Abstract: In an example, a method may include obtaining anomaly characteristics associated with an anomaly in a transmission medium in an optical transmission system. The anomaly may cause a degradation in one or more signal characteristics of an optical signal traversing the transmission medium. Based on the anomaly characteristics, the method may also include adjusting a first output power of a first optical amplifier that may be disposed at an input end of the transmission medium. Alternatively, or additionally, based on the anomaly characteristics, the method may also include adjusting a second output power of a second optical amplifier that may be disposed at an output end of the transmission medium.

Abstract: A method may include obtaining an image of a scene from a first perspective, the image including an object, and detecting the object in the image using a machine learning process, where the object may be representative of a known shape with at least four vertices at a first set of points. The method may also include automatically predicting a second set of points corresponding to the at least four vertices of the object in a second perspective of the scene based on the known shape of the object. The method may additionally include constructing, without user input, a transformation matrix to transform a given image from the first perspective to the second perspective based on the first set of points and the second set of points.

Abstract: A method may include obtaining a first image of a first view. The first illustrated by the first image may be defined by one or more viewing parameters. The method may also include acquiring, from a machine learning system, a location of an object within the first image, calculating a relative position of the object within the first image using the location of the object within the first image, and determining whether the relative position of the object satisfies a condition. In response to the relative position of the object not satisfying the condition, at least one of the viewing parameters may be adjusted based on the relative position of the object and the condition. The method may further include obtaining a second image of a second view. The second view illustrated by the second image may be defined by the adjusted at least one of the viewing parameters.

Abstract: A method may include directing transmission of a first optical noise signal along a frequency channel of an optical network at a first power level. The first optical noise signal may include a notch at a frequency in the frequency channel. The method may also include while transmission of the first optical noise signal occurs along the frequency channel, obtaining a measurement of a first noise level at the frequency and obtaining a measurement of a second noise level at the frequency. The frequency channel may include a second power level when the measurement of the second noise level is obtained and the second power level may be different than the first power level. The method may further include estimating a noise level of an optical data signal transmitted along the frequency channel based on the first noise level and the second noise level.

Abstract: A method may include directing transmission of a first optical noise signal along a frequency channel of an optical network at a first power level. The first optical noise signal may include a notch at a frequency in the frequency channel. The method may also include while transmission of the first optical noise signal occurs along the frequency channel, obtaining a measurement of a first noise level at the frequency and obtaining a measurement of a second noise level at the frequency. The frequency channel may include a second power level when the measurement of the second noise level is obtained and the second power level may be different than the first power level. The method may further include estimating a noise level of an optical data signal transmitted along the frequency channel based on the first noise level and the second noise level.

Abstract: Systems and methods including identifying a physical intelligent moving object (IMO), the physical IMO associated with a current location and a service request; creating, from a digital representation template that is based on the service request, a digital representation instance of the physical IMO in a particular edge cloud of a distributed cloud computing environment that is closest to the current location of the physical IMO; in response to creating the digital representation instance, establishing a network connection between the digital representation and the physical IMO using the particular edge cloud; detecting a movement of the physical IMO from coverage of the particular edge cloud; in response to detecting the movement of the physical IMO: identifying a target edge cloud of the distributed cloud computing environment for coverage of the physical IMO; and establishing a network connection between the digital representation and the physical IMO using the target edge cloud.

Abstract: A method may include sending a first machine learning model to one or more optical systems in which the first machine learning model is configured to predict span losses in the optical systems. Each respective optical system may be configured to identify the span losses associated with the respective optical system and locally train the first machine learning model according to the respective identified span losses to obtain a respective local first machine learning model that includes one or more respective local model parameters. The method may include obtaining the respective local model parameters from each respective optical system without obtaining the corresponding respective locally trained first machine learning model. The method may also include generating a second machine learning model based on the obtained local model parameters. The second machine learning model may be used to predict occurrences of span losses corresponding to a given optical system.

