Abstract: In some implementations, a verification device may receive a request for an electronic exchange of information. The verification device may receive geographic location information associated with the request for the electronic exchange of information. The verification device may determine, using a machine learning model and based on the geographic location information, a validity of the request for the electronic exchange of information. The verification device may determine whether to execute the electronic exchange of information based on the determination of the validity of the request for the electronic exchange of information. The verification device may perform one of executing the electronic exchange of information or rejecting the request for the electronic exchange of information based on the determination of whether to execute the electronic exchange of information.

Abstract: A trim retention assembly (280) for a recessed luminaire (100) comprising a —retention device anchor (328) and a retention device retaining feature (329) both disposed in the recessed luminaire (100), —retention device coupling feature (755) disposed on a trim (749), and —retention device (330) having a —luminaire anchor (335), —resilient feature (334), —luminaire retention feature (333), and —trim coupling feature (331), where the i) luminaire anchor is coupled to the retention device anchor, ii) trim coupling feature is coupled to the retention device coupling feature, iii) resilient feature has a loaded position and an unloaded position, iv) retention device retaining feature holds the resilient feature in the loaded position, v) trim coupling feature is disposed below a structure (159) when the resilient feature is in the loaded position, and vi) resilient feature pulls the trim against the structure when resilient feature is in the unloaded position.

Abstract: A method and related system for training a machine learning model using a federated learning structure by selectively sharing condensed data between devices includes operations to obtain datasets from client devices comprising a first client device and a second client device and updating a datasets subset to comprise a first dataset. The method further includes updating the datasets subset to comprise a second dataset based on a result indicating that a feature space distance between the first dataset and the second dataset satisfies a set of criteria and sending, to a third client device, the datasets subset comprising the first dataset and the second dataset. The method further includes obtaining, from the third client device, a set of model parameters that is derived from training based on the datasets subset and updating a server version of a machine learning model based on the set of model parameters.

Abstract: A trim attachment system includes a light fixture housing and a first coiled spring bracket having a first coil section and a first elongated section. The first elongated section is positioned in the light fixture housing and attached to the light fixture housing, where the first coil section is attachable to a trim to pull up the trim toward an opening of the housing. The trim attachment system further includes a second coiled spring bracket having a second coil section and a second elongated section. The second elongated section is positioned in the light fixture housing and attached to the light fixture housing, where the second coil section is attachable to the trim to pull up the trim toward the opening of the housing.

Abstract: The present inventions is directed to systems and methods for automated stress testing of data models and comprises steps of generating, from an initial training dataset used for training a data model, a first data profile comprising a descriptive summary of the initial training dataset, generating a stress profile from an analysis of the data model and the initial training dataset used for training the data model, and modifying the first data profile by the stress profile to generate an altered data profile. A synthetic dataset may then be generated from the altered data profile. A stress performance output of the data model may then be used to identify weak points in the performance of the data model and improve the model's stress performance response using synthetic data.

Abstract: A video recording device, holster and article of clothing are disclosed to reliably and covertly provide for the capture of video, audio, and metadata, and perform other commands. The holster may be provided with a carrier that is, in turn, inserted into the holster. In one embodiment, the holster may be confirmed as being associated with the video recording device to authenticate a user, and establishes a docked position. Moreover, the video recording device may enter a mode of operation associated with using the video recording apparatus automatically when inserted into a holster.

Abstract: A computer-implemented method to send targeted messages based on a driver's intent. The method includes identifying, by a sending vehicle, one or more additional vehicles in the vicinity of the sending vehicle, including a first vehicle. Monitoring a set of data related to a current scenario for the sending vehicle and determining, based on a current scenario, an intent score for the sending vehicle. The method includes activating a horn device associated with the sending vehicle. The method further includes determining, in response to the activating, the intent score is above an intent threshold for the first vehicle. The method includes generating, in response to the intent score being above the intent threshold, a message; and sending, to a target vehicle, the message. Further aspects of the present disclosure are directed to systems and computer program products containing functionality consistent with the method described above.

Abstract: A compressor casing is provided. The compressor casing includes an outer wall, a rail extending inwardly from the outer wall and comprising scallop features encompassing pathways and an inner wall connected with an inboard end of the rail. The inner wall includes a first platform surface at a first side of the rail and including first fillets interfacing with first sides of the scallop features and a second platform surface outboard of the first platform surface at a second side of the rail opposite the first side and including second fillets interfacing with second sides of the scallop features.

Abstract: A sterile environment system can include an enclosure and a support system. The enclosure can include a barrier separating a sterile environment inside of the enclosure from a non-sterile environment outside of the enclosure. The barrier can include an expandable portion configured to expand from an unexpanded state to an expanded state for working within the sterile environment, and a patient-interfacing portion including a fenestration configured for placement directly over an area of interest of a patient, the fenestration having a sealed state and an unsealed state for access to the area of interest from within the sterile environment. The support system can be coupled to the patient-interfacing portion of the barrier such that it is positioned on at least opposite sides of the fenestration.

Abstract: A bioprocessing system includes a first fluid assembly having a first fluid assembly line connected to a first port of a first bioreactor vessel though a first bioreactor line of a first bioreactor vessel, a second fluid assembly having a second fluid assembly line connected to a second port of the first bioreactor vessel through a second bioreactor line of the first bioreactor vessel, and an interconnect line providing for fluid communication between the first fluid assembly and the second fluid assembly, and for fluid communication between the second bioreactor line of the first bioreactor vessel and the first bioreactor line of the first bioreactor vessel.

Abstract: Systems and methods for detecting anomalous data updates in federated learning. In some aspects, the system retrieves a plurality of data updates and a corresponding plurality of data profiles during a first interval of time. The system generates a first data profile trend based on the plurality of data profiles, including an expectation value and a measure of variance. The system receives a subsequent data update and a corresponding subsequent data profile. The system determines a measure of deviation based on the expectation value of the first data profile trend and the subsequent data profile. The system generates an anomaly score based on the measure of deviation and the measure of variance. Based on the anomaly score, the system determines whether to label the subsequent data update as acceptable for inclusion in training data to generate a local model.

Abstract: Systems and methods for detecting anomalous data updates in federated learning. In some aspects, the system receives a plurality of data updates. Each data update contains data in a first real-valued space. The system selects a first function to project the plurality of data updates into a second real-valued space. The system selects a second function to partition the second real-valued space into a plurality of sectors. The system generates a plurality of sector datasets associated with the plurality of sectors. The system processes the plurality of sector datasets to generate a relational data structure. The system determines outliers in the relational data structure corresponding to anomalous data updates.

Abstract: A computer-implemented method to send targeted messages based on a driver's intent. The method includes identifying, by a sending vehicle, one or more additional vehicles in the vicinity of the sending vehicle, including a first vehicle. Monitoring a set of data related to a current scenario for the sending vehicle and determining, based on a current scenario, an intent score for the sending vehicle. The method includes activating a horn device associated with the sending vehicle. The method further includes determining, in response to the activating, the intent score is above an intent threshold for the first vehicle. The method includes generating, in response to the intent score being above the intent threshold, a message; and sending, to a target vehicle, the message. Further aspects of the present disclosure are directed to systems and computer program products containing functionality consistent with the method described above.

Abstract: In some implementations, an expert system may receive, from a user device, a data structure representing a project associated with a technical request. The expert system may map the data structure to a graph representation of a user space to determine a set of users. The expert system may determine a set of statuses, corresponding to the set of users, associated with availability of the set of users. The expert system may transmit, to the user device, instructions for a user interface including visual indicators for the set of users and the set of statuses. The expert system may receive, from the user device, an indication of a selected user from the set of users and may transmit a message addressed to the selected user.

Abstract: Methods and systems for scalable dataset content embedding for improved searchability. For example, the system may retrieve a first dataset from a first data source. The system may generate a first data profile of the first dataset. The system may generate a latent index of the first data profile based on processing the first data profile using a first embedding algorithm. The system may receive, via a user interface, a first request for a first text string. The system may generate an embedded request corresponding to the first request based on processing the first text string using the first embedding algorithm. The system may process the embedded request using the latent index. The system may generate for display, in the user interface, a result based on processing the embedded request using the latent index.

Abstract: Systems and methods for deploying machine learning models trained on synthetic data generated based on a predicted future data drift are described herein. In some aspects, the system analyzes data profiles that include snapshots of data from different points in time from the same data stream to predict a future data drift. The system generates synthetic data based on the previous data profiles. The system determines, based on a first and second data profile, that a first data drift exceeds a threshold and updates a machine learning model. The system determines a predicted data drift and generates a synthetic snapshot of the data stream corresponding to a time in the future. The system generates a speculative machine learning model from updating the first updated machine learning model based on the synthetic snapshot. The system deploys the speculative machine learning model to replace the first updated machine learning model.

Abstract: A vehicle system includes: a drivetrain that includes an electric motor configured to drive rotation of a wheel; an input device that receives an input and outputs an initial throttle command responsively; an electronic control module that receives the initial throttle command from the input device and outputs an adjusted throttle command, wherein the adjusted throttle command is determined based on a natural frequency of the drivetrain; a first sensor that senses an output of the electric motor; and an inverter having control circuitry that receives the adjusted throttle command from the electronic control module and receives sensor data from the first sensor and controls power supplied to the electric motor based on the sensor data and the adjusted throttle command to counter torsional wind-up of the drivetrain.

Abstract: Systems and methods for novel uses and/or improvements to data labeling applications, particularly data labeling applications involving sensitive data. As one example, systems and methods are described herein for preventing sensitive data leakage, using weak learner libraries, during label propagation.

Abstract: Disclosed herein are systems and methods related to an image capture device and one or more processors. The image capture device can capture one or more images. The one or more processors can determine that a parameter, such as gain or exposure, of the one or more images satisfies a threshold and cause the image capture device to reduce a frame rate of detecting the one or more images responsive to the parameter satisfying the threshold.

Abstract: A system determines that a first data element in a first message is linked to a first data field in a first mapped dataset. The system receives a request to determine to which data field in a second mapped dataset a second data element in a second message should be mapped. The system extracts a first set of features from the first message. The system determines that the first data element is located on a first location within the first message. The system extracts a second set of features from the second message. The system determines that the second data element is location on a second location within the second message. The system determines a difference between the first location and the second location. If the difference is less than a threshold distance, the system associates the second data element to the first data element in the second mapped dataset.