Abstract: Various disclosed embodiments are directed to automatically generating a score indicative of a recommendation for applying a color value to content in an image based on extracting features from one or more objects in the image. In other words, particular embodiments map currently detected objects in an image to objects of the same class of historical images, which are then mapped to their corresponding background colors in order to recommend a particular background color of an image. In an illustrative example, if a particular set of Christmas objects, such as a reindeer object and Santa object, have historically been included in a red background, particular embodiments recommend a red color for the background of a currently processed image that includes the same reindeer and Santa objects.

Abstract: Early detection of Room Temperature Data Retention (RTDR) phenomena in programmed metablocks of data storage devices. In one embodiment, a memory controller includes a memory interface configured to interface with a non-volatile memory and a controller. The controller is configured to program a metablock of the non-volatile memory. Programming the metablock includes assigning the metablock to one of a plurality of thermal region tags (“TRTs”) associated with a respective one of a plurality of thermal regions. Each TRT is associated with a respective set of read parameters. The controller is further configured to perform a periodic TRT update to detect a RTDR phenomena associated with the metablock. In response to determining that the threshold associated with the detection of a RTDR phenomena has been exceeded, the controller reassigns the metablock to a different one of the TRTs.

Abstract: An application management platform comprising at least a packaging and bundling component, a deployment management component, and an update component. The packaging and bundling component versions, packages, and bundles a plurality of infrastructure components for a remote data center. The deployment management component provisions one or more nodes of the remote data center with the plurality of infrastructure components for an application. The update component monitors available updates to one or more of the plurality of infrastructure components used by the remote data center and facilitates update of the one or more of the plurality of infrastructure components at the remote data center.

Abstract: An application management platform comprising at least a packaging and bundling component, a deployment management component, and an update component. The packaging and bundling component versions, packages, and bundles a plurality of infrastructure components for a remote data center. The deployment management component provisions one or more nodes of the remote data center with the plurality of infrastructure components for an application. The update component monitors available updates to one or more of the plurality of infrastructure components used by the remote data center and facilitates update of the one or more of the plurality of infrastructure components at the remote data center.

Abstract: An application management platform comprising at least a packaging and bundling component, a deployment management component, and an update component. The packaging and bundling component versions, packages, and bundles a plurality of infrastructure components for a remote data center. The deployment management component provisions one or more nodes of the remote data center with the plurality of infrastructure components for an application. The update component monitors available updates to one or more of the plurality of infrastructure components used by the remote data center and facilitates update of the one or more of the plurality of infrastructure components at the remote data center.

Abstract: The present disclosure describes methods, systems, and non-transitory computer-readable media for implementing a machine learning framework to generate a recommend digital assets from a digital image. For example, in one or more embodiments, the disclosed systems utilize a machine learning model to detect a shape, color, pattern, or other digital asset type from a digital image and then extract (and further modify) the detected asset type to create various different digital assets as recommendations. In some cases, the disclosed system utilizes the machine learning model to determine one or more digital asset classes associated with the digital image, generate preprocessed digital assets from the digital image for those digital asset classes, and generate production-ready digital assets from the preprocessed digital assets. Further, in some instances, the disclosed systems provide one or more of the digital assets via recommendations based on asset scores determined via the generation process.

Abstract: A method and system for performing adaptive consensus in a distributed ledger network are disclosed. The method includes identifying a selector node from plurality of nodes within distributed ledger network, based on random selection algorithm. The method includes adaptively selecting set of consensus nodes from plurality of nodes based on set of predefined node parameters and plurality of sensitivity parameters to create an unverified block in a ledger of each of adaptively selected set of consensus nodes. The method includes computing hash value for each of at least one new transaction in distributed ledger network. The method includes performing consensus based on computed hash value for identifying set of valid transactions in unverified blocks created by each of adaptively selected set of consensus nodes. The method includes creating verified block including set of valid transactions, and commits verified block to distributed ledger in distributed ledger network.

Abstract: A system, apparatus, and method for dynamic allocation of sub-blocks. First, a non-volatile memory array receives a set of write commands. The non-volatile memory array comprises multiple memory dies organized into metablocks. The metablocks are configured to span two or more memory dies. A stream manager determines a workload type for the set of write commands. A block allocation manager selects a target storage block to receive the set of write commands based on the workload type. The selected target storage block is configured to receive data blocks for the workload type and the block allocation manager directs the set of write commands to the target storage block.

Abstract: A method and system are described for secure communication. The system receives a first secure protocol data packet during an authenticated session to communicate with a user computing device using a secure protocol. The encrypted linked data in first secure protocol data packet is decrypted using a secure key that is dependent on encrypted linked data and user credentials. The system retrieves a second secure protocol data packet from a distributed ledger network that is associated with first secure protocol data packet. The encrypted linked data in second secure protocol data packet is decrypted. The system identifies changes between decrypted linked data of first secure protocol data packet and decrypted linked data of second secure protocol data packet and if changes are identified then first secure protocol data packet is considered as tampered and actions in first secure protocol data packet are not executed, thereby preventing fraudulent execution of transactions.

Abstract: There is a need for more reliable and efficient disease spread forecasting. This need can be addressed by, for example, solutions for performing optimization-based disease spread forecasting using a multi-risk-level disease spread forecasting machine learning model.

