Abstract: Personalization with on-device privacy preservation is provided by receiving, at a user device, a generalized recommendation from a remote provider backend, which include a plurality of candidate items responsive to a request from an application running on the user device; generating a plurality of candidate vectors corresponding to the plurality of candidate items representing a corresponding candidate item in a binary format across a plurality of metrics associated with the plurality of candidate items; generating a user vector based on personal data stored on the user device, the user vector representing a user in a binary format across one or more metrics associated with the personal data; determining interaction propensities based on the user vector and the plurality of candidate vectors according to a global model run on the user device; and displaying, on the user device, the plurality of candidate items according to the interaction propensities.

Abstract: Embodiments are disclosed for a method for a wearable secure data device. The method includes setting an operational mode for the wearable secure data device that stores a plurality of secure data items. The method also includes receiving a request for at least one of the secure data items from a client device that is communicating with a third-party device. Additionally, the method includes determining if the operational mode is associated with allowing access to the secure data items. Further, the method includes providing a response based on the determination.

Abstract: A set of network traffic among a plurality of legacy applications is monitored. From the set of network traffic, a communication graph is generated for the plurality. From the communication graph, a set of migratable applications within the plurality is identified. The set of migratable applications is migrated to a cloud edge layer, and a user is notified of the migration.

Abstract: A set of network traffic among a plurality of legacy applications is monitored. From the set of network traffic, a communication graph is generated for the plurality. From the communication graph, a set of migratable applications within the plurality is identified. The set of migratable applications is migrated to a cloud edge layer, and a user is notified of the migration.

Abstract: A notification message is received by a communication device The notification message includes a message identifier and a digital signature generated by an original sender of the notification message. That an integrity of message content in the notification message and an original sender of the notification message is verified is determined using the digital signature. Responsive to determining that the notification message is verified, the notification message is forwarded by the communication device using a peer-to-peer communication channel over a mesh network.

Abstract: A trained base model is distributed to a set of nodes. From a first node in the set of nodes, a first set of meta-metrics resulting from a transfer learning operation on the trained base model at the first node is collected. The transfer learning at the first node uses first local data available at the first node. The first node is clustered in a cluster with a second node from the set of nodes, in response to a meta-metric in the first set of meta-metrics being within a tolerance value of a corresponding meta-metric in a second set of meta-metrics collected from the second node. A normalized set of model parameters is constructed after an iteration of transfer learning or local learning at the first and second nodes. The normalized set of model parameters is distributed to the first node and the second node in the cluster.

Abstract: According to an embodiment, a method for registering a component is provided. The method includes receiving a request for registration of the component. The method also includes acquiring registration information of the component in response to the request by communicating directly with the component and exacting the registration information and modifying a registration entry associated with the component in a registration database according to the registration information.

Abstract: Embodiments are disclosed for a method for a wearable secure data device. The method includes setting an operational mode for the wearable secure data device that stores a plurality of secure data items. The method also includes receiving a request for at least one of the secure data items from a client device that is communicating with a third-party device. Additionally, the method includes determining if the operational mode is associated with allowing access to the secure data items. Further, the method includes providing a response based on the determination.

Abstract: Personalization with on-device privacy preservation is provided by receiving, at a user device, a generalized recommendation from a remote provider backend, which include a plurality of candidate items responsive to a request from an application running on the user device; generating a plurality of candidate vectors corresponding to the plurality of candidate items representing a corresponding candidate item in a binary format across a plurality of metrics associated with the plurality of candidate items; generating a user vector based on personal data stored on the user device, the user vector representing a user in a binary format across one or more metrics associated with the personal data; determining interaction propensities based on the user vector and the plurality of candidate vectors according to a global model run on the user device; and displaying, on the user device, the plurality of candidate items according to the interaction propensities.

Abstract: A portable computing system includes a portable computing device consisting essentially of a logical processor, a memory in communication with the logical processor with operating system software, a high speed, secure wireless communication module in communication with the logical processor, an integrated power source suitable to provide all power needs of the portable computing device and an integrated electric power generation mechanism in communication with the integrated power source to recharge the integrated power source. In addition a visual display is provided that has a power supply separate from the integrated power source of the portable computing device and a complementary wireless communication module, the portable visual display in communication with the high speed, secure wireless communication module through the complementary wireless communication module. The portable computing device and the visual display do not share a physical connection.

Abstract: A trained base model is distributed to a set of nodes. From a first node in the set of nodes, a first set of meta-metrics resulting from a transfer learning operation on the trained base model at the first node is collected. The transfer learning at the first node uses first local data available at the first node. The first node is clustered in a cluster with a second node from the set of nodes, in response to a meta-metric in the first set of meta-metrics being within a tolerance value of a corresponding meta-metric in a second set of meta-metrics collected from the second node. A normalized set of model parameters is constructed after an iteration of transfer learning or local learning at the first and second nodes. The normalized set of model parameters is distributed to the first node and the second node in the cluster.

