Abstract: Examples disclosed herein may involve a computing system configured to (i) after one or more sensor-equipped vehicles have traversed a real-world environment and captured sensor data that is representative of the real-world environment, perform an analysis of the sensor data; (ii) based on the analysis of the sensor data, derive a set of information about a traffic light within the real-world environment that includes one or more of (a) signal-face information that comprises an identification of each signal face of the traffic light or (b) traffic-rule information that comprises an indication of at least one traffic rule that is applicable to the traffic light; and (iii) encode the derived set of information about the traffic light into a map for the real-world environment.

Abstract: Examples disclosed herein may involve a computing system configured to (i) identify a stationary element in a real-world environment for which to infer information, (ii) detect a semantic relationship between the stationary element and one or more other stationary elements in the real-world environment, (iii) based on the detected semantic relationship, infer information about the stationary element, (iv) include the inferred information about the stationary element within a set of information that describes the stationary element.

Abstract: This disclosure describes a card-scan system that can update a card-scan machine learning model to improve card-character predictions for character-bearing cards by using an active-learning technique that learns from card-scan representations indicating corrections by users to predicted card characters. In particular, the disclosed systems can use a client device to capture and analyze a set of card images of a character-bearing card to predict card characters using a card-scan machine learning model. The disclosed systems can further receive card-scan gradients representing one or more corrections to incorrectly predicted card characters. Based on the card-scan gradients, the disclosed systems can generate active-learning metrics and retrain or update the card-scan machine learning model based on such active-learning metrics.

Abstract: This disclosure describes a card-scan system that can update a card-scan machine learning model to improve card-character predictions for payment cards, driver licenses, or other character-bearing cards by using an active-learning technique that learns from card-scan representations indicating corrections by users to predicted card characters. In particular, the disclosed systems can use a client device to capture and analyze a set of card images of a character-bearing card to predict card characters using a card-scan machine learning model. The disclosed systems can further receive card-scan gradients representing one or more corrections to incorrectly predicted card characters. Based on the card-scan gradients, the disclosed systems can generate active-learning metrics and retrain or update the card-scan machine learning model based on such active-learning metrics.

Abstract: Examples disclosed herein may involve a computing system configured to (i) identify a stationary element in a real-world environment for which to infer information, (ii) detect a semantic relationship between the stationary element and one or more other stationary elements in the real-world environment, (iii) based on the detected semantic relationship, infer information about the stationary element, (iv) include the inferred information about the stationary element within a set of information that describes the stationary element.

Abstract: Examples disclosed herein may involve a computing system that is operable to (i) identify a source map and a target map for transferring map data, where the source map and the target map have different respective coordinate frames and respective coverage areas that at least partially overlap, (ii) select a real-world element for which to transfer previously-created map data from the source map to the target map, (iii) select a source image associated with the source map in which the selected real-world element appears and has been labeled, (iv) select a target image associated with the target map in which the selected real-world element appears, (v) derive a geometric relationship between the source image and the target image, and (vi) use the derived geometric relationship between the source image and the target image to determine a position of the real-world element within the respective coordinate frame of the target map.

Abstract: An artificial intelligence (AI) prediction engine is used to correctly classify an entity based on a predetermined classification taxonomy, e.g., NAICS. The engine and process for using takes as inputs an entity's social presence (e.g., name, web address, etc.) and address. The AI prediction engine employs various machine learning models to make a classification prediction.

Abstract: This disclosure describes a card-scan system that can update a card-scan machine learning model to improve card-character predictions for payment cards, driver licenses, or other character-bearing cards by using an active-learning technique that learns from card-scan representations indicating corrections by users to predicted card characters. In particular, the disclosed systems can use a client device to capture and analyze a set of card images of a character-bearing card to predict card characters using a card-scan machine learning model. The disclosed systems can further receive card-scan gradients representing one or more corrections to incorrectly predicted card characters. Based on the card-scan gradients, the disclosed systems can generate active-learning metrics and retrain or update the card-scan machine learning model based on such active-learning metrics.

Abstract: Examples disclosed herein may involve a computing system that is operable to (i) identify a source map and a target map for transferring map data, where the source map and the target map have different respective coordinate frames and respective coverage areas that at least partially overlap, (ii) select a real-world element for which to transfer previously-created map data from the source map to the target map, (iii) select a source image associated with the source map in which the selected real-world element appears and has been labeled, (iv) select a target image associated with the target map in which the selected real-world element appears, (v) derive a geometric relationship between the source image and the target image, and (vi) use the derived geometric relationship between the source image and the target image to determine a position of the real-world element within the respective coordinate frame of the target map.