Abstract: A method and system for performing adaptive consensus in a distributed ledger network are disclosed. The method includes identifying a selector node from plurality of nodes within distributed ledger network, based on random selection algorithm. The method includes adaptively selecting set of consensus nodes from plurality of nodes based on set of predefined node parameters and plurality of sensitivity parameters to create an unverified block in a ledger of each of adaptively selected set of consensus nodes. The method includes computing hash value for each of at least one new transaction in distributed ledger network. The method includes performing consensus based on computed hash value for identifying set of valid transactions in unverified blocks created by each of adaptively selected set of consensus nodes. The method includes creating verified block including set of valid transactions, and commits verified block to distributed ledger in distributed ledger network.

Abstract: A method and system are described for secure communication. The system receives a first secure protocol data packet during an authenticated session to communicate with a user computing device using a secure protocol. The encrypted linked data in first secure protocol data packet is decrypted using a secure key that is dependent on encrypted linked data and user credentials. The system retrieves a second secure protocol data packet from a distributed ledger network that is associated with first secure protocol data packet. The encrypted linked data in second secure protocol data packet is decrypted. The system identifies changes between decrypted linked data of first secure protocol data packet and decrypted linked data of second secure protocol data packet and if changes are identified then first secure protocol data packet is considered as tampered and actions in first secure protocol data packet are not executed, thereby preventing fraudulent execution of transactions.

Abstract: A system, apparatus, and method for dynamic allocation of sub-blocks. First, a non-volatile memory array receives a set of write commands. The non-volatile memory array comprises multiple memory dies organized into metablocks. The metablocks are configured to span two or more memory dies. A stream manager determines a workload type for the set of write commands. A block allocation manager selects a target storage block to receive the set of write commands based on the workload type. The selected target storage block is configured to receive data blocks for the workload type and the block allocation manager directs the set of write commands to the target storage block.

Abstract: A storage device may include a controller performing non data word line (NDWL) maintenance in sub block mode (SBM). The NDWL maintenance in SBM can include proactive select gate drain (SGD) detection and phased SGD correction. For example, when a block reaches a PE cycle threshold value, SGD phased correction occurs upon detection of an error, by determining whether a sister sub block of the selected block contains data. If the sister sub block contains data, the data is transferred from the sister sub block, and then the block and sister sub block undergo correction for NDLW maintenance.

Abstract: A method and device for controlling a vehicle based on neighboring vehicles is disclosed. The method includes identifying a fiduciary object associated with each of at least one neighboring vehicle based on at least one image captured for the at least one neighboring vehicle. The method further includes tracking a position of the fiduciary object associated with each of the at least one neighboring vehicle based on a bounding box surrounding the fiduciary object. The method includes determining a direction-speed vector for the vehicle and determining trajectory data associated with each of the one or more neighboring vehicles. The method further includes correlating the position of the fiduciary object and the trajectory data associated with each of the at least one neighboring vehicle. The method includes re-computing the direction-speed vector of the vehicle based on a result of correlating and controlling the vehicle thereafter.

Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that use a design-component-neural network to categorize a design component from an interface-design file as a platform widget corresponding to a particular computing platform. Having categorized the design component as a platform widget, in certain implementations, the disclosed systems compare and validate properties of the design component against user-interface guidelines for the particular computing platform. Upon determining that the design component does not comply with a user-interface guideline, the systems can provide and implement options to modify the design component to comply with the user-interface guideline.

Abstract: A method and device for controlling a vehicle based on neighboring vehicles is disclosed. The method includes identifying a fiduciary object associated with each of at least one neighboring vehicle based on at least one image captured for the at least one neighboring vehicle. The method further includes tracking a position of the fiduciary object associated with each of the at least one neighboring vehicle based on a bounding box surrounding the fiduciary object. The method includes determining a direction-speed vector for the vehicle and determining trajectory data associated with each of the one or more neighboring vehicles. The method further includes correlating the position of the fiduciary object and the trajectory data associated with each of the at least one neighboring vehicle. The method includes re-computing the direction-speed vector of the vehicle based on a result of correlating and controlling the vehicle thereafter.

Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that use a design-component-neural network to categorize a design component from an interface-design file as a platform widget corresponding to a particular computing platform. Having categorized the design component as a platform widget, in certain implementations, the disclosed systems compare and validate properties of the design component against user-interface guidelines for the particular computing platform. Upon determining that the design component does not comply with a user-interface guideline, the systems can provide and implement options to modify the design component to comply with the user-interface guideline.

Abstract: A non-isolated capacitive AC-DC conversion power supply includes a current limiting input module that receives AC input power and has an output capacitor that supplies DC power. Charge storage stages have charge storage capacitors, a rectifier supplying rectified current from the input module to charge the charge storage capacitors and the output capacitor during a first part-cycle of the AC input power. The charge storage stages also include current amplifiers and unidirectional elements that conduct discharge current from the charge storage capacitors to charge the output capacitor during a second part-cycle of the AC input power. Ground of the DC output can be connected to the live AC input.

Abstract: The present invention relates to micro machined metal diaphragm for Fabry-Perot interferometer sensor and Fabry Perot Fiber optic Sensor system using said metal diaphragm and method of fabrication thereof. Fabry Perot sensor with micro machined metallic diaphragms at the fiber optic end is developed ensuring accuracy, controllability by deterministic process. Advantageously, the system involves the metal diaphragm with high reflectivity inside surface facing the fiber end as a basic functional element. Importantly, the micro machined metal diaphragm is miniaturized to suit various critical applications including bio medical sensing devices for measuring various physiological parameters with desired accuracy.