Abstract: A system and method are disclosed for training a neural network to predict remaining battery capacity. Measured battery parameters are collected over time from a battery, including voltage, current, temperature, remaining voltage, and full charge voltage. The measured parameters are preprocessed to generate input feature vectors, including determining a rate of change of voltage over time. A training data set is generated comprising the input feature vectors and corresponding target output vectors indicating low battery, very low battery, and depleted battery states. A neural network comprising an input layer, at least one hidden layer, and an output layer is initialized and trained by iterative forward propagation, loss computation, and backpropagation-based weight and bias updates. Training is terminated upon satisfaction of a predefined tolerance or a maximum number of iterations. The trained neural network is stored for use in generating battery alarm indications during battery discharge.

Abstract: Aspects of the subject disclosure may include, for example, determining, in relation to a communication node, a neighboring node of a wireless network, wherein the neighboring node comprises a baseband processor in communication with a radio frequency (RF) subsystem. A determination is made regarding one of a spatial configuration, a hosting infrastructure configuration, or both, of the neighboring node. The spatial configuration includes one of a divided configuration, including geographically separated centralized and a distributed baseband units, and an undivided configuration including an undivided baseband unit. The hosting infrastructure configuration distinguishes a physical configuration having the baseband processor includes dedicated compute resources allocated to the node, from a virtual configuration having a virtual baseband processor hosted on shared compute resources.

Abstract: Facilitating network slicing information preservation in advanced networks in advanced networks is provided herein. Operations of a system include receiving, from second network equipment, network slice configuration information for a user device during a first handover of the user device from the second network equipment to the first network equipment. The network slice configuration information can include information indicative of a first network slice and a second network slice generated via a microservice of a network intelligent controller. Further the operations can include transmitting, to third network equipment, the network slice configuration information for the user device during a second handover of the user device from the first network equipment to the third network equipment.

Abstract: Aspects of the subject disclosure may include, for example, transmitting a first message that identifies a first plurality of capabilities supported by the device, based on the transmitting of the first message, obtaining a second message from a user equipment that identifies a second plurality of capabilities supported by the user equipment, wherein the second plurality of capabilities is a subset of the first plurality of capabilities, and provisioning a first communication service to the user equipment in accordance with at least one capability included in the second plurality of capabilities. Other embodiments are disclosed.

Abstract: Disclosed embodiments provide techniques for creating a smaller version of an original document. An ontology is defined, and a document type for an original document is determined, based on the ontology. Multiple key-value pairs (KVPs) are extracted from the original document based on the document type. Pages in the original document that include one or more KVPs are identified, and the smaller, condensed version includes the identified pages from the original document.

Abstract: Embodiments of the disclosure relate to electronically parsing a complicated table to extract data. Aspects include electronically parsing an electronic image to identify an irregular table. Aspects include selecting an anchor column in the irregular table, the anchor column comprising column data, where the anchor column is selected based at least in part on coordinates of the column data and on vertical distances of the column data, where rows are determined based on vertical relationships of the vertical distances of the column data of the anchor column. Aspects include separating the rows into snippets in accordance with the vertical relationships of the column data, where row data is extracted from the snippets. Aspects include generating a new data structure such that the row data is combined in the new data structure and causing an action to be performed in response to generating the new data structure.

Abstract: A method and a system for filling and sealing a liquid-filled hard capsule are provided. The method includes: separating a capsule body and a capsule cap, filling a material into the capsule body, and inflating an inert gas into the capsule cap, wherein the material at least includes a liquid; fitting the capsule cap and the capsule body obtained in step S1 to obtain a liquid-filled capsule; injecting a glue into a fitting gap, while applying pressure to the liquid-filled capsule, so that the glue fills the fitting gap using negative pressure, and then heating the fitting gap to implement sealing.

Abstract: Aspects of the subject disclosure may include, for example, analyzing data by applying AI modeling to the data where the analyzing includes analyzing network conditions at a SA network and an NSA network resulting in analyzed network conditions; predicting a better user experience for a communication session of an end user device based on the analyzed data resulting in a prediction; selecting one of the SA network or the NSA network for the end user device based on the prediction resulting in a selected network; determining a time period for the end user device to continue utilizing the selected network for future communication sessions; and providing an instruction to a network element that causes the end user device to connect to the selected network, where the end user device utilizes the selected network for the communication session and the future communication sessions during the time period. Other embodiments are disclosed.

Abstract: A system selects a network type for a UE to communicate with a network. The network type may be a classical radio access network (RAN) or a virtual RAN. The selection process may be device-driven, network-driven, or a combination. A network device may collect and analyze network performance data and UE processing capabilities to determine and reconfigure the optimal network type. The UE may gather data, receive network recommendations, and communicates its preference. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, communicatively coupling to a first communication device over an LTE mobile network, and determining a first handover to a first target base station, the first target base station is part of a 5G (or next generation) mobile network. Further embodiments can include determining that the first communication device is performing a first type of service resulting in a first determination, and preventing the first handover to the first target base station based on the first determination. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, obtaining data regarding one or more local networks, wherein the one or more local networks provide network connectivity for a user device, receiving policy information from an SMO system, and causing the data and the policy information to be provided to an AIC that is associated with one or more access networks, wherein the causing enables the AIC to determine whether to effect a handover for the user device from the one or more local networks to the one or more access networks. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, receiving a service request relating to a user device, identifying service delivery requirements for the service request, resulting in identified requirements, creating a resource slice based on the service delivery requirements, and providing data regarding the resource slice to a first intelligent controller and a second intelligent controller, wherein the first intelligent controller relates to one or more networks that are associated with a premises, wherein the premises comprises a residential premises or a commercial premises, wherein the second intelligent controller relates to the user device, and wherein the providing causes the first intelligent controller to manage use of resources in the one or more networks to facilitate traffic delivery for the service request and causes the second intelligent controller to manage use of resources in the user device to facilitate data processing for the service request. Other embodiments are disclosed.

Abstract: Aspects of the subject disclosure may include, for example, receiving a service request relating to a user device, identifying service delivery requirements for the service request, resulting in identified requirements, obtaining first information from a first intelligent controller regarding resources in network(s) that are associated with a premises, wherein the premises comprises a residential/commercial premises, obtaining second information from a second intelligent controller regarding resources in the user device, based on the identified requirements and the first and second information, selecting a first resource in the network(s) and a second resource in the user device, and facilitating service delivery for the user device by coordinating with the first intelligent controller to utilize the first resource for delivery of traffic associated with the service request and by coordinating with the second intelligent controller to utilize the second resource for processing relating to the traffic.

Abstract: Facilitating network slicing information preservation in advanced networks in advanced networks is provided herein. Operations of a system include receiving, from second network equipment, network slice configuration information for a user device during a first handover of the user device from the second network equipment to the first network equipment. The network slice configuration information can include information indicative of a first network slice and a second network slice generated via a microservice of a network intelligent controller. Further the operations can include transmitting, to third network equipment, the network slice configuration information for the user device during a second handover of the user device from the first network equipment to the third network equipment.

Abstract: Aspects of the subject disclosure may include, for example, obtaining first network performance data characterizing a wireless network, wherein the wireless network provides one or more users of a plurality of users access to a collection of servers that enable a plurality of services; obtaining second network performance data characterizing a wired network, wherein the wired network provides the one or more users access to the collection of servers that enable the plurality of services; obtaining first service performance data characterizing a first service of the plurality of services that are enabled by the collection of servers; obtaining first service requirements of the first service; and responsive to a first user of the one or more users indicating a preference to utilize the first service, selecting one of the wireless network or the wired network as a selected network for the first user, wherein the selecting of the selected network is based upon the first network performance data, the second networ

Abstract: Compositions and methods are described herein for treating subjects having hypercholesterolemia and/or cardiovascular disease.

Abstract: Systems and methods for detecting an occlusion in an infusion device are disclosed. One method includes generating, during an infusion session at predetermined intervals, a feature vector comprising an initial measurement of a physical force caused by fluid motion through an infusion device at the start of an infusion session, a current measurement of the physical force, a long term change in the measurement of the physical force, and a short term change in the measurement of the physical force. The feature vector is inputted, during the predetermined intervals, into a support vector machine (“SVM”) to output an indication of a presence or an absence of an occlusion in the infusion device. The SVM may be trained using reference data from reference infusion sessions having known consequences regarding the presence or the absence of an occlusion at various times during the reference infusion sessions.

Abstract: Aspects of the subject disclosure may include, for example, obtaining a measurement report from a communication device, the measurement report indicates a first mobile network resource of a first neighbor base station, and reporting the first mobile network resource of the first neighbor base station to an automatic neighbor relation (ANR) optimizer (ANR-o) xApplication running on a radio access network (RAN) intelligent controller (RIC). The ANR-o xApplication provides a first indication of a first group of mobile network resources of the first neighbor base station to the serving base station. Further embodiments can include receiving the first indication of the first group of mobile network resources associated with the first neighbor base station, and updating an ANR table associated with the serving base station with the first mobile network resource and the first group of mobile network resources associated with the first neighbor base station. Other embodiments are disclosed.