Abstract: Operations may include obtaining lists of inter-Network-Element connections (inter-NE connections) between connection points of different network elements included in a network and obtaining lists of internal connections of the network elements included in the list of inter-NE connections. The operations may also include generating, based on the lists of inter-NE connections and the lists of internal connections, a global list of connection points that correspond to the inter-NE connections and the internal connections. Moreover, the operations may include generating, based on the global list of connection points, a plurality of upstream connection chains and a plurality of downstream connection chains with respect to the internal connections. In addition, the operations may include generating a list of end-to-end circuits by combining the respective upstream connection chains and the respective downstream connection chains of each respective internal connection.

Abstract: An example method may include obtaining network information of a network and determining a second path from a first node of multiple nodes to a second node of the multiple nodes. The network information may include a network topology that may include the multiple nodes and multiple links connecting the multiple nodes. The multiple links may include a first routing metric and a second routing metric. The network information may also include multiple first paths from each node of the multiple nodes to all other nodes of the multiple nodes along the multiple links. The multiple first paths may be determined based on the first routing metric. The determining the second path may include selecting path segments for the second path along the multiple links based on the path segments being included in the multiple first paths based on the second routing metric of the multiple links included in the path segments.

Abstract: Systems and methods for identifying physical intelligent moving objects (IMOs); creating, for a first subset of the physical IMOs, digital representations in edge clouds of a distributed cloud computing environment, each digital representation representative of a physical IMO of the first subset of the physical IMOs; generating a cooperative network computing (CNC) platform that includes the digital representations of the first subset of the physical IMOs, each digital representation functioning as a CNC entity in the CNC platform for the corresponding physical IMO; identifying a CNC task of a first physical IMO of the plurality of physical IMOs; and performing, by a first digital representation of the representations that corresponds to the first physical IMO, the CNC task in the CNC platform, including accessing data associated with a second digital representation of the digital representations in the CNC platform to perform the CNC task at the first digital representation.

Abstract: An example method may include obtaining multiple symbols each associated with a different state in a quadrature amplitude modulation scheme used for transmission of a data signal. The method may further include determining a sequence of symbols of the multiple symbols for a first portion of the data signal. The determining may include selecting an index value from multiple index values for the first portion of the data signal. The determining may also include obtaining energy states of multiple sequences of the symbols using the energy levels of the symbols. The determining may further include obtaining a relationship between the energy levels of the symbols, the energy states of the multiple sequences of the symbols, and the multiple index values. The determining may further include selecting the sequence of symbols based on the relationship and the index value for the first portion of the data signal.

Abstract: A method may include obtaining an image of a scene from a first perspective, the image including an object, and detecting the object in the image using a machine learning process, where the object may be representative of a known shape with at least four vertices at a first set of points. The method may also include automatically predicting a second set of points corresponding to the at least four vertices of the object in a second perspective of the scene based on the known shape of the object. The method may additionally include constructing, without user input, a transformation matrix to transform a given image from the first perspective to the second perspective based on the first set of points and the second set of points.

Abstract: An example method may include obtaining network information of a network and determining a second path from a first node of multiple nodes to a second node of the multiple nodes. The network information may include a network topology that may include the multiple nodes and multiple links connecting the multiple nodes. The multiple links may include a first routing metric and a second routing metric. The network information may also include multiple first paths from each node of the multiple nodes to all other nodes of the multiple nodes along the multiple links. The multiple first paths may be determined based on the first routing metric. The determining the second path may include selecting path segments for the second path along the multiple links based on the path segments being included in the multiple first paths based on the second routing metric of the multiple links included in the path segments.

Abstract: Systems and methods for provisioning real-time three-dimensional maps, including: at a first processing stage: updating a three-dimensional map of an environment based on received point cloud data; extracting three-dimensional proposals of objects of the environment; projecting the three-dimensional proposals onto a two-dimensional image of the environment; generating two-dimensional proposals of the objects of the environment; at a second processing stage: detecting the objects of the environment from the two-dimensional image of the environment; generating two-dimensional bounding boxes of the objects of the environment; matching the two-dimensional bounding box with a particular two-dimensional proposal of the two-dimensional proposals; and labeling, for each two-dimensional proposal that is matched to a two-dimensional bounding box, the three-dimensional proposal corresponding to the two-dimensional proposal with semantic information associated with the two-dimensional bounding box that is matched to the

