Abstract: Systems, computer program products, and methods are described herein for extraction of historical data in workflow automation platform architectures. The present disclosure is configured to introduce an advanced approach to historical data extraction from workflow automation platform architectures. At its core, it employs parallel processing, utilizing a multi-threaded asynchronous tool specifically designed within a workflow automation platform architecture framework. This ensures high performance and scalability, enabling easy extraction of large data volumes within designated system maintenance windows without impinging on system performance.

Abstract: Systems and methods for characterizing uncertainty on a boundary of a region of interest includes inputting, via a processor, an ultrasound image having the region of interest into a trained neural network. Systems and methods also include outputting, via the processor, from the trained neural network a first prediction of the boundary of the region of interest and a second prediction of a region segmentation of the region of interest. Systems and methods further include determining, via the processor, an uncertainty on the boundary based on mismatch between the first prediction and the second prediction.

Abstract: Techniques are described for maintaining patient privacy in association with obtaining patient data for machine learning applications. In an example, a method can comprise accessing, by a system comprising a processor, a training dataset associated with a machine learning model, the training dataset comprising of data samples respectively comprising unique characteristics of subjects. The method further comprises determining, by the system, characteristic curve information that correlates different data portions extracted from the data samples to respective probabilities of matching the different data portions to respective ones of the data samples from which they are extracted.

Abstract: A method for analyzing uncertainty in a multi-scale interpretation of a medical image includes inputting the medical image into a trained segmentation network. The method includes outputting via the trained segmentation network a segmentation output mask for each pixel of the medical image or a region of interest of the medical image. The method includes utilizing a deterministic function to aggregate segmentation output masks for all pixels of the medical image or the region of interest and to output a first classification prediction of the aggregated segmentation output masks. The method includes inputting the medical image into a trained classification network. The method includes outputting a second classification prediction of the medical image or the region of interest. The method includes determining an uncertainty between the first classification prediction and the second classification prediction via comparison of the first classification prediction to the second classification prediction.

Abstract: An epoxy resin component(s) for a recyclable epoxy resin system is disclosed. The recyclable epoxy resin system comprises an epoxy resin component having a structural Formula I or an epoxy resin component having a structural Formula II and a curing agent. A process(es) for preparing the epoxy resin component having the structural Formula I and the epoxy resin system having the structural Formula II is also disclosed.

Abstract: Methods and systems are provided for generating user guidance for ultrasound imaging. In one example, a method includes determining, with a probe recommendation model, a user action to an ultrasound probe prior to and/or during acquisition of a current ultrasound image frame, one or more anatomical features in the current ultrasound image frame, and an anatomy view of the current ultrasound image frame, and outputting, for display on a display device, a probe motion recommendation based on the user action, the one or more anatomical features, and the anatomy view.

Abstract: Systems/techniques that facilitate improved uncertainty estimation via object-specific and object-agnostic segmentation disagreement are provided. In various embodiments, a system can access an image depicting an object. In various aspects, the system can localize, via execution of an object-specific segmentation model on the image, a first inferred boundary of the object. In various instances, the system can generate an uncertainty score for the first inferred boundary, based on a second inferred boundary of the object generated via execution of an object-agnostic segmentation model on the image.

Abstract: A computer implemented method for generating a response to a received electronic message. A generative AI is prompted to analyse the electronic message and to generate intent data indicative of an intent associated with the electronic message and data-identifier data indicative of one or more predetermined data identifiers present in the electronic message. The electronic message is analysed to identify and retrieve client data associated with one or more parties associated with the electronic message. The method includes Verifying the retrieved client data includes data corresponding to the generated data-identifier data. If so, query an ERP system with the verified data-identifier data to extract ERP data corresponding to the predetermined data identifiers of which the data-identifier data is indicative, select a response-message template using the intent data, populate the selected response-message template with the ERP data, and present the populated response-message template to a user for approval.

Abstract: An apparatus includes a processor and a memory having instructions stored thereon that, when executed by the processor, cause the apparatus to process a first notification received from a first network node to determine a first status of the first network node. The apparatus is also caused to process a second notification received from a second network node to determine a second status of the second network node. The apparatus is further caused to, response to determining the first status and the second status indicate an alarm state, cause a workload assigned to a first data center associated with the first network node and the second network node to be reassigned to a second data center different from the first data center.

Abstract: An automated power on notification system includes a non-transitory computer readable medium configured to store instructions thereon. The system further includes a processor connected to the non-transitory computer readable medium. The processor is configured to execute the instructions for detecting a failure to establish a connection with a newly powered on component. The processor is further configured to instruct a transmitter to transmit a periodic timer signal to the newly powered on component, wherein the periodic timer signal indicates a time period for the newly powered on component to wait prior to repeating an attempt to connect to a network. The processor is further configured to receive a connection request from the newly powered on component after the time period has elapsed. The processor is further configured to establish a connection between the newly powered on component and the network.

