Abstract: According to various aspects, a new concept of Steady-State Visually Evoked Potential (SSVEP) based Brain-Computer Interface (BCI) is described where brain-computer communication occurs by capturing SSVEP induced by consciously imperceptible visual stimuli integrated into, for example, a virtual scene. These consciously imperceptible visual stimuli are able to convey subliminal information to a computer. In various embodiments, computer based operations can be mapped to visual elements with associated flickering stimuli, and induced SSVEP can be detected when the user focused upon them. In various embodiments, these visual elements can be introduced into existing display without any perceivable change to content being displayed.

Abstract: Disclosed herein are system, method, and computer program product embodiments for an interactive user interface portal. A specially trained predictive model may detect user interface (e.g., webpage, application, etc.) configurations and recommend a multiple array of entities and services (e.g., healthcare providers/networks, treatment services, etc.). Communication with the entities and services may be facilitated via an interactive portal embedded in the user interface. The entities and services may be identified with respect to user preferences/intent and with consideration of location-based regulations/restrictions. Changes and updates to the user interface may be detected and any services and/or utilities associated with and/or necessitated by the changes and updates may be linked to the interactive portal.

Abstract: A system for performing optimization of hyper parameters in machine learning typically includes a classical computer apparatus and a quantum optimizer in communication with the classical computer apparatus. The classical computer apparatus is configured for gathering data sets associated with an application, identifying parameters associated with the application, constructing a machine learning model using the data sets and the parameters, determining conditions associated with optimizing the machine learning model, transmitting the machine learning model, the data sets, and the conditions to the quantum optimizer. The quantum optimizer computing a set of optimal hyperparameters for the machine learning model based on the data sets and the conditions and transmitting the set of optimal hyperparameters to the classical computer apparatus.

Abstract: A computer-implemented method for simulating quantum hardware performance can include accessing, by a computing system including one or more computing devices, a quantum hardware sample generation model configured to generate quantum hardware samples. The quantum hardware sample generation model can include one or more quantum hardware parameters. The computer-implemented method can include sampling, by the computing system, a quantum hardware sample from the quantum hardware sample generation model. The computer-implemented method can include obtaining, by the computing system, one or more simulated performance measurements based at least in part on the quantum hardware sample.

Abstract: An example method is provided for conducting differentially private communication of training data for training a machine-learned model. Initial label data can be obtained that corresponds to feature data. A plurality of label bins can be determined to respectively provide representative values for initial label values assigned to the plurality of label bins. Noised label data can be generated, based on a probability distribution over the plurality of label bins, to correspond to the initial label data, the probability distribution characterized by, for a respective noised label corresponding to a respective initial label of the initial label data, a first probability for returning a representative value of a label bin to which the respective initial label is assigned, and a second probability for returning another value. The noised label data can be communicated for training the machine-learned model.

Abstract: A method includes providing a first quantum state at a first node, transforming the first quantum state to obtain a first plurality of transformed quantum states, and measuring the first plurality of transformed quantum states to obtain a first set of measurement results. The method further includes providing a second quantum state at a second node, transforming the second quantum state to obtain a second plurality of transformed quantum states, the second plurality of unitary operations corresponding to the first plurality of unitary operations, and measuring the second plurality of transformed quantum states to obtain a second set of measurement results. A similarity measure between the first quantum state and the second quantum state is determined in terms of the first set of measurement results and the second set of measurement results, the similarity measure including a trace product of the first quantum state and the second quantum state.

Abstract: A computer-implemented system personalizes virtual advisors for immersive healthcare by creating virtual medical and spiritual avatars that resemble trusted authority figures using deepfake technology and multimodal deep neural networks. The virtual medical advisor tailors guidance by analyzing unstructured electronic health record data with natural language processing and BERT-based techniques while adapting its communication based on real-time physiological data from sensors like EEG and photoplethysmography. Concurrently, the virtual spiritual advisor offers faith-based counseling by factoring in user-declared spiritual preferences and sacred text analysis weighted for doctrinal considerations. Additional features include gamification with cryptocurrency tokens or NFTs for health activities, blockchain-based audit trails for HIPAA compliance, and federated learning with differential privacy.

Abstract: Embodiments of the present disclosure relate to a method and an apparatus for an autonomous decision of network node. A method performed at a first network node may comprise: broadcasting a solution for a task to a network; and performing the solution, when a plurality of verification results about the solution satisfy a predetermined condition. The plurality of verification results may be from a plurality of second network nodes in the network. According to embodiments of the present disclosure, the collaboration level between different network nodes for decision of how to operate is improved.

Abstract: One or more computing devices, systems, and/or methods are provided. In an example, a method comprises receiving, by a device, incoming motion data from a motion sensor, generating, by the device, an incoming embedding vector based on the incoming motion data, generating, by the device, a predicted embedding vector based on the incoming embedding vector, assigning, by the device, an activity classification based on the predicted embedding vector, and modifying an operating parameter of the device based on the activity classification.

Abstract: Data acquirable from a physical system is received and processed by at least one classical computing device to provide data indicative of a digital twin of the physical system by digitally computing a quantum-inspired algorithm. The data indicative of the digital twin is indicative of a reconfiguration of a physical parameter of the physical system, and the physical parameter has a reconfigurable digital counterpart in the digital twin.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support dynamically updated ensemble-based machine learning (ML) classification. An ensemble of ML classