Abstract: The present disclosure provides methods and systems for real-time delivery of a target content in a streaming content. The method comprising receiving a request for streaming content from at least one user device [102]. The request comprises user segment information associated with the at least one user device. Next, the method comprises dynamically fetching at least one target content for the at least one user device [102] based on the user segment information. Next, the method comprises creating a customized virtual manifest by inserting the at least one target content in the requested streaming content in real-time. Next, the method comprises sending the customized virtual manifest to the at least one user device [102] based on the user segment information. Thereafter, the method comprises delivering the at least one target content in the requested streaming content to the at least one user device [102] based on the customized virtual manifest.

Abstract: The disclosure relates to a framework for dynamic management of analytic functions such as data processors and machine learned (“ML”) models for an Internet of Things intelligent edge that addresses management of the lifecycle of the analytic functions from creation to execution, in production. The end user will be seamlessly able to check in an analytic function, version it, deploy it, evaluate model performance and deploy refined versions into the data flows at the edge or core dynamically for existing and new end points. The framework comprises a hypergraph-based model as a foundation, and may use a microservices architecture with the ML infrastructure and models deployed as containerized microservices.

Abstract: A system and method for accounting for the impact of concept drift in selecting machine learning training methods to address the identified impact. Pattern recognition is performed on performance metrics of a deployed production model in an Internet-of-Things (IoT) environment to determine the impact that concept drift (data drift) has had on prediction performance. This concurrent analysis is utilized to select one or more approaches for training machine learning models, thereby accounting for the temporal dynamics of concept drift (and its subsequent impact on prediction performance) in a faster and more efficient manner.

Abstract: A system and method for dynamically optimizing content delivery in a wireless communication network. The method comprises receiving, at a transceiver [208A], a request for delivery of a content from at least one user device [202]. A manifest module [208B] determines one or more first parameters for the at least one user device [202] and compares one or more parameters of the at least one user device [202] with one or more second parameters of the at least one cohort. The manifest module [208B] dynamically identifies (or generates) a virtual manifest associated with the at least one cohort (or the at least one user device [202]) based on the comparison. A segmenter module [208C] automatically extracts a stream of data associated with the virtual manifest. The transceiver [208A] delivers the content to the at least one user device [202] based on the extracted stream of data.

Abstract: The disclosure relates to a framework for dynamic management of analytic functions such as data processors and machine learned (“ML”) models for an Internet of Things intelligent edge that addresses management of the lifecycle of the analytic functions from creation to execution, in production. The end user will be seamlessly able to check in an analytic function, version it, deploy it, evaluate model performance and deploy refined versions into the data flows at the edge or core dynamically for existing and new end points. The framework comprises a hypergraph-based model as a foundation, and may use a microservices architecture with the ML infrastructure and models deployed as containerized microservices.

Abstract: The disclosure relates to technology that implements flow control for machine learning on data such as Internet of Things (“IoT”) datasets. The system may route outputs of a data splitter function performed on the IoT datasets to a designated target model based on a user specification for routing the outputs. In this manner, the IoT datasets may be dynamically routed to target datasets without reprogramming machine-learning pipelines, which enable rapid training, testing and validation of ML models as well as an ability to concurrently train, validate, and execute ML models.

Abstract: Aspects of the embodiments include receiving a packet at a network element of a packet-switched network; identifying a presence of a shared service destination address in a header of the packet; identifying a shared service destination address for the packet based, at least in part, on a destination internet protocol (IP) address stored in a forward information base; and forwarding the packet to the shared service destination address.

Abstract: Examples described herein relate to a network element comprising an ingress pipeline and at least one queue from which to egress packets. The network element can receive a packet and generate a congestion notification packet at the ingress pipeline to a sender of the packet based on detection of congestion in a target queue that is to store the packet and before the packet is stored in a congested target queue. The network element can generate a congestion notification packet based on a queue depth of the target queue and likelihood the target queue is congested. The likelihood the queue is congested can be based on a probabilistic function including one or more of Proportional-Integral (PI) or Random Early Detection (RED). The network element can determine a pause time for the sender to pause sending particular packets based at least on a time for the target queue to drain to a target level.

Abstract: A system and method for accounting for the impact of concept drift in selecting machine learning training methods to address the identified impact. Pattern recognition is performed on performance metrics of a deployed production model in an Internet-of-Things (IoT) environment to determine the impact that concept drift (data drift) has had on prediction performance. This concurrent analysis is utilized to select one or more approaches for training machine learning models, thereby accounting for the temporal dynamics of concept drift (and its subsequent impact on prediction performance) in a faster and more efficient manner.

Abstract: The disclosure relates to a framework for dynamic management of analytic functions such as data processors and machine learned (“ML”) models for an Internet of Things intelligent edge that addresses management of the lifecycle of the analytic functions from creation to execution, in production. The end user will be seamlessly able to check in an analytic function, version it, deploy it, evaluate model performance and deploy refined versions into the data flows at the edge or core dynamically for existing and new end points. The framework comprises a hypergraph-based model as a foundation, and may use a microservices architecture with the ML infrastructure and models deployed as containerized microservices.

