Abstract: An apparatus distributing communication load over a plurality of communication cells may select action centers from random cell reselection values, based on a standard deviation of an internet protocol (IP) throughout over the plurality of communication cells; input a first vector indicating a communication state of a communication system and a second vector indicating the standard deviation of the IP throughout of the plurality of communication cells, to a neural network to output a sum of the action centers and offsets as cell reselection parameters; and transmit the cell reselection parameters to the communication system to enable a base station of the communication system to perform a cell reselection based on the cell reselection parameters.

Abstract: A method includes obtaining at least one policy parameter of a neural network corresponding to a load balancing policy, receiving trajectories for each mobile device in a plurality of mobile devices of the wireless network, each trajectory corresponding to a sequence of states of a respective mobile device, wherein the sequence of states is generated based on a continuous interaction of an existing policy of the respective mobile device with the wireless network, estimating advantage functions for each mobile device in the plurality of mobile devices based on the trajectories for each respective mobile device, and updating the at least one policy parameter based on the estimated advantage functions such that the load balancing policy is determined based on states of each mobile device in the plurality of mobile devices.

Abstract: An ultrasound imaging system may acquire ultrasound data from a heart. The ultrasound data may be analyzed to on-invasively provide a value for cardiac pressure, such as left ventricular end diastolic pressure (LVEDP). In some examples, the ultrasound data may be acquired from B-mode images, Doppler images, and/or strain measurements. In some examples, the ultrasound data may be acquired across an entire cardiac cycle of the heart. In some examples, the ultrasound data may include strain measurements and/or volume measurements of the left atrium. In some examples, the ultrasound data may be analyzed by a correlation algorithm, such as a partial least squares model and/or a neural network.

Abstract: The present disclosure provides for methods, apparatuses, and non-transitory computer-readable storage media for load balancing traffic scenarios by a network device. In an embodiment, a method includes training a plurality of learning agents to load balance a respective plurality of traffic scenarios to obtain a plurality of control policies. The method further includes performing at least one clustering iteration. Each clustering iteration includes selecting a pair of control policies and merging the pair of control policies into a clustered control policy that replaces the pair of control policies. The method further includes determining to stop the performing of the at least one clustering iteration when a quantity of control policies remaining in the plurality of control policies meets a predetermined value. The method further includes deploying to each base station of a plurality of base stations a corresponding control policy from the plurality of control policies.

Abstract: Parameters for load balancing in a cellular communication system are determined. The cellular communication system performance is measured by key performance indicators (KPIs). A policy (artificial intelligence model) is obtained to optimize the cellular communication system performance with respect to the KPIs. The policy for determining parameters used for load balancing the cellular communication system is obtained using meta multi-objective reinforcement learning (meta MORL). A distilled policy may be obtained to initialize the meta MORL determination. Various loss functions may be used to obtain the distilled policy.

Abstract: Several policies are trained for determining communication parameters used by mobile devices in selecting a cell of a first communication network to operate on. The several policies form a policy bank. By adjusting the communication parameters, load balancing among cells of the first communication network is achieved. A policy selector is trained so that a target communication network, different than the first communication network, can be load balanced. The policy selector selects a policy from the policy bank for the target communication network. The target communication network applies the policy and the load is balanced on the target communication network. Improved load balancing leads to a reduction of the number of base stations needed in the target communication network.

Abstract: Described herein is a computer implemented method. The method comprises executing an application defining a feature flag, the execution of the application being associated with a user identifier. The method further comprises determining if version data associated with the feature flag and user identifier is stored in a local data store. In response determining that the version data associated with the feature flag and user identifier is stored in the local data store an evaluation request is generated that includes the version data and the user identifier. The evaluation request is then communicated to a feature flag evaluation service.

Abstract: Described herein is a computer implemented method. The method comprises executing an application defining a feature flag, the execution of the application being associated with a user identifier. The method further comprises determining if version data associated with the feature flag and user identifier is stored in a local data store. In response determining that the version data associated with the feature flag and user identifier is stored in the local data store an evaluation request is generated that includes the version data and the user identifier. The evaluation request is then communicated to a feature flag evaluation service.

Abstract: An apparatus distributing communication load over a plurality of communication cells may select action centers from random cell reselection values, based on a standard deviation of an internet protocol (IP) throughout over the plurality of communication cells; input a first vector indicating a communication state of a communication system and a second vector indicating the standard deviation of the IP throughout of the plurality of communication cells, to a neural network to output a sum of the action centers and offsets as cell reselection parameters; and transmit the cell reselection parameters to the communication system to enable a base station of the communication system to perform a cell reselection based on the cell reselection parameters.

Abstract: The invention provides a method for assessing cardiac valve regurgitation. The method includes obtaining 4D ultrasound data of a region of interest, wherein the region of interest comprises a cardiac valve. The 4D ultrasound data comprises a time sequence of 3D ultrasound images comprising B-mode ultrasound data and color Doppler ultrasound data. Image stabilization is performed on the images of the time sequence of 3D ultrasound images and a dynamic jet is then segmented from the time sequence of stabilized 3D ultrasound images. A dynamic surface model is fit to the valve in the time sequence of stabilized 3D ultrasound images based on the segmented jet. The method further includes identifying a dynamic regurgitant orifice based on the applied surface model and the time sequence of stabilized 3D ultrasound images and fitting a flow convergence model to the time sequence of stabilized 3D ultrasound images based on the identified dynamic regurgitant orifice.

Abstract: In some embodiments, a system may evaluate third-party data for an enterprise (e.g., a potential risk enterprise such as an insurance company), based on information about potential customers received via a first-party data source and additional information about the potential customers from sources other than the enterprise received via a third-party data source. A model factory may provide information about at least one enterprise predictive model, and a third-party data evaluation platform may analyze the additional information to determine an impact on the enterprise predictive model. The third-party data evaluation platform may then output an indication of a result of said analysis to a database of findings (e.g., for use by data scientists).

Abstract: An isolation mechanism for isolating a submerged pump in a storage vessel, where the isolation mechanism comprises a primary valve member and a secondary valve member, which are both biased in a fail-closed position. The isolation mechanism allows for redundancy for safety and reliability, and can be operated externally of the storage vessel. Furthermore, the isolation mechanism comprises venting and purging devices for safe operation of removal and installation of the pump in the storage vessel.

Abstract: The present disclosure relates to the technical field of supplying vehicles with energy, and discloses a supply station and a method capable of charging electricity and filling with hydrogen gas simultaneously or separately, the supply station comprising: a power supply unit, a storage battery system, a device capable of converting electric power into hydrogen gas, a hydrogen gas storage system, a device capable of converting hydrogen gas into electric power, a charger and a hydrogen dispenser; the power supply unit is connected with the storage battery system to deliver power; the storage battery system is connected with the device capable of converting electric power into hydrogen gas so as to convert the electric power provided by the storage battery system into hydrogen gas; the device capable of converting electric power into hydrogen gas is connected with the hydrogen gas storage system to store hydrogen gas in the hydrogen gas storage system; the hydrogen gas storage system is connected with the device

Abstract: A method for dispensing liquefied fuel, the method including: providing a non-petroleum fuel as a liquefied fuel to a storage tank; increasing pressure of the liquefied fuel to a target pressure using a pump disposed within the storage tank, where a first portion of the liquefied fuel is bypassed around or at least partially around a heat exchanger, and a second portion of the liquefied fuel is discharged to the heat exchanger, where the heat exchanger is configured to warm the second portion of the liquefied fuel. A dispenser is provided that incorporates a control system that allows coordinated fueling of one or more vehicles simultaneously, where the heat exchanger uses only the fuel itself without external refrigeration to manage final dispensing temperature and the fueling station does not include a storage subsystem disposed between the pump and the dispenser.

