Abstract: A method and system control a water distribution network. A database is maintained of prior states based on a residential water demand, a tank level, and an energy tariff. A current state of the water distribution network is determined. Rewards are determined and include a tank level constraint, an energy cost, and a toggle count. A query based model is used to determine a set of control points used to control a first prior state. An RL agent is trained based on the prior states and rewards. The RL agent determines a control setpoint (that changes the pump speed) that maintains the tank level, minimizes the energy cost, and complies with the toggle count. The RL agent determines time slots and selects one of the time slots. Hybrid setpoints are generated to control the water distribution network within the selected time slot.

Abstract: The present disclosure provides fusion proteins with a multifunctional biologic design for programmed target engagement. In certain embodiments, the fusion proteins described herein provide for concurrent T cell and target antigen engagement and immune checkpoint targeting.

Abstract: A method for generating fraud and approval rules for a decision engine for detecting fraud in electronic transactions includes: receiving transaction data for a plurality of electronic transactions, the transaction data including a fraud determination and data values for the respective electronic transaction; applying a first rule of a plurality of rules to the electronic transactions to identify a first subset of transactions that satisfy the first rule and include a fraud determination indicative of fraud; filtering the first subset of transactions out of the plurality of electronic transactions; repeating the application step and filtering step using additional rules of the plurality of rules until a threshold criteria is met; and generating a rule order for the first rule and the additional rules based on at least a size of the subset of transactions identified using the respective rule.

Abstract: The present disclosure relates to a system and computer-implemented method for character recognition in a payment card. The method includes receiving an image of a payment card and one or more details associated with the payment card. Further, a derivative of the image is determined based on the one or more details and a horizontal sum of pixel values is determined for a plurality of rows in the image. Furthermore, one or more Regions of Interest (ROIs) are identified in the image by comparing the horizontal sum of pixel values with a predefined first threshold. Subsequently, one or more characters in the one or more ROIs are extracted using one or more peak values in a histogram of the one or more ROIs. Finally, each of the one or more characters extracted from the one or more ROIs is recognized using a trained Artificial Intelligence technique.

Abstract: A system and method of managing a network that includes assets are described. The method includes modeling the network as a directed graph with each of the assets represented as a node and determining alternative paths to each node from each available corresponding source of the node. The method also includes computing upstream robustness of each node, computing upstream robustness of the network, and computing downstream criticality of each node. Managing the network and each asset of the network is based on the upstream robustness and the downstream criticality of each node.

Abstract: A system and method for homomorphic encryption in a healthcare network environment is provided and includes receiving digital data over the healthcare network at a data custodian server in a plurality of formats from various data sources, encrypting the data according to a homomorphic encryption scheme, receiving a query at the data custodian server from a data consumer device concerning a portion of the encrypted data, initiating a secure homomorphic work session between the data custodian server and the data consumer device, generating a homomorphic work space associated with the homomorphic work session, compiling, by the data custodian server, a results set satisfying the query, loading the results set into the homomorphic work space, and building an application programming interface (API) compatible with the results set, the API facilitating encrypted analysis on the results set in the homomorphic work space.

Abstract: A bead exerciser system for an automated wheel assembly may include a center lift configured to lift a wheel assembly off of a conveyor belt, a drum roller configured to rotate the wheel assembly, a pair of pinch rollers driven by a driver and configured to apply force to a tire of the wheel assembly, a force sensor configured to detect a force of the tire against the pinch rollers, and a controller configured to receive the force from the force sensor and generate a command for an alert in response to the force falling outside of a predefined threshold range.

Abstract: Aspects of the present disclosure relate generally to a vision system that detects objects moving in an environment. The vision system detects objects that crossed a boundary of an environment during a first period of time, and determines a count of objects that crossed the boundary in a first direction. The vision system retrieves historical egress and ingress data for a second period of time corresponding to the first period of time. The historical egress and ingress data comprises a detected historic count of crossings in the first direction and a corrected historic count of crossings in the first direction. The vision system calculates an error rate for the second period of time based on a ratio of the detected historic count and the corrected historic count, and determines a corrected count for the first period of time by adjusting the count using the error rate.

Abstract: Techniques for automated facial measurement are provided. A set of coordinates for a set of landmarks on a face of a user are extracted by processing an image using a machine learning model. An orientation of the face of the user is determined. It is determined that impedance conditions are not present in the images, and a reference distance on the face of the user is estimated based on the image, where the image depicts the user facing towards the imaging sensor. A nose depth of the user is estimated based on a second image based at least in part on the reference distance, where the second image depicts the user facing at an angle relative to the imaging sensor. A facial mask is selected for the user based on the nose depth.