Abstract: The disclosure relates to technology that implements flow control for machine learning on data such as Internet of Things (“IoT”) datasets. The system may route outputs of a data splitter function performed on the IoT datasets to a designated target model based on a user specification for routing the outputs. In this manner, the IoT datasets may be dynamically routed to target datasets without reprogramming machine-learning pipelines, which enable rapid training, testing and validation of ML models as well as an ability to concurrently train, validate, and execute ML models.

Abstract: Disclosed are systems, methods, and computer-readable storage media for minimizing the number of entries in network access control lists (ACLs). In some embodiments of the present technology a networking device can receive, from a first computing device, a first data transmission intended for a second computing device, the first data transmission including first transmission data. The networking device can normalize at least a subset of the first transmission data based on a predetermined normalization algorithm, yielding a first normalized data set for the first data transmission. Subsequently, the networking device can identify a first access control list entry from a set of access control list entries based on the first normalized data set, the first access control list entry identifying a first action, and implement the first action in relation to the first data transmission.

Abstract: A system and method for providing in-flight weather information to compute an optimized vertical flight profile are disclosed. In one embodiment, on-board weather information is obtained from one or more aircraft at regular intervals during flight. Further, weather information is identified for a predicted flight trajectory of an aircraft from the obtained on-board weather information. For example, the aircraft is preceding the at least one aircraft. Furthermore, a subset of the identified weather information is dynamically provided to a flight management system (FMS) in the aircraft, during flight, to compute the optimized vertical flight profile.

Abstract: Aspects of the embodiments include receiving a packet at a network element of a packet-switched network; identifying a presence of a shared service destination address in a header of the packet; identifying a shared service destination address for the packet based, at least in part, on a destination internet protocol (IP) address stored in a forward information base; and forwarding the packet to the shared service destination address.

Abstract: Techniques are presented herein for distributing address information of host devices in a network. At a first router device, a packet is received from a first host device that is destined for a second host device. The first host device is dually-connected to the first router and a second router device. The second router device is part of a virtual port channel pair with the first router device. A message is sent to the second router device, the message indicating that the first host device is connected to the second router device. The packet is encapsulated with an overlay header and is sent to a third router device that is connected to the second host device. The encapsulated packet contains a Layer 2 address associated with the first host device and a Layer 3 address associated with the first host device.

Abstract: Aspects of the embodiments include receiving a packet at a network element of a packet-switched network; identifying a presence of a shared service destination address in a header of the packet; identifying a shared service destination address for the packet based, at least in part, on a destination internet protocol (IP) address stored in a forward information base; and forwarding the packet to the shared service destination address.

Abstract: A system and method for aircraft cabin activity management occurring during turnaround using video analytics are disclosed. In one embodiment, real-time video feed of the aircraft cabin activities is obtained during the turnaround from at least one video camera disposed in an aircraft cabin. Further, aircraft cabin activity time stamps and progress associated with one or more aircraft cabin activities are determined by applying video analytics on the obtained video feed. Furthermore, the aircraft cabin activities are managed using the determined aircraft cabin activity time stamps and the progress associated with the one or more aircraft cabin activities.

Abstract: A system for monitoring scheduled turnaround activities and alerting on time deviation from the scheduled turnaround activities is disclosed. The system includes a ground computing station system, an aircraft on-board system, a cloud, and user interface. The cloud is communicatively coupled to the ground station computing system and the aircraft on-board system. The cloud includes processor and memory. The memory includes an analytics module to obtain actual start and end time stamps associated with scheduled turnaround activities, from touchdown to takeoff of an aircraft, from aircraft on-board systems and a ground station system. The analytics module to determine time deviation of scheduled turnaround activities by analyzing the obtained actual start and end time stamps. The user interface to present each scheduled turnaround activity and determined time deviation of the scheduled turnaround activities.

Abstract: In one example, a computing system to monitor aircraft operational parameters during turnaround of an aircraft is disclosed. The computing system may include at least one processor, and memory coupled to the at least one processor. The memory may include an analytics module to obtain at least one aircraft operational parameter during turnaround of an aircraft from an aircraft on-board system, analyze the at least one aircraft operational parameter related to the turnaround with respect to a threshold value or a range of threshold values, and generate an alert based on the analysis of the at least one obtained aircraft operational parameter.

Abstract: A method for en-route flight path optimization is disclosed. A plurality of alternate flight paths between an origin and a destination of the aircraft in flight is determined based on real-time weather data, air traffic conflict data, and air space constraint data. Further, flight time savings and fuel savings for each of the plurality of alternate flight paths with respect to an actual path is computed. Furthermore, an optimal flight path from the plurality of alternate flight paths is determined based on the computed flight time savings, fuel savings, and a priority for the flight time savings and the fuel savings.