Abstract: Embodiments of the present disclosure relate to a method and system for optimizing vehicle allocation in a transportation system. The method comprises receiving sensor values from a first set of vehicles of a plurality of vehicles. The method also comprises applying, using an AI model, an imputation technique on the sensor values to estimate missing sensor values corresponding to the second set of vehicles, and to generate a complete set of sensor values for the plurality of vehicles. Further, the method comprises determining an optimized vehicle plan for one or more routes of the transportation system based on the complete set of sensor values. The optimized vehicle plan comprises trip-wise plan of vehicles with sensors and sensor-less vehicles for each route. Lastly, the method comprises allocating the plurality of vehicles to the one or more route at least based on the optimized vehicle plan.

Abstract: According to an embodiment of the disclosure, a method may include generating one or more masked relevant images by masking-out irrelevant entities from plurality of the relevant images; generating, for each of the one or more target entities, a relative skeletal map using the one or more masked relevant images; generating, for the source image, a feature map comprising information corresponding to physical aspects of the source entities appearing in the source image, and aspects corresponding to a scene identified in the source image; generating an image reconstruction map, based on the feature map of the source image and at least one of the relative skeletal maps; generating, based on the image reconstruction map, a modified source image comprising the one or more target entities.

Abstract: A method and a system for classifying one or more hyperlinks in a document are provided. The method includes identifying the one or more hyperlinks in the document based on an analysis of text strings of the document. The method further includes analyzing surrounding text strings around each of the one or more hyperlinks and classifying, based on the analysis of the surrounding text strings around each of the one or more hyperlinks, the one or more hyperlinks into at least one category among a plurality of predetermined categories.

Abstract: This present disclosure provides a method for generating diagrammatic representation of an area. The method includes obtaining, by an electronic device (100), sensor data over a period of time of a plurality of locations of the area. Further, the method includes generating, by the electronic device (100), a heat map of the sensor data of each of the location of the area. Further, the method includes generating, by the electronic device (100), the diagrammatic representation of the area based on the heat map of the sensor data.

Abstract: According to an aspect, a radar system comprising a transmitter transmitting a radar signal, a receiver receiving a reflected signal that is a reflection of the radar signal from a plurality of objects, in that the receiver is configured generate a point cloud comprising plurality of points with each point representing a range, a velocity and a position information, a feature extension unit configured to generate a plurality of tracks from the point cloud with each track comprising a corresponding set of points and generating an extended feature set for each track, in that each track representing an object in the plurality of objects and a classifier classifying the plurality of tracks into a set of classes using a reference data derived from the range, the velocity, the position information and the extended features.

Abstract: Among other things, equipment is located at an intersection of a transportation network. The equipment includes an input to receive data from a sensor oriented to monitor ground transportation entities at or near the intersection. A wireless communication device sends to a device of one of the ground transportation entities, a warning about a dangerous situation at or near the intersection, there is a processor and a storage for instructions executable by the processor to perform actions including the following. A machine learning model is stored that can predict behavior of ground transportation entities at or near the intersection at a current time. The machine learning model is based on training data about previous motion and related behavior of ground transportation entities at or near the intersection.

Abstract: A system includes an array of sensors configured to capture data about an environment for vehicular traffic. The array of sensors is disposed at a non-vehicular location. The system also includes one or more computing devices that include one or more processors. The one or more processors are configured to process the captured data about the environment to detect one or more road users in the environment and/or to detect information about traffic signage in the environment. The one or more processors are also configured to transmit, in real-time, an indication of the one or more detected road users and/or the detected information about the traffic signage in the environment to a vehicle.

Abstract: A control system for a machine includes one or more component controllers for one or more components of the machine. The control system also includes a supervisory controller, connected to the one or more component controllers, and having at least one supervisory processor configured to perform operations comprising receiving supervisory system inputs, including at least one of a machine component status input, a key switch input, a directional input, or an operator presence input, from an operator of the machine, requesting and receiving, from each of the one or more component controllers, a status of the one or more components, and, upon receiving an indication that a status of a component, of the one or more components, is faulted, disabling the faulted component, and disabling any other components, of the one or more components, that require the faulted component for operation.

Abstract: Methods and systems for operating a voltage regulator are described. A integrated circuit can be configured to adjust at least one of a deadtime parameter and a drive strength parameter of a power stage based on at least one of an input voltage being provided to a power stage, a switch node voltage of the power stage, and an output current of the power stage. A controller of the power stage can be further configured to adjust a deadtime of the power stage based on adjustment of the deadtime parameter. The controller can be further configured to adjust a drive strength of the first driver and the second driver based on adjustment of the drive strength parameter.

Abstract: A computer system for controlling access to medical resources, the system comprising at least one processor configured to: provide at least one trained machine learning model which has been trained on a training data set comprising healthcare event associated data, the at least one trained machine learning model having an input for receiving at least one operating data set associated with a particular healthcare event and an output for generating at least one value associated with the particular healthcare event; provide the at least one operating data set to the trained model and to receive the at least one value; and in dependence upon the at least one value, generate an indication of an assignment of medical resources for a patient associated with the event.

