Abstract: Computer vision systems and methods for text classification are provided. The system detects a plurality of text regions in an image and generates a bounding box for each detected text region. The system utilizes a neural network to recognize text present within each bounding box and classifies the recognized text, based on at least one extracted feature of each bounding box and the recognized text present within each bounding box, according to a plurality of predefined tags. The system can associate a key with a value and return a key-value pair for each predefined tag.

Abstract: Metallic alloy development has been traditionally based on experimental or theoretical equilibrium phase diagrams and the like. The synthesis, processing and mechanical testing of small and large real samples are a challenging task requiring huge amount of effort in terms of time, money, resource, tedious testing and processing equipment and man-hour for which conventional Calphad calculations etc. alone do not help much in their local structure and related property prediction. Embodiments of the present disclosure provide simulation systems and methods for structure evolution and property prediction Molecular Dynamics (MD) combined with accelerated Monte Carlo techniques, wherein information on atomic elements and composition specific to alloy material is obtained to generate a MD potential file that is further used to generate a 3D structure file by executing a structure equilibration technique.

Abstract: An apparatus comprises a distributed acoustic sensing (DAS) optical fiber, a DAS interrogator coupled to the DAS optical fiber, and a connector. The connector couples the DAS interrogator, a first digitizer, and a second digitizer, wherein the first digitizer is to generate a first digitized DAS signal based on an analog DAS signal from the DAS interrogator, and the second digitizer is to generate a second digitized DAS signal based on the analog DAS signal. The apparatus also comprises one or more processors and a machine-readable medium having program code executable to cause the apparatus to simultaneously generate a first set of values that correlate with a first physical property based on the first digitized DAS signal and generating a second set of values that correlate with a second physical property based on the second digitized DAS signal.

Abstract: The present disclosure provides novel compositions and methods of forming those compositions by complexing a micronutrient with at least two organic acids, preferably in the presence of a base to form an aqueous formulation. Compositions comprising the complexed micronutrient are tank mix compatible and can be used to deliver a water-soluble source of the particular micronutrient to plants (e.g., corn plants), with foliar application being particularly preferred.

Abstract: A system and method are disclosed for training a machine learning model using information pertaining to job titles. Training data for the machine learning model is generated. Generating the training data includes generating first training input including information identifying the job titles associated with organizations, and generating a first target output for the first training input. The first target output identifies an indication of job families. A job family identifies a category of personnel positions that are categorized based on one or more characteristics that are shared between the personnel positions of the category. The training data to train the machine learning model on (i) a set of training inputs including the first training input, and (ii) a set of target outputs including the first target output is provided.

Abstract: Methods and system for modeling wellbore treatment operations in which the flow of treatment fluids may be diverted are provided. In one embodiment, the methods comprise: receiving, at a processing component, one or more treatment operation inputs characterizing a treatment operation for a wellbore system comprising a wellbore penetrating at least a portion of a subterranean formation and a treatment fluid comprising a diverter, wherein at least one of the one or more treatment operation inputs comprises the inlet concentration of the diverter in the treatment fluid; and using the processing component to determine a wellbore system pressure distribution and a wellbore system flow distribution based, at least in part, on the one or more treatment operation inputs and a diversion flow model, wherein the diversion flow model captures an effect of the diverter on fluid flow in the wellbore system.

Abstract: A data stream monitor including a processor and associated memory initiates a data stream monitoring application. The data stream monitoring application is configured to test a plurality of data streams, and obtains a plurality of data stream records associated with the plurality of data streams to be tested. The data stream monitor writes a lastRecord indicator to a file. The lastRecord indicator identifies a last data stream to have been tested. The data streams are tested, and the lastRecord indicator is updated each time a subsequent data stream is tested. The data stream monitor determines whether a value of the lastRecord indicator has changed from a previous value. In response to determining that the value of the lastRecord indicator has not changed, testing of the plurality of data streams is restarted.

Abstract: An expandable lift system includes an expandable platform including at least one detachable panel to expand a dimension of the expandable platform. At least one stationary stanchion houses a first lifting assembly. The first lifting assembly is coupled to a first side of the expandable platform. At least one translatable stanchion houses a second lifting assembly, and the second lifting assembly is coupled to a second side of the platform. At least one track is coupled to a substructure on which the lift sits. The track includes a rail defined within the at least one track. The at least one translatable stanchion is configured to translatably engage the rail to allow the at least one translatable stanchion to move laterally in a first direction. At least one stop is located at at least one end of the track to retain engagement of the translatable stanchion within the rail.

Abstract: Disclosed are systems and methods for detecting the beginning of a flush volume. A blended fluid is output by a fluid blending apparatus and pumped into a wellbore. The blended fluid transitions from a first composition to a second composition. A blending signal comprising time-varying data relating to characteristics of the blending apparatus or measured from sensors associated with the blending apparatus is received. Based on a first portion of the blending signal corresponding to the first composition, a calibration profile is generated. Based on the calibration profile and a second portion of the blending signal corresponding to the second composition, a transition indicator corresponding to a change in the blended fluid from the first composition to the second composition is determined. Based on the transition indicator, a flush signal indicating the beginning of a flush volume being output by the blending apparatus and pumped into the wellbore is generated.

