Abstract: Certain aspects of the present disclosure provide techniques for determining a topology of an electric vehicle supply equipment (EVSE) network. An example method includes obtaining, for a first time period, for each of a plurality of pieces of equipment of the EVSE network, a respective magnitude of a respective current phasor, wherein for each of one or more pieces of equipment of the plurality of pieces of equipment, a respective phase angle of the respective current phasor is unknown; and determining, based on at least the respective magnitude of the respective current phasor for each of at least one piece of equipment of the one or more pieces of equipment, a respective subset of lines of the EVSE network to which the respective piece of equipment is coupled.

Abstract: Provided herein are techniques for managing charging stations with diverse communication capabilities. A system for EVSE management may include a first communication controller in communication with a first network to communicatively couple to a central control system, a second communication controller in communication with a second network to communicatively couple to a first EVSE charger, and a third communication controller in communication with a third network to communicatively couple to a second EVSE charger.

Abstract: Certain aspects of the present disclosure provide techniques electric vehicle charging management. In one example, a method includes: detecting a connection between an electric vehicle supply equipment and an electric vehicle; receiving image data depicting an electric vehicle charging scene; determining one or more candidate vehicles in the image data; for each respective candidate vehicle of the one or more candidate vehicles in the image data, determining one or more vehicle characteristics associated with the respective candidate vehicle; associating one candidate vehicle of the one or more candidate vehicles with the electric vehicle based on one or more vehicle characteristics associated with the one candidate vehicle; determining if a user account is associated with the one candidate vehicle associated with the electric vehicle; and determining a charging authorization decision for the electric vehicle.

Abstract: Certain aspects of the present disclosure provide techniques for concurrently performing inferences using a machine learning model and optimizing parameters used in executing the machine learning model. An example method generally includes receiving a request to perform inferences on a data set using the machine learning model and performance metric targets for performance of the inferences. At least a first inference is performed on the data set using the machine learning model to meet a latency specified for generation of the first inference from receipt of the request. While performing the at least the first inference, operational parameters resulting in inference performance approaching the performance metric targets are identified based on the machine learning model and operational properties of the computing device. The identified operational parameters are applied to performance of subsequent inferences using the machine learning model.

Abstract: Certain aspects of the present disclosure provide techniques for charging a plurality of electric assets. One embodiment of a system includes EVSE for charging an EV, the EVSE including a three-phase transformer for sending energy to the EV and an edge environment that is coupled to the EVSE. The edge environment may include logic that causes the system to receive configuration information associated with the EVSE, where the configuration information includes a phase assignment for the EVSE, determine whether the phase assignment is labeled as unknown, where the phase assignment of unknown was applied in response to a determination that a previous phase assignment was invalid or missing, and generate an optimization problem for the EVSE. In some embodiments, the logic may cause the system to solve the optimization problem to generate a trajectory for the three-phase transformer and cause implementation of the trajectory on the EVSE.

Abstract: Certain aspects of the present disclosure provide techniques for concurrently performing inferences using a machine learning model and optimizing parameters used in executing the machine learning model. An example method generally includes receiving a request to perform inferences on a data set using the machine learning model and performance metric targets for performance of the inferences. At least a first inference is performed on the data set using the machine learning model to meet a latency specified for generation of the first inference from receipt of the request. While performing the at least the first inference, operational parameters resulting in inference performance approaching the performance metric targets are identified based on the machine learning model and operational properties of the computing device. The identified operational parameters are applied to performance of subsequent inferences using the machine learning model.

Abstract: A method includes accessing a first dataset including aerial imagery data and infrared data, accessing a second dataset including property boundary data, and identifying property boundaries associated with a geographic area. A plurality of models is applied to the datasets to identify and compute information of interest. Based on the first dataset and constrained by the property boundaries, a building detection model can be applied to identify a building, and a vegetation detection model can be applied to identify one or more areas of vegetation. An estimated distance can be determined between each of the areas of vegetation and the building as separation data, which can be compared to a defensible space guideline to determine a defensible space adherence score. A wildfire risk map can be generated, including the defensible space adherence score associated with the geographic area.

Abstract: The present disclosure provides a generative modeling framework for generating highly realistic and privacy preserving synthetic records for heterogenous time-series data, such as electronic health record data, financial data, etc. The generative modeling framework is based on a two-stage model that includes sequential encoder-decoder networks and generative adversarial networks (GANs).

Abstract: Certain aspects of the present disclosure provide techniques for concurrently performing inferences using a machine learning model and optimizing parameters used in executing the machine learning model. An example method generally includes receiving a request to perform inferences on a data set using the machine learning model and performance metric targets for performance of the inferences. At least a first inference is performed on the data set using the machine learning model to meet a latency specified for generation of the first inference from receipt of the request. While performing the at least the first inference, operational parameters resulting in inference performance approaching the performance metric targets are identified based on the machine learning model and operational properties of the computing device. The identified operational parameters are applied to performance of subsequent inferences using the machine learning model.

Abstract: Certain aspects of the present disclosure provide techniques for concurrently performing inferences using a machine learning model and optimizing parameters used in executing the machine learning model. An example method generally includes receiving a request to perform inferences on a data set using the machine learning model and performance metric targets for performance of the inferences. At least a first inference is performed on the data set using the machine learning model to meet a latency specified for generation of the first inference from receipt of the request. While performing the at least the first inference, operational parameters resulting in inference performance approaching the performance metric targets are identified based on the machine learning model and operational properties of the computing device. The identified operational parameters are applied to performance of subsequent inferences using the machine learning model.