Abstract: A system, method and non-transitory computer-readable medium including instructions executable by one or more processors to display, a listing of one or more Open Radio Access Network (O-RAN) units; receive, by an orchestrator tool, a first user selection of a first set of O-RAN units; receive a first user entry of a version identifier of a first upgrade; receive a second user entry of a path associated with the first upgrade; receive a first request to deploy the first upgrade to the first set of O-RAN units; and in response to receiving the first request, prepare a first standardized configuration payload. The first standardized configuration payload includes the version identifier of the first upgrade; and the path associated with the first upgrade. The instructions cause transmission of the first standardized configuration payload in a first configuration file to a configuration management module or service.

Abstract: An epoxy resin component(s) for a recyclable epoxy resin system is disclosed. The recyclable epoxy resin system comprises an epoxy resin component having a structural Formula I or an epoxy resin component having a structural Formula II and a curing agent. A process(es) for preparing the epoxy resin component having the structural Formula I and the epoxy resin system having the structural Formula II is also disclosed.

Abstract: Techniques are described that facilitate training an artificial intelligence (AI) model in a manner that ensures equitable model performance across different sub-groups. According to an embodiment, a system is provided that includes a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory. The computer executable components include a training component that trains a machine learning (ML) model on training data to perform an inferencing task using an equitable loss function that drives equitable performance of the ML model across different sub-groups represented by the training data, resulting in trained version of the ML model that provides a defined equitable performance level across the different sub-groups. The equitable loss function is “sub-group aware” and penalizes variation in model performance across the sub-groups during model training and validation.

Abstract: Systems/techniques that facilitate task-specific image style transfer are provided. In various embodiments, a system can access a first medical image, wherein the first medical image can exhibit anatomical content and a first visual style. In various aspects, the system can generate, via execution of an optimization algorithm, a second medical image based on the first medical image, wherein the second medical image can exhibit the anatomical content and a second visual style that is different from the first visual style. In various instances, the optimization algorithm can be based on feature maps extracted from a pre-trained deep learning neural network that has been configured to perform an inferencing task on medical images exhibiting the second visual style.

Abstract: An ultrasound imaging system and method for calculating and displaying a probe position adjustment. The method includes acquiring a volumetric dataset with an ultrasound probe in a volumetric acquisition mode. The method includes automatically identifying, with a processor, an object representing a structure-of-interest from the volumetric dataset. The method includes automatically identifying, with the processor, an axis of the structure-of-interest based on the object. The method includes automatically calculating, with the processor, a probe position adjustment from a current probe position to enable the acquisition of a target scan plane of the structure-of-interest that either includes and is parallel to the axis or is perpendicular to the axis. The method includes presenting the probe position adjustment on a display device.

Abstract: The present invention relates to a process and system for recycling epoxy thermosets, containing cleavable bonds, said process using an acid solution to dissolve the epoxy thermoset and devolatizing the acid solution from a thermoplastic acidic mixture to produce the thermoplastic component. The process allows recovery of a recyclable thermoplastic component and optionally a recyclable reinforcement matrix component. The process comprising dissolving the epoxy thermoset in an acid solution under heated conditions resulting in a thermoplastic mixture; optionally filtering the thermoplastic mixture to separate out a reinforcement matrix component from a thermoplastic solution; and devolatizing the thermoplastic solution to obtain a recyclable thermoplastic component.

Abstract: Various methods and systems are provided for computer-aided diagnosis. In one embodiment, a method comprises acquiring, with an imaging system, a medical image of a subject, generating, with a radiologist model associated with a radiologist of an institution, a computer-aided diagnosis for the medical image, the radiologist model comprising a deep neural network trained on a plurality of diagnoses provided by the radiologist, displaying, to the radiologist via a display device, the medical image and the computer-aided diagnosis, and selectively updating, based on the medical image, one or more of the radiologist model, an institution model associated with the institution, and a geographic model associated with a geographic area containing the institution. In this way, a radiologist may be assisted by a deep neural network model configured as a digital twin of the radiologist.

Abstract: An axial flux motor may include a motor housing, a shaft rotatably mounted in the housing, and a stator mounted in the motor housing, and having a stator ring and a through-hole through which the shaft extends. Two rotors may be mounted on the shaft within the motor housing on opposing sides of the stator, each rotor having a plurality of magnets arranged radially on a stator-facing surface thereof. In addition, magnet wire may be wound on portions of the stator, the magnet wire comprising an inner coolant passage disposed within a copper tube, and a green glass coating on an outer surface of the copper tube, the green glass coating comprising glass solids, one or more of surfactants, solvents, and polymers.

Abstract: This disclosure relates generally to system and method for parameter compression of capsule networks using deep features. The conventional capsule networks have distinct capability of retaining spatial correlations between extracted features but that comes at a cost of intensive computational, cost, memory usage and bandwidth requirement. The embodiments herein disclose a system and method for employing a lightweight deep features based capsule network that is capable of compressing the parameters. In an embodiment, the system includes a deep feature based capsule network such that the capsule layer is preceded by feature blocks. Said feature blocks comprises convolutional operation with a kernel size 3, followed by convolutional operation with kernel of size 1, and a Batch Normalization layer, and hence are able to extract deep features.

Abstract: Embodiments of the present disclosure are directed to coated glass articles which reduce glass particle formation caused by glass to glass contact in pharmaceutical glass filling lines.