Abstract: A fluid bypass method for controlling the temperature of a non-petroleum fuel, the fluid bypass method includes: providing a fuel at a pressure sufficient to effect a desired flow rate to a vehicle, the fuel being at a liquid or substantially supercritical thermodynamic state requiring further heat addition in a vaporizer; and diverting a bypass stream with partial or no vaporization to a heat exchanger as a cold fluid on a cold side of the heat exchanger. The method further includes providing a remainder stream of the fuel to the vaporizer; mixing the remainder stream outflowed from the vaporizer with the cold fluid outflowed from the cold side of the heat exchanger to form a combined fuel stream; and providing the combined fuel stream to the heat exchanger as a warm fluid on a warm side of the heat exchanger.

Abstract: A communication protocol overlay that governs wireless data communications between an access point and subscribers. The communication protocol overlay includes a repeating pattern of superframes, each superframe including frames. Each frame includes a beacon emitted by an access point in a downlink communication to the subscribers at a beginning of the frame. Each frame further includes communication slots following the beacon. Each of the communication slots is uniquely assigned to one of the subscribers, permitting the subscriber to perform an uplink communication to the access point, within the communication slot. The beacon is precisely timed, and each of the communication slots follows the beacon with a specified temporal offset. A single superframe of the repeating pattern of superframes serves all subscribers by providing at least one communication slot to each of the subscribers.

Abstract: A communication protocol overlay that governs wireless data communications between an access point and subscribers. The communication protocol overlay includes a repeating pattern of superframes, each superframe including frames. Each frame includes a beacon emitted by an access point in a downlink communication to the subscribers at a beginning of the frame. Each frame further includes communication slots following the beacon. Each of the communication slots is uniquely assigned to one of the subscribers, permitting the subscriber to perform an uplink communication to the access point, within the communication slot. The beacon is precisely timed, and each of the communication slots follows the beacon with a specified temporal offset. A single superframe of the repeating pattern of superframes serves all subscribers by providing at least one communication slot to each of the subscribers.

Abstract: A burner apparatus (10) includes a fluid-based flame stabilizer for discharging a stabilized flame therefrom, a burner tile (44), and fuel lances associated with the burner tile. Each of the fuel lances has a discharge nozzle (40). A Coanda feature (34) having a Coanda surface directs a portion of the stabilized flame from the passage defined by the burner tile at the discharge end of a primary flow passage (32) toward at least one first fuel lance of the plurality of fuel lances to cross light the at least one first fuel lance. In another embodiment, a method of combustion includes supplying a first gaseous fuel to fuel lances of a burner apparatus and igniting and sustaining combustion of a gaseous fuel by cross lighting at the discharge nozzles of the fuel lances by flow from the fluid-based flame stabilizer along a Coanda surface of a Coanda feature toward the discharge nozzles.

Abstract: An isolation mechanism for isolating a submerged pump in a storage vessel, where the isolation mechanism comprises a primary valve member and a secondary valve member, which are both biased in a fail-closed position. The isolation mechanism allows for redundancy for safety and reliability, and can be operated externally of the storage vessel. Furthermore, the isolation mechanism comprises venting and purging devices for safe operation of removal and installation of the pump in the storage vessel.

Abstract: A fluid bypass method for controlling the temperature of a non-petroleum fuel, the fluid bypass method includes: providing a fuel at a pressure sufficient to effect a desired flow rate to a vehicle, the fuel being at a liquid or substantially supercritical thermodynamic state requiring further heat addition in a vaporizer; and diverting a bypass stream with partial or no vaporization to a heat exchanger as a cold fluid on a cold side of the heat exchanger. The method further includes providing a remainder stream of the fuel to the vaporizer; mixing the remainder stream outflowed from the vaporizer with the cold fluid outflowed from the cold side of the heat exchanger to form a combined fuel stream; and providing the combined fuel stream to the heat exchanger as a warm fluid on a warm side of the heat exchanger.