Abstract: A method includes accessing a first dataset including aerial imagery data and infrared data, accessing a second dataset including property boundary data, and identifying property boundaries associated with a geographic area. A plurality of models is applied to the datasets to identify and compute information of interest. Based on the first dataset and constrained by the property boundaries, a building detection model can be applied to identify a building, and a vegetation detection model can be applied to identify one or more areas of vegetation. An estimated distance can be determined between each of the areas of vegetation and the building as separation data, which can be compared to a defensible space guideline to determine a defensible space adherence score. A wildfire risk map can be generated, including the defensible space adherence score associated with the geographic area.

Abstract: A system includes a processing device and memory device storing instructions that result in accessing a first dataset including aerial imagery data and infrared data, accessing a second dataset including property boundary data, and identifying property boundaries associated with a geographic area. A plurality of models is applied to the datasets to identify and compute information of interest. Based on the first dataset and constrained by the property boundaries, a building detection model can be applied to identify a building, and a vegetation detection model can be applied to identify one or more areas of vegetation. An estimated distance can be determined between each of the areas of vegetation and the building as separation data, which can be compared to a defensible space guideline to determine a defensible space adherence score. A wildfire risk map can be generated, including the defensible space adherence score associated with the geographic area.

Abstract: A method includes receiving an input histology image, processing, using a cell classification model, the input histology image to generate one or more lymphocyte density maps within the input histology image, and performing morphological image processing on the one or more lymphocyte density maps to identify one or more TLS regions within the input histology image. Each TLS region is represented by a respective cluster of lymphocyte cells. For each corresponding TLS region of the one or more TLS regions identified in the input histology image, the method also includes extracting, from the respective cluster of lymphocyte cells, a respective set of TLS features, and processing, using a TLS classification model, the respective set of TLS features to classify the corresponding TLS region as one of a first TLS maturation state, a second TLS maturation state, or a third TLS maturation state.

Abstract: Certain aspects of the present disclosure provide techniques electric vehicle charging management. In one example, a method includes: detecting a connection between an electric vehicle supply equipment and an electric vehicle; receiving image data depicting an electric vehicle charging scene; determining one or more candidate vehicles in the image data; for each respective candidate vehicle of the one or more candidate vehicles in the image data, determining one or more vehicle characteristics associated with the respective candidate vehicle; associating one candidate vehicle of the one or more candidate vehicles with the electric vehicle based on one or more vehicle characteristics associated with the one candidate vehicle; determining if a user account is associated with the one candidate vehicle associated with the electric vehicle; and determining a charging authorization decision for the electric vehicle.

Abstract: This invention is directed to a compound of formula (I): wherein R1, R2 and R3 are as defined herein, a pharmaceutical composition comprising the compound, intermediates and processes for making said compounds, and the use of the compound to treat allergic and/or inflammatory disorders, particularly disorders such as allergic rhinitis, asthma, chronic obstructive pulmonary disease (COPD) and age-related macular degeneration (AMD).

Abstract: The present disclosure provides, in an aspect, computer-implemented method for generating data associated with a vehicle event, the method including obtaining vehicle event data for a vehicle event associated with a vehicle; identifying a parameter associated with the vehicle event; emulating the parameter based on simulating the vehicle event with the vehicle event data and a model of the parameter, and extrapolating parameter data based on the simulated vehicle event.

Abstract: A system includes a processing device and memory device storing instructions that result in accessing a first dataset including aerial imagery data and infrared data, accessing a second dataset including property boundary data, and identifying property boundaries associated with a geographic area. A plurality of models is applied to the datasets to identify and compute information of interest. Based on the first dataset and constrained by the property boundaries, a building detection model can be applied to identify a building, and a vegetation detection model can be applied to identify one or more areas of vegetation. An estimated distance can be determined between each of the areas of vegetation and the building as separation data, which can be compared to a defensible space guideline to determine a defensible space adherence score. A wildfire risk map can be generated, including the defensible space adherence score associated with the geographic area.

Abstract: A method includes accessing a first dataset including aerial imagery data, accessing a second dataset including property boundary data, and identifying property boundaries associated with a geographic area. A plurality of artificial-intelligence (AI) models are applied to the datasets to identify and compute information of interest. Based on the first dataset and constrained by the property boundaries, a building detection model can be applied to identify a building footprint, and a tree detection model can be applied to identify one or more trees. An estimated distance can be determined between each of the trees and a nearest portion of the building footprint as separation data, which can be compared to a defensible space guideline to determine a defensible space adherence score. A wildfire risk map can be generated, including the defensible space adherence score associated with the geographic area.

Abstract: This invention is directed to a compound of formula (1): wherein R1, R2 and R3 are as defined herein, a pharmaceutical composition comprising the compound, intermediates and processes for making said compounds, and the use of the compound to treat allergic and/or inflammatory disorders, particularly disorders such as allergic rhinitis, asthma, chronic obstructive pulmonary disease (COPD) and age-related macular degeneration (AMD).

Abstract: A remote surveillance apparatus and method comprising a camera coupled to a support structure and configured to capture video data and transmit the captured video data, a router bound to a public internet protocol (IP) address of a data center computing device external to the remote surveillance apparatus using a virtual private network (VPN), the router being configured to receive the captured video data, and wirelessly retransmit the captured video data, via a modem, to a requesting computing device external to the remote surveillance apparatus in response to a request originating at the requesting computing device that is addressed to the public IP address of the data center computing device and subsequently directed to the router by the data center computing device.