Abstract: Aspects of the present disclosure relate to controlling resource consumption of a server and storage array. In embodiments, a request can be received by a server that is communicatively coupled to a storage array. Further, the services required to process the request can be identified. Additionally, services' activation can be controlled based on a mapping of request-related actions and initiated services.

Abstract: A delivery system (400) for delivering and deploying an implant (550) to a bodily lumen (600). The delivery system (400) comprises a delivery element (410) and a detach mechanism (420) connected to a distal portion of the delivery element (410). The detach mechanism (420) has a first configuration configured to grip the implant (550) and a second configuration configured to release the implant (550). An actuating mechanism (430) is configured to extend through the lumen of a delivery catheter (500) to the detach mechanism (420). Moving the actuating mechanism (430) from a first position to a second position changes the detach mechanism (430) from the first configuration to the second configuration.

Abstract: A system for the delivery of an embolization device comprising a delivery wire and an expandable structure, wherein the system comprises a loading device comprising a compartment configured to contain the expanded structure of the embolization device; a conduit configured to receive the delivery wire of the embolization device, wherein the conduit is coupled to the compartment; and a fluid inlet in fluid communication with the compartment.

Abstract: A method, computer program product, and computer system are provided for evaluating carbon sequestration contributions of nature-based assets located in water environments. The method includes: obtaining meta-descriptors of a nature-based asset and a region of a water environment in which the asset is located; mapping dimensions of the nature-based asset; accessing data of monitored physical characteristics of the nature-based asset in the water environment based on the meta-descriptors of the asset; accessing data of monitored carbon concentration in the region of the water environment based on the meta-descriptors of the region; accessing data on monitored physical, chemical, and biological properties of the water environment based on the meta-descriptors of the region; and applying a model to the accessed data to assign a carbon sequestration contribution per unit measurement of the nature-based asset.

Abstract: An embolization system for promoting clot formation in a body lumen (700). The system comprises a self-expandable embolization device (100), having a collapsed delivery configuration and an expanded deployed configuration in which the self-expandable embolization device (100) is radially expanded to anchor to a bodily lumen (700). The system also comprises an inflatable body (800) connected to the embolization device (100), the inflatable body (800) having a deflated configuration and an inflated configuration, wherein in the inflated configuration the inflatable body (800) anchors to the bodily lumen (700). The inflatable body (800) is positionable relative to the self-expandable embolization device (100) such that it is inflatable from the deflated configuration to the inflated configuration as the self-expandable embolization device (100) remains in the collapsed delivery configuration.

Abstract: Techniques of facilitating deep learning model rescaling by computing devices. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise: a rescaling component; and a forecasting component. The rescaling component can determine a scaling ratio that maps low mesh resolution predictive data output by a partial differential equation (PDE)-based model for a sub-domain to high-resolution observational or ground-truth data for a domain comprising the sub-domain. The forecasting component can generate high mesh resolution predictive data for the domain with a machine-learning model using input data of the PDE-based model and the scaling ratio.

Abstract: A computing device configured for automatic selection of model parameters includes a processor and a memory coupled to the processor. The memory stores instructions to cause the processor to perform acts including providing an initial set of model parameters and initial condition information to a model based on historical data. A model generates data based on the model parameters and the initial condition information. After determining whether the model-generated data is similar to an observed data, updated model parameters are selected for input to the model based on the determined similarity.

Abstract: A method for quantifying oceanic carbon dioxide (CO2) sequestration is provided. The method includes obtaining a plurality of oceanic spatiotemporal carbon dioxide (CO2) measurements. A plurality of spatiotemporal chlorophyll a (Chl-a) and a plurality of oceanic temperature measurements are obtained. The obtained plurality of oceanic spatiotemporal CO2 measurements is mapped to the obtained plurality of spatiotemporal Chl-a and the plurality of oceanic temperature measurements in a multidimensional grid. At least one a priori oceanic spatiotemporal CO2 estimate is generated based on the multidimensional grid.

Abstract: In an approach for a virtual assistant career mentor that provides a user with personalized career recommendations, a processor identifies a position a user wishes to achieve in a request for a personalized career recommendation. A processor compares a user profile of the user to a marketplace profile for the position to determine whether there are one or more gaps in the user profile that would prevent the user from achieving the position. Responsive to determining there is a gap in the user profile, a processor assigns the user a task to address the gap in the user profile. A processor generates a performance score using a reinforcement learning model. Responsive to updating the user profile with the performance score, a processor generates a recommendation using machine learning, wherein the recommendation includes a series of actions the user may take to achieve the position identified and an appropriate timeline.

