Abstract: Techniques are described with respect to a system, method, and computer program product for parallel reality-based content presentation. An associated method includes receiving a viewing event; analyzing the viewing event, and generating a privatized parallel reality-based credential associated with a user based on the analysis.

Abstract: A method, system, and computer program product are configured to: receive camera data from a thermal camera; determine a suggested region of interest (ROI) using the camera data, an object detection model, an anomaly detection model, and a shape recommendation model; determine a final ROI using the suggested ROI and a selection rule; and communicate the final ROI to the thermal camera.

Abstract: A computer-implemented method may include linking a user's virtual interaction data with a service or product to a virtual token; determining that the virtual token is associated with a user that provided consent to link a virtual avatar to a user's real-world computing device anonymously via TSP scrubbing; linking the virtual avatar to the user's real-world computing device anonymously; determining competitive recency, frequency, and time analysis (CRFT) based on the user's virtual interaction data with the service or product via the virtual avatar; determining, based on the CRFT metrics, a match between the virtual token and the service or product; and communicating to an entity associated with the service or product of a determination of the match between the virtual token and the service or product based on the CRFT metrics.

Abstract: Application migration recommendation based on energy consumption includes receiving time series data of application energy consumption and application usage metrics associated with an application being considered for migration in a computing environment. Energy aware design catalog having a list of design patterns for migration and associated design detection functions is provided. For each of the design patterns listed in the energy aware design catalog, a design detection function associated with a design pattern is run using the time series data of application energy consumption and application usage metrics, where the design detection function outputs whether the application is suitable for transformation using the design pattern and projected energy savings if the transformation is implemented using the design pattern. A design pattern estimated to have largest projected energy savings is returned as recommended migration for the application.

Abstract: One embodiment provides a method including dynamically measuring, by a computing device, dust level representing decay in transistor current output by utilizing at least one particle deposition (PD) detection sensor that utilizes machine learning (ML) for condition based photovoltaic (PV) panel cleaning. An ML-based edge process is utilized for managing a cleaning schedule and cleaning fleets. Yield is boosted and dynamic planning is improved based on multiple input sources for the ML-based edge process.

Abstract: A system, method, and computer program product are configured to receive a first hash along with time stamps, wherein the first hash comprises a hash of a branded product and a list of virtual identifications (IDs) which interacted with the branded product in a metaverse, and wherein each of the time stamps corresponds to the time of interaction between each of the virtual ID and the product; receive a hash pre-image; compare the hash pre-image with the first hash; retrieve a list of users associated with the virtual IDs of the first hash; generate tokens, respective ones of the tokens associated with respective ones of the users; and transmit the tokens to a server associated with the branded product.

Abstract: A workload allocation engine is configured to allocate a workload in a cloud architecture. A data center for an enterprise is identified, and for the data center, a plurality of servers within the data center and a plurality of virtual machines (VMs) running on the servers are identified. Based upon at least one predetermined factor, a plurality of clusters of the servers generated. For each of the clusters, a plurality of time-series variables are tracked. For each of the clusters and the workload, carbon emissions generated by a particular cluster and for the workload are predicted. The workload is assigned to the particular cluster based upon the predicted carbon emissions associated with the particular cluster, and the workload is performed by the particular cluster.

Abstract: A method is presented including inspecting a cell site, in real-time, with an unmanned aerial vehicle (UAV) including an edge-based artificial intelligence (AI) component mounted thereon, capturing, by one or more cameras of the UAV, a plurality of images pertaining to at least antennae and communication equipment associated with the cell site, identifying, by the AI component, in real-time, the plurality of images to dynamically apply AI inspection models thereto, and generating, in real-time, an inspection report based on information and data derived from applying the AI inspection models to the plurality of images captured.

Abstract: A method includes enabling a plurality of users to interact with a virtual world, each of the users represented as one or more avatars in the virtual world, obtaining preferences and consent of each of the users, displaying promotional messages to a user of the plurality of users in the virtual world based on the user's preferences and consent, and after displaying the promotional messages to the user, filtering the user's preferences and consent from the virtual world to remove transaction footprints.

Abstract: A method, computer program product, and computer system are provided for storing images and/or other data on an edge computing device in an edge computing environment. Data is received from one or more sensors operatively coupled to the edge computing device. One or more features and metadata are extracted from the received data. The extracted features and metadata are compared to a pre-defined tolerance range and one or more exogenous variables. The received data is caused to be stored on either the edge computing device or a second edge computing device based on a determination that the compared features and metadata falls within the tolerance range or outside of the tolerance range, respectively.

Abstract: An edge device can receive a commercial communication, a scrubbed token list and a telephone number list. Responsive to determining the mobile device is detected in the specific area, whether a telephone number of the mobile device is contained in the telephone number list can be determined. Responsive to determining that the telephone number of the mobile device is contained in the telephone number list, the telephone number of the mobile device, the scrubbed token list and the commercial communication can be communicated to an originating access provider, wherein the originating access provider communicates to the mobile device the commercial communication based, at least in part, upon whether the telephone number of the mobile device matches a token contained in the scrubbed token list.