Abstract: The present invention relates to a process for producing a recombinant protein in a cell culture medium. comprising culturing mammalian cells expressing the protein of interest in a production medium at suitable conditions: and supplementing the production medium with feed components in such quantity that the residual carbon to nitrogen ratio is controlled. The present invention further relates to a process for producing a recombinant protein in a cell culture medium, wherein recombinant protein of interest has increased acidic variants and/or acidic variants and reduced basic variants.

Abstract: A control system includes a controller that may determine whether a second speed limit, which is less than or equal to a first speed limit, is in effect for a segment of the route. The controller may switch one or more operational settings of a vehicle from the first speed limit to the second speed limit, and may operate the vehicle at the first speed limit outside of the segment of the route and operate the vehicle at or below the second speed limit while the vehicle is approaching or within the segment of the route.

Abstract: Various aspects include methods for managing communication links with different networks. A user equipment (UE) processor may start a first retry timer in a first network communication module in response to receiving a connection reject message from a first communication network, send a value of the first retry timer to a second network communication module, start a second retry timer in the second network communication module based on the value of the first retry timer, send a service request from the second network communication module to a second communication network, and send a connection success message from the second network communication module to the first network communication module upon establishing a communication link with the second communication network before the second retry timer expires. The first communication network may be a terrestrial cellular network and the second communication network may be a satellite communication network.

Abstract: According to an aspect, a method of determining two dimensional (2D) angle of arrival (AoA) in a radar system comprising determining one dimensional (1D) AoA to generate a first set of (AoA), selecting a set of valid 1D AoA angles from the first set AoA, and determining the 2D AoA from the set of valid 1D AoA. Wherein the 1D AoA is determined on a first set of data received over a first uniform linear antenna array arranged in the first axis and the 2D AoA is determined on a second set data received over the first and the second MIMO antenna array arranged in the second axis and the set of valid 1D AoA in the first axis. Wherein the second antenna array need not be orthogonal to the first linear antenna array.

Abstract: According to an aspect, a method of determining Doppler in a radar system comprising receiving a set of chirps, sampling in time the set of chirps to generate a set of non-uniform samples with one sample per chirp that is non-uniform in time in each chirp across the set of chirps, generating a first Doppler frequency from the set of non-uniform samples, generating a set of non-aliased Doppler frequencies for the first Doppler frequencies from a corresponding set of hypothesis, determining a first set of angles of arrival for every non-aliased Doppler frequency in the a set of non-aliased Doppler frequencies and selecting a first non-aliased Doppler frequency in the set of non-aliased Doppler frequencies that corresponds to the first angle of arrival with a minimum error in the a set of angles of arrival.

Abstract: Recommender Systems (RS) tend to recommend more popular items instead of the relevant long-tail items. Mitigating such popularity bias is crucial to ensure that less popular but relevant items are recommended. System described herein analyses popularity bias in session-based RS obtained via deep learning (DL) models. DL models trained on historical user-item interactions in session logs (having long-tailed item-click distributions) tend to amplify popularity bias. To understand source of this bias amplification, potential sources of bias at data-generation stage (user-item interactions captured as session logs) and model training stage are considered by the system for recommendation wherein popularity of item has causal effect on user-item interactions via conformity bias, and item ranking from models via biased training process due to class imbalance.

Abstract: A computer system for generating a quantitative value relating to a negative health outcome, the computer system comprising: a conversion module configured to receive multiple sets of data items associated with patients and each comprising a descriptor and the time at which that event impacted the patient. The conversion module generates a training data structure which comprises for each patient an array of selected features, each selected feature associated with a numerical value representing a score indicative of the relevance of that feature to the prediction of the negative health outcome, and a label indicating if the patient exhibits the negative health outcome; and a machine learning model which is trained using the training data structure so as to be operable to generate a quantitative value relating to a negative health outcome for a patient with at least some of the features.

Abstract: A method and system for performing blackstart functionality from renewable generation and battery energy storage systems are disclosed. A plant may include a microgrid that includes one or more customer loads and that may provide power to a utility grid. Blackstart may be performed to restore operations to part or all of the plant or to external loads such as microgrid customer loads or part of the utility grid. In practice, blackstart may be performed in order to restore operation to the one or more feeders in the plant, such as to the generation sources within the plant, to restore power to the plant auxiliary loads, customer loads in the microgrid, and to provide power to different sections of the grid when transitioning from shutdown mode of operation. In this way, the method and system may automatically transition from a shutdown mode of operation to an islanded mode of operation.

Abstract: A method and system for transitioning between grid-tied and islanded modes of operation are disclosed. A plant may include a microgrid that includes one or more customer loads and that may provide power to a utility grid. The plant may include clean energy sources, such as DC-coupled photovoltaics and battery systems, as well as other types of clean energy generation and storage technologies. In certain instances, the plant may transition from grid-tied (in which the plant receives or provides power to the utility grid) to islanded (where the plant is disconnected from and does not receive or provide power to the utility grid), and vice-versa. The method and system may automatically transition between grid-tied and islanded without interruption of power to the one or more customer loads.