Abstract: Technical solutions are described for selecting components from multiple vendors for a system. An example computer-implemented method includes receiving, by a processor, an environment map that identifies a first component placeholder of the system. The computer-implemented method further includes identifying, by the processor, that the first component placeholder interfaces with a second component placeholder of the system. The computer-implemented method further includes determining, by the processor, a role assigned to the first component placeholder, where the role indicates a type of data that a first component at the first component placeholder communicates with a second component at the second component placeholder. The computer-implemented method further includes determining, by the processor, a list of components for selecting the first component, where each component from the list of components matches the role assigned to the first component placeholder.

Abstract: A notification message is received by a communication device The notification message includes a message identifier and a digital signature generated by an original sender of the notification message. That an integrity of message content in the notification message and an original sender of the notification message is verified is determined using the digital signature. Responsive to determining that the notification message is verified, the notification message is forwarded by the communication device using a peer-to-peer communication channel over a mesh network.

Abstract: An application configured to provide a service using a particular type of sensor data can be executed by a first mobile device. The application attempting to access the particular type of sensor data from the first mobile device can be detected. Responsive to detecting the application attempting to access the particular type of sensor data from the first mobile device, the first mobile device can receive first sensor data from at least a second mobile device via at least a first low energy communication link, wherein the first sensor data received from the second mobile device is the particular type of sensor data the application is attempting to access, and the first mobile device can execute program code configured to provide the particular type of sensor data, and providing the first sensor data received from the second mobile device to the application.

Abstract: Techniques for reconfiguring mobile networks based on network state information are provided. In one aspect, a method for managing a mobile network is provided. The method includes the steps of: gathering network state information from an edge of the mobile network, wherein the edge of the mobile network includes a radio network and a cellular network through which user equipment communicate with an internet protocol (IP) network which is at a core of the mobile network; analyzing the network state information based on policy controls to determine actions for optimizing the mobile network; and reconfiguring the mobile network using the actions for optimizing the mobile network. A system for managing a mobile network is also provided.

Abstract: An application configured to provide a service using a particular type of sensor data can be executed by a first mobile device. The application attempting to access the particular type of sensor data from the first mobile device can be detected. Responsive to detecting the application attempting to access the particular type of sensor data from the first mobile device, the first mobile device can receive first sensor data from at least a second mobile device via at least a first low energy communication link, wherein the first sensor data received from the second mobile device is the particular type of sensor data the application is attempting to access, and the first mobile device can execute program code configured to provide the particular type of sensor data, and providing the first sensor data received from the second mobile device to the application.

Abstract: An application configured to provide a service using a particular type of sensor data can be executed by a first mobile device. The application attempting to access the particular type of sensor data from the first mobile device can be detected. Responsive to detecting the application attempting to access the particular type of sensor data from the first mobile device, the first mobile device can receive first sensor data from at least a second mobile device via at least a first low energy communication link, wherein the first sensor data received from the second mobile device is the particular type of sensor data the application is attempting to access, and the first mobile device can execute program code configured to provide the particular type of sensor data, and providing the first sensor data received from the second mobile device to the application.

Abstract: A method of black ice detection includes receiving image stream data from a mobile device. The mobile device is in a vehicle. At least one of accelerometer data from at least one accelerometer, temperature and humidity data, and on board dash vehicle data is received. A classifier embedded in the mobile device is run to evaluate the received image stream data, and the at least one of the accelerometer data, the temperature and humidity data, and the on board dash vehicle data. It is determined whether black ice is present in the image stream data based on a result generated by the classifier.

Abstract: Technical solutions are described for selecting components from multiple vendors for a system. An example computer-implemented method includes receiving, by a processor, an environment map that identifies a first component placeholder of the system. The computer-implemented method further includes identifying, by the processor, that the first component placeholder interfaces with a second component placeholder of the system. The computer-implemented method further includes determining, by the processor, a role assigned to the first component placeholder, where the role indicates a type of data that a first component at the first component placeholder communicates with a second component at the second component placeholder. The computer-implemented method further includes determining, by the processor, a list of components for selecting the first component, where each component from the list of components matches the role assigned to the first component placeholder.

Abstract: A method of black ice detection includes receiving image stream data from a mobile device. The mobile device is in a vehicle. At least one of accelerometer data from at least one accelerometer, temperature and humidity data, and on board dash vehicle data is received. A classifier embedded in the mobile device is run to evaluate the received image stream data, and the at least one of the accelerometer data, the temperature and humidity data, and the on board dash vehicle data. It is determined whether black ice is present in the image stream data based on a result generated by the classifier.