Abstract: Peer-based positioning of nodes in an environment is disclosed. A node is able to determine its own position using sources. The sources may include fixed and/or mobile beacons. Each of the sources is associated with a distance error and a position error. These errors, along with distance measurements between the node and each of the sources, are used to determine a position and a total positioning error, which reflects the accuracy of the determined position.

Abstract: One example method includes scanning, at a point of sale (POS) site, a physical object, transmitting, from the POS site to a regional environment, information obtained as a result of the scanning of the physical object, identifying the physical object based on the information, automatically labeling any new data generated as a result of the identifying of the physical object, and storing the new data. The information obtained as a result of the scanning may be used to determine whether or not a fraudulent transaction has taken place at the POS site.

Abstract: Real-time event detection is performed on nodes in an environment using position data that is not available to a node in real time but is delayed. A node performs real time event detection by predicting a position of the node based at least in part on delayed position data. The delayed position data is aligned to other sensor data. Aligning the position data may include predicting a position based on dead reckoning and/or a machine learning model. One or more collections of data, each collection including sensor data and predicted position data, is input to a model that performs event detection.

Abstract: Real-time event detection is performed on nodes in an environment using position data that is not available to a node in real time but is delayed. A node performs real time event detection by predicting a position of the node based at least in part on delayed position data. The delayed position data is aligned to other sensor data. Aligning the position data may include predicting a position based on dead reckoning and/or a machine learning model. One or more collections of data, each collection including sensor data and predicted position data, is input to a model that performs event detection.

Abstract: Digital twin-based logistics operations are disclosed. A digital twin virtual environment models a physical environment and includes virtual nodes and virtual sensors that have corresponding physical nodes and physical sensors in the physical environment. Positions of the nodes are tracked in the digital twin. Using position data and other sensor data, the digital twin can be used to train machine learning models, label data for training, aggregate data, generate warnings, and cause a real or virtual display to be displayed when an event is predicted or determined.

Abstract: Detecting damaged packages is disclosed. Transport mechanisms, such as pallets, are equipped with sensors including inertial sensors. The inertial data, in conjunction with characteristics of the packages such as fragility values, can be used to determine whether a package may be damaged. If damage is suspected, the package can be inspected. The ability to detect damage may also use package geometries and the like. When damage is suspected, remedial actions can be performed.

Abstract: One example method includes receiving datasets based on one or more instances of sensor data that are received from one or more sensors. The sensor data is associated with an aggregate fragility level that indicates how fragile one or more packages being transported by a movable edge node in an edge environment are. Features that are based on the datasets are extracted. Based on the extracted features, events that indicate anomalous driving patterns for the movable edge node are determined. In response to determining the events, an alarm based on a predetermined threshold that is based on the aggregate fragility level is generated.

Abstract: One example method includes receiving datasets based on one or more instances of sensor data that are received from one or more sensors. The sensor data is associated with an aggregate fragility level that indicates how fragile one or more packages being transported by a movable edge node in an edge environment are. Features that are based on the datasets are extracted. Based on the extracted features, events that indicate anomalous driving patterns for the movable edge node are determined. In response to determining the events, an alarm based on a predetermined threshold that is based on the aggregate fragility level is generated.

Abstract: One example method is performed at a far edge device and includes collecting data with one or more IoT (Internet of Things) devices, feeding the data to a feedback loop that includes multiple stages, running the feedback loop, providing learning information, comprising output from one or more of the stages of the feedback loop, to a central manager by way of a learn interface, accessing learning information generated by one or more other far edge devices, and updating the feedback loop using the learning information generated by the one or more other far edge devices.

Abstract: Peer-based positioning of nodes in an environment is disclosed. A node is able to determine its own position using sources. The sources may include fixed and/or mobile beacons. Each of the sources is associated with a distance error and a position error. These errors, along with distance measurements between the node and each of the sources, are used to determine a position and a total positioning error, which reflects the accuracy of the determined position.

Abstract: Real-time event detection is performed on nodes in an environment using position data that is not available to a node in real time but is delayed. A node performs real time event detection by predicting a position of the node based at least in part on delayed position data. The delayed position data is aligned to other sensor data. Aligning the position data may include predicting a position based on dead reckoning and/or a machine learning model. One or more collections of data, each collection including sensor data and predicted position data, is input to a model that performs event detection.

Abstract: An event driven detection model is disclosed. A model operates at a node using data generated by sensors associated with the node to identify events. The events are provided to a model configure to infer whether the event is non-normative. When a non-normative event is inferred by the model, a decision may be made and performed.

Abstract: At least one processing platform comprises virtualization infrastructure, an assurance module, an orchestration module, and an analytic engine coupled to the assurance module and the orchestration module. The assurance module is configured to monitor resources provided using the virtualization infrastructure under the control of the orchestration module. The analytic engine is configured to process monitoring results from the assurance module and to generate corresponding feedback to the orchestration module. The feedback to the orchestration module is utilized for at least one of adjusting one or more characteristics of the resources provided using the virtualization infrastructure, and performing one or more orchestration operations relating to the resources provided using the virtualization infrastructure. A topology module may be coupled to the analytic engine and configured to generate topology information relating to the resources.

Abstract: Distributed nodes are implemented using virtualization infrastructure of at least one processing platform. The processing platform is implemented using at least one processing device comprising a processor coupled to a memory. The distributed nodes collectively provide at least a portion of a distributed contextual analytics framework comprising analytics functions deployed at respective ones of the nodes. For example, the distributed nodes illustratively comprise multiple local nodes and at least one central node, with the distributed contextual analytics framework comprising local analytics functions deployed at respective ones of the local nodes and a central analytics function deployed at the central node.

Abstract: A plurality of virtual content delivery network nodes are implemented using virtualization infrastructure of at least one processing platform. The processing platform is implemented using at least one processing device comprising a processor coupled to a memory. Each of the virtual content delivery network nodes comprises one or more virtual network function instances of a network functions virtualization framework of the virtualization infrastructure. The virtual content delivery network nodes may be dynamically added to, modified in and deleted from at least one virtual content delivery network in accordance with one or more specified policy criteria. A virtual content delivery network control plane may be arranged as an overlay relative to the network functions virtualization framework of the virtualization infrastructure. The virtual content delivery network control plane communicates with the network functions virtualization framework via one or more application programming interfaces.

Abstract: A processing platform implemented using one or more processing devices comprises a data fabric layer and a storage infrastructure layer underlying the data fabric layer. The data fabric layer comprises at least one database application having a plurality of nodes. The storage infrastructure layer comprises a plurality of storage servers and is configured to implement one or more virtual storage volumes for each of the nodes of the database application of the data fabric layer using the storage servers. In some embodiments, responsive to detection of a failure of a given one of the nodes of the database application, the one or more virtual storage volumes associated with the given node are utilized to facilitate instantiation of a replacement node for the given node. For example, a virtual storage volume may be unmounted from the given node and attached to the replacement node.

Abstract: An apparatus comprises at least one processing platform implemented using at least one processing device comprising a processor coupled to a memory. The processing platform comprises virtualization infrastructure, an assurance layer and an analytic layer. The assurance and analytic layers are configured to provide data collection and event management functionality to support automation relating to resources of the virtualization infrastructure and associated workloads. By way of example, the assurance and analytic layers illustratively comprise respective deterministic and indeterministic functional groupings of components. The functional groupings of components of the assurance and analytic layers are utilized to implement closed-loop remediation workflows and other types of automation relating to the virtualization infrastructure resources and their associated workloads.