Abstract: Disclosed methods for network modernization include obtaining a list of end-to-end circuits carried in a circuit-switched network, calculating, for each circuit, an early retirement credit (ERC) score and a circuit load factor (CLF) score, selecting, dependent on the ERC and CLF scores, a circuit to migrate to a new network, adding the selected circuit to a circuit migration sequence, and removing the circuit from the list. The ERC score represents the number of circuit-switching units on which no circuits would be carried and that would remain in the network following its removal. The CLF score represents an average number of circuits that would be carried on each circuit-switching unit currently traversed by the circuit following its removal. When two circuits have the highest ERC score, the circuit with the lowest CLF score is selected for migration. The method is repeated until the list is empty.

Abstract: Operations may include obtaining lists of inter-Network-Element connections (inter-NE connections) between connection points of different network elements included in a network and obtaining lists of internal connections of the network elements included in the list of inter-NE connections. The operations may also include generating, based on the lists of inter-NE connections and the lists of internal connections, a global list of connection points that correspond to the inter-NE connections and the internal connections. Moreover, the operations may include generating, based on the global list of connection points, a plurality of upstream connection chains and a plurality of downstream connection chains with respect to the internal connections. In addition, the operations may include generating a list of end-to-end circuits by combining the respective upstream connection chains and the respective downstream connection chains of each respective internal connection.

Abstract: Systems and methods for allocating edge computing resources may receive a predicted user route defining multiple wireless access points available along the route at respective time points and an assured delay constraint, determine, for each wireless access point, datacenters in the network meeting the assured delay constraint when accessed through the wireless access point, and construct an auxiliary graph dependent on the predicted user route and the determined datacenters. Each determined datacenter is represented by at least one node in the graph and each path in the graph defines a sequence of datacenters and a corresponding sequence of wireless access points through which they are accessible. A lowest cost path in the graph is determined and the sequences of datacenters and wireless access points defined by the lowest cost path are provided to a resource orchestrator that allocates edge computing resources for a mobile user traversing the predicted user route.

Abstract: Disclosed methods for network modernization include obtaining a list of end-to-end circuits carried in a circuit-switched network, calculating, for each circuit, an early retirement credit (ERC) score and a circuit load factor (CLF) score, selecting, dependent on the ERC and CLF scores, a circuit to migrate to a new network, adding the selected circuit to a circuit migration sequence, and removing the circuit from the list. The ERC score represents the number of circuit-switching units on which no circuits would be carried and that would remain in the network following its removal. The CLF score represents an average number of circuits that would be carried on each circuit-switching unit currently traversed by the circuit following its removal. When two circuits have the highest ERC score, the circuit with the lowest CLF score is selected for migration. The method is repeated until the list is empty.

Abstract: Systems and methods for constellation shaping using low rate loss bit-level distribution matchers include receiving blocks of input bits and, for each input block of a predetermined size, assigning a respective codeword of a predetermined output block size. The number of bits of a given bit value in the codeword is dependent on a predetermined target probability distribution. A one-to-one mapping exists between each possible combination of input bits and a codeword for input blocks containing the combination. Some codewords include a number of bits having the given bit value that is different than the predetermined target probability distribution, but an average number of bits having the given bit value in the available codewords meets the predetermined target probability distribution. The disclosed methods result in more available codewords and a lower rate loss than in bit-level distribution matchers with a constant modulus, while achieving similar shaping.

Abstract: A method may include publishing metadata to a blockchain, the metadata describing a training task associated with a global machine-learning model and computational resource requirements for performing the training task. The method may include receiving a request to participate in training the global machine-learning model from one or more clients based on a relevance of a respective local dataset of each of the clients to the training task and a suitability of the clients to the computational resource requirements for performing the training task. The method may include obtaining local model updates in which each respective local model corresponds to a respective client and each respective local model update is generated based on training the global machine-learning model with each of the local datasets. The method may include aggregating the plurality of local model updates and generating an updated global machine-learning model based on the aggregated local model update.