Abstract: A semiconductor device includes: a semiconductor substrate; a drift zone of a first conductivity type in the semiconductor substrate; an array of interconnected gate trenches extending from a first surface of the semiconductor substrate into the drift zone; a plurality of semiconductor mesas delimited by the array of interconnected gate trenches; a plurality of needle-shaped field plate trenches extending from the first surface into the plurality of semiconductor mesas; in the plurality of semiconductor mesas, a source region of the first conductivity type and a body region of a second conductivity type separating the source region from the drift zone; and a current spreading region of the first conductivity type at the bottom of the gate trenches and having a higher average doping concentration than the drift zone. Methods of producing the semiconductor device are also described.

Abstract: A device, system, and method for autonomously feeding livestock animals includes receiving signals from RFID tag readers, determining animals associated with the signals are eligible for feeding, causing a motor to rotate an auger for dispensing an output feed amount, and updating a feed history of the animal. The animals are determined to be eligible for feeding based on a feed history associated with the RFID tag and a feed schedule or a feed routine.

Abstract: A computational tool is proposed that is adapted as an automated batch impact evaluator (ABIE). The computational tool, for example, can be configured to monitor and track batch processing, generating computational outputs that can be surfaced to a user or downstream devices in the form of computer interface or application programming interface.

Abstract: Aligning pillars of a three-dimensional NAND memory assembly can include forming a first pillar and a corresponding first pillar alignment feature in at least a portion of a first substrate stack. The alignment method can include depositing a second substrate stack on the first substrate stack, covering the first pillar alignment feature and the first pillar, and depositing a first masking layer on at least a portion of the second substrate stack. Illumination light can be used to illuminate a portion of the first masking layer. A reflected portion of the illumination light can indicate a location of the first pillar alignment feature corresponding to the first pillar. Particular wavelengths of the illumination light can be blocked or filtered by the first masking layer.

Abstract: An ensemble machine learning model is used to visualize complex data relationships. Complex data is provided to multiple generator models that each independently create a graph representing relationships in the data. At least one of the generator models is a machine learning model that can be trained with a generator model loss function. The graphs produced by the separate generator models are combined by an ensemble model to create a consensus graph. The ensemble model may be implemented as an edge-selector neural network. The models are trained jointly with a ensemble model loss function that includes the loss functions of the generator models added as regularization terms. A visualization of the ensemble graph is created to aid a user in understanding the complex data relationships.

Abstract: A memory array includes a plurality of bit-cells arranged as a set of rows of bit-cells intersecting a plurality of columns. The memory array also includes a plurality of in-memory-compute (IMC) cells arranged as a set of rows of IMC cells intersecting the plurality of columns of the memory array. Each of the IMC cells of the memory array includes a first bit-cell having a latch, a write-bit line and a complementary write-bit line, and a second bit-cell having a latch, a write-bit line and a complementary write-bit line, wherein the write-bit line of the first bit-cell is coupled to the complementary write-bit line of the second bit-cell and the complementary write-bit line of the first bit-cell is coupled to the write-bit line of the second bit-cell.

Abstract: A driveline including a motor/generator configured to receive power from an engine and output power to a tractive element, an accessory drive configured to receive power from the engine and output power to an accessory, and an energy storage system including a battery, the energy storage system electrically coupled to the motor/generator and the accessory drive. The driveline is operable in a charge mode with the motor/generator and the accessory drive providing electrical power to the energy storage system. The driveline is operable in a silent mobility mode with the energy storage system providing electrical power to the motor/generator and the accessory drive to operate the military vehicle.

Abstract: A military vehicle including an engine coupled to the chassis for providing mechanical power to the military vehicle, a motor/generator coupled to the engine, and an energy storage system including a battery electrically coupled to the motor/generator. The military vehicle is operable in a silent mobility mode with the engine inactive and the energy storage system providing power to the motor/generator to operate the military vehicle. The motor/generator and the battery are sized such that electrical power generation through engine drive of the motor/generator is greater than the power depletion through operation of the military vehicle in the silent mobility mode. The motor/generator can charge the energy storage system while the military vehicle is driving or stationary.

Abstract: A system for monitoring potential damage to a tissue within a patient caused by tissue retraction during a surgical procedure, the system comprising: a housing body; an attachment mechanism for attaching the housing body to a tip of a surgical retractor; a force sensor; an inertial sensor; a feedback module; and a control module configured to: track force applied by the retractor tip to the tissue based on force signals received from the force sensor; detect the force applied approaching a force threshold, the force threshold based on a relationship between force applied by the retractor tip to the tissue and orientation of the retractor tip against the tissue; in response to the force applied approaching the force threshold, generating a first warning prompt indicating a possibility of damage to the tissue; and outputting the first warning prompt via a feedback module.

Abstract: The present invention relates to a composition comprising an aqueous dispersion of polymer encapsulated TiO2 composite particles and an organic matting agent, as well as a method for making the composition. The composition of the present invention is useful for coating compositions to improve mar resistance of coatings.