to train a machine learning model for in-vehicle air quality control in a knowledge-based system, executed by one or more computer processors, includes collecting data related to in-vehicle air quality from a plurality of probe cars where the data is collected by various on-board systems in each probe car. The method includes correlating the data related to in-vehicle air quality from each probe car with air quality measurements from each probe car, where the correlation is used to update the machine learning model. The method includes determining a situation when an in-vehicle air quality measurement of the air quality measurements is above a pre-determined in-vehicle air quality level and determining instructions for actions by one or more of the one or more on-board systems in each of the probe cars to maintain an in-vehicle air quality level at or below the pre-determined in-vehicle air quality level.

Abstract: Method for limiting growth of KDP-type crystals with a long seed where an upper and a lower ends of the long seed crystal are respectively limited by an upper baffle plate and a lower tray to restrain growth of a pyramidal surface and allow only four prismatic surfaces in [100] and [010] directions to grow. Finally grown crystal contains no pyramid-prism interface that severely restricts quality of optical element, and all cut optical elements have high optical quality. As four prismatic surfaces are subjected to highly similar growing environment and grow simultaneously, all optical elements cut therefrom have high optical uniformity. Due to uniqueness of a cutting angle of a KDP crystal frequency-tripled element, high cutting efficiency is achieved in the element, and an area of a maximum frequency-tripled element that may be cut is known in advance according to a horizontal size of the grown crystal.

Abstract: A conflict alerting method based on control voice comprises: collecting radio voice messages of a controller and a pilot and converting the radio voice messages into digital signals by an audio card of a control position; converting the digital signals into text messages by a voice recognition function and sending the text messages together to a system server; extracting, by the system server, control commands from the text messages; determining a moving track of an aircraft in a future period of time based on the control commands; identifying a possible dangerous conflict between aircrafts in combination with current location messages, motion parameter messages and future motion tracks of various aircrafts in an air traffic management system, and providing an alert prompt.

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: The present invention discloses a novel low-temperature fuel reforming unit based on combined external reformer of an engine, comprising an engine cylinder and an external low-temperature fuel reformer; the external low-temperature fuel reformer is winded with a heater strip and is provided with a first temperature controlled meter, the inlet of the external low-temperature fuel reformer is connected with a air inlet pipe and a fuel sample injection pipe, and a flow meter is arranged on the air inlet pipe; the fuel sample injection pipe is connected with a fuel injection pump and a fuel vaporization tank which is provided with a second temperature controlled meter; the outlet of the external low-temperature fuel reformer is connected with the engine inlet pipe via a reforming gas pipe; and the reformed low-temperature products enter into the engine inlet pipe via the reforming gas pipe for combining with the fresh air again to form a uniform hybrid gas, and the hybrid gas is introduced into the engine cylinde

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.