Abstract: Examples disclosed herein may involve a computing system configured to (i) identify a stationary element in a real-world environment for which to infer information, (ii) detect a semantic relationship between the stationary element and one or more other stationary elements in the real-world environment, (iii) based on the detected semantic relationship, infer information about the stationary element, (iv) include the inferred information about the stationary element within a set of information that describes the stationary element.

Abstract: A method of employing an encoding scheme for media independent handover, comprising: having at least some data type carry only required information to determine the end of data without a length value.

Abstract: A self-organizing IP multimedia subsystem exhibiting node splitting and node merging functions wherein any node within the self organizing IP multimedia subsystem may assume any role thereby providing node balancing and fault tolerance to an overall network.

Abstract: A mechanism by which handoff delay can be minimized while not compromising the IMS/MMD security and also protecting the media if required by certain applications is presented. Methods for mitigating delay during SA re-association and mitigating the IPSec tunnel overhead for signaling and media at the Mobile Node are given. In one embodiment, SA keys can be transferred from the old P-CSCF to new P-CSCF, enabling the establishment of SAs before Mobile Node physically moves to the new subnet in a network. Proactive handover is used. In another embodiment, SA keys are transferred from S-CSCF to new P-CSCF. In this case, the SA keys are transferred to the new P-CSCF by S-CSCF through a context transfer mechanism well in advance so that SAs may be established before Mobile Node physically moves to new subnet. In another embodiment, methods for mitigating IPSec tunnel overhead are presented.

Abstract: A mobile device includes: multiple interfaces that are configured to support a various access technology such as 3G or Wi-Fi etc. A public land mobile network (PLMN) selector that generates a list for each of the PLMN networks that provide coverage to the mobile device. A PLMN selection policy parameter that is set to True or False to allow or prohibit the selection of PLMN networks by the mobile device based on the generated list where the generated list includes information as to different access technologies and selection priorities supported on the PLMN access networks providing coverage to the mobile device. In particular, when the PLMN selection policy parameter is set to True, multiple PLMN registrations are allowed; and when the A PLMN selection policy parameter is set to False, multiple PLMN registrations are prohibited.

Abstract: A mechanism by which handoff delay can be minimized while not compromising the IMS/MMD security and also protecting the media if required by certain applications is presented. One proactive method includes proactive authentication. Another proactive method includes proactive security association, such as transferring SA keys from old proxy to new proxy, or transferring keys through serving signal entities. Reactive methods include transferring SA keys from old proxy to new proxy, using either push or pull technology. Other reactive methods include transferring keys through serving signal entities using either push or pull technology.

Abstract: In some of the preferred embodiments, a method for network discovery of a mobile device to use at least one of a plurality of access networks within an IP network includes: obtaining specified network information in the vicinity of a given location based on a set of criteria when a mobile is connected to the IP network from any location.

Abstract: According to some embodiments, a key management apparatus for deploying in a smart grid system adapted to receive metering data from smart meters connected to at least one relay via a network, includes: a key control mechanism that derives a key array of individual purpose specific keys from one master key such that the purpose specific key in the key array are each independent cryptographic keys for each specific usage in an application or for each application if there is only one specific usage in an application.

Abstract: A solution framework is employed that includes defining of a mechanism to run multiple queries in a single message exchange, along with a priority on a per-query basis. In some embodiments, a system for facilitating handover of a mobile device across heterogeneous access networks by ensuring response to queries transmitted by the mobile device includes: a) a mobile device having a plurality of wireless network interfaces for communicating over a plurality of heterogeneous access networks, having a media independent handover (MIH) entity to facilitate handovers between the heterogeneous networks, and configured to transmit queries related to handover operation between the heterogeneous access networks to MIH entities within said heterogeneous access networks; and b) said media independent handover entity of said mobile device being configured to transmit multiple queries in a single message exchange to an MIH entity in an access network with prioritization among said multiple queries.

Abstract: In some of the preferred embodiments, a method for network discovery of a mobile device to use at least one of a plurality of access networks within an IP network includes: obtaining specified network information in the vicinity of a given location based on a set of criteria when a mobile is connected to the IP network from any location.

Abstract: The preferred embodiments involve a mechanism to bootstrap Kerberos from EAP in which EAP is used for initial network access authentication and Kerberos is used for provisioning session keys to multiple different protocols. The preferred embodiments make use of an EAP extension method (EAP-EXT) to realize the mechanism.