Abstract: Systems and methods for securely pairing a transmitting device with a receiving device are described. The systems and methods may communicate with a first device via a first communication method over a wireless communication network. The systems and methods may transmit, to the first device via a second communication method, a first sensory pattern representing a first key. In addition, the system and methods may communicate with the first device via the first communication method using the first key.

Abstract: A cartridge of an electronic vaping device includes a housing extending in a longitudinal direction. The housing includes a sidewall, a transverse wall at the first end of the sidewall, and an inner tube integrally formed with the housing. The sidewall is generally cylindrical and a first end and a second end. The transverse wall includes at least one outlet therein. The inner tube extends in the longitudinal direction. The inner tube is concentrically positioned with respect to the sidewall. The inner tube communicates with the at least one outlet. The cartridge also includes a reservoir between the sidewall and the inner tube. The reservoir is configured to contain a pre-vapor formulation.

Abstract: Disclosed herein are system, method, and computer program product embodiments for machine learning systems to process incoming call-center calls based on inferred sentiments. An incoming call is routed to a call agent based on an inferred topic, classified based on one or more inferred sentiments of a current caller's speech, determining, based on the call classification, that a complaint has been articulated and initiating an automated assistance by searching for one or more similar callers to the current caller. Based on finding a successful call outcome associated with one or more similar callers, the system suggests one or more phrases to the call agent for use in a dialog with the current caller to improve the one or more inferred sentiments.

Abstract: Aspects described herein may relate to a transaction exchange platform using a streaming data platform (SDP) and microservices to process transactions according to review and approval workflows. The transaction exchange platform may receive transactions from origination sources, which may be added to the SDP as transaction objects. Microservices on the transaction exchange platform may interact with the transaction objects based on configured workflows associated with the transactions. Processing on the transaction exchange platform may facilitate clearing and settlement of transactions. Some aspects may provide for dynamic and flexible reconfiguration of workflows and/or microservices. Other aspects may provide for data snapshots and workflow tracking, allowing for monitoring, quality control, and auditability of transactions on the transaction exchange platform.

Abstract: A system for inspecting the reliability of an image. The system may include a processor in communication with a client device; and a storage medium. The storage medium may store instructions that, when executed, configure the processor to perform operations including: obtaining a plurality of images; categorizing the images into a plurality of image classes; calculating a plurality of probability outcomes; determining whether highest predicted probabilities of the images are less than a first threshold and whether an entropy of a predicted density of the probability outcomes exceeds a second threshold; indicating whether the image is associated with the image classes; ranking, the image amongst the plurality of images; filtering, a plurality of low reliability images according to a third threshold; providing, a likelihood of whether a user scanned a vehicle object associated with the image; and identifying a percentage of user scan failures.

Abstract: A caliper-arm-position sensor comprising a differential variable reluctance transducer (DVRT) and circuits to drive the DVRT with a substantially sinusoidal signal and to sample a signal at the DVRT once per drive-signal cycle at a predetermined position in the drive-signal cycle is disclosed.

Abstract: Methods for positioning an expandable metal sealing element in the wellbore. An example method includes an expandable metal sealing element having a reactive metal and disposed in a location. The method further includes actuating a washout prevention element, contacting the expandable metal sealing element with a fluid that reacts with the reactive metal to produce a reaction product having a volume greater than the reactive metal, and allowing the washout prevention element to prevent at least a portion of the reaction product from flowing away from the location.

Abstract: A method for processing a transaction initiated using an electronic wallet application may include storing a virtual payment device configured to initiate a transaction. A rewards inquiry may be communicated to an issuer. A rewards inquiry response may be received from the issuer containing a rewards amount associated with the virtual payment device. The rewards amount may be displayed. A transaction may be initiated with a merchant using the virtual payment device. A redemption request may be communicated to the issuer. A redemption response including an updated rewards amount may be received from the issuer and include a difference between the rewards amount and the rewards amount applied toward the transaction. A system and computer program product are also disclosed.

Abstract: Overlapping pores in a multiscale model of heterogeneous core formation contributes errors during flow simulations. A scale-coupled multiscale modeling that corrects for contributions of overlapping pores may be used to determine capillary pressure and relative permeability of the heterogenous core formation more accurately. The effects of overlapping pores may be removed by converting pores that have a certain radius or are filled with certain fluids into solid regions. The effects of overlapping pores may also be removed by running flow simulations on a modified model and correcting various fluid properties of the core formation with the results.

Abstract: A running tool coupled to a running string and for operational use in a well casing. The running tool having a collapsed and expanded state, a tubular positioned around the centralizer to hold the centralizer in the collapsed state, a release assembly maneuverable to release the tubular causing the centralizer to enter into an expanded state, and a cleaning device for cleaning walls of the well casing. The cleaning device includes at least one of a scraper, magnet, brush, and a high flow rate circulation valve for channeling fluid from the running string into the well casing. The centralizer functions as a stabilizer in the expanded state protecting the running tool during operation.

Abstract: Described herein are systems, methods, and apparatuses for performing a user-less payment for an item upon its delivery by an unmanned delivery vehicle. The unmanned delivery vehicle may navigate to a delivery location, receive payment information, initiate a payment transaction with a remote server, and release the item at a specified location upon successful completion of the payment transaction. Upon arrival of the unmanned delivery vehicle, a wireless data transmission device may send payment information to a remote server, and the remote server may provide the unmanned delivery vehicle with an indication of whether the item can be released and a specific location at which the item can be released.