Abstract: An embodiment establishes a knowledge base based at least in part on sensor data received from a network. The embodiment generates a predicted performance parameter for a designated entity of the network using a first machine learning algorithm. The embodiment compares the predicted performance parameter to an actual performance parameter and determines whether the actual performance parameter exceeds a threshold difference from the predicted performance parameter. The embodiment generates, responsive to determining that the threshold difference is exceeded, incentive data using a second machine learning algorithm, where the incentive data is representative of an action selected by the second machine learning algorithm using an iterative optimization process, and where the iterative optimization process comprises performing the action and determining that the actual performance parameter approaches the threshold value in response to the action.

Abstract: Embodiments are directed to a computer-implemented method of analyzing a land region that has been decomposed into a plurality of regular or irregular sub-regions. The computer-implemented method includes applying, using a processor system, a feature extraction process that extracts a set of sub-region environmental descriptors for each of the plurality of sub-regions. The processor system applies a similarity analysis to the set of sub-region environmental descriptors to generate groups of the plurality of sub-regions. The processor system creates a plurality of group-based graphs by encoding each of the groups into a corresponding group-based graph. A spatio-temporal neural network is used to train a model based at least in part on the plurality of group-based graphs.

Abstract: Systems and methods for are provided for offloading computing tasks from constrained devices. An example apparatus includes an offload computing protocol (OCP) enabled device. The OCP enabled device includes OCP extensions to the operating system to enable the offloading of computing tasks. A proximity locator may use a radio transceiver to locate an OCP device that can accept a computing task. The OCP enabled device may include an OCP bundle comprising code and data, wherein the OCP bundle is to be sent to the OCP device.

Abstract: A method, computer program product and computer system to generate safety alerts is provided. A processor retrieves a plurality of measurements associated with a location. A processor determines a set of features based on the plurality of measurements. A processor identifies a set of membership functions for the set of features. A processor determines a safety index for the body of water based on the set of membership functions and one or more input value ranges for the set of features. In response to the safety index being above a threshold value, a processor sends an alert to one or more users regarding the location.

Abstract: Job report objects (Java objects) are created by task executors in connection with implementation of a job on a storage system. The Java objects are passed to a job report service that converts the Java objects into XML objects using an XML encoder/decoder. The XML objects are persisted by the job report service as text in a database. If a job report is requested, the job report service retrieves a job record for the corresponding report from the database, creates Java objects, and passes the Java objects to a storage system management client. The client creates an internal model of the report containing a corresponding set of strongly typed TypeScript objects. The TypeScript objects are passed to a pdf data exporter that converts the internal TypeScript objects into untyped JavaScript objects. The untyped JavaScript objects are input to a .pdf generator which generates the requested report as a .pdf document.

Abstract: Embodiments for managing a wave energy converter (WEC) device by one or more processors are described. At least one environmental characteristic associated with a WEC device in a body of water is received. A prediction of wave conditions on the body of water is calculated based on the at least one environmental characteristic. A signal representative of the prediction of wave conditions is generated.

Abstract: Systems and methods for are provided for offloading computing tasks from constrained devices. An example apparatus includes an offload computing protocol (OCP) enabled device. The OCP enabled device includes OCP extensions to the operating system to enable the offloading of computing tasks. A proximity locator may use a radio transceiver to locate an OCP device that can accept a computing task. The OCP enabled device may include an OCP bundle comprising code and data, wherein the OCP bundle is to be sent to the OCP device.

Abstract: Intelligent classification for product pedigree identification are presented. A transaction agreement request may be received from a user. A revised transaction agreement request may be generated based on one or more user profiles, a multi-party entity feedback loop, one or more constraints relating to the transaction agreement request, and a transaction agreement fulfillment requirements of the entity.

Abstract: Embodiments for providing enhanced edge-based forecasting in a computing environment by a processor. Data from received from one or more data sources may be incorporated into a graph neural network. A forecast of one or more future conditions may be generated based the graph neural network using one or more forecasting models.

Abstract: Embodiments for providing expert-in-the-loop training of machine learning models in a computing environment by a processor. A performance of a machine learning model may be learned. Feedback for the machine learning model may be received based on learning the performance the machine learning model, where the feedback includes domain knowledge provided by a domain expert. The machine learning model may be trained or updated based the feedback of the performance of the machine learning model.

Abstract: Embodiments for providing enhanced generative models based assistance for design and creativity in a computing environment by a processor. A partially completed design of an object may be received. A set of recommendations may be generated for completing the partially completed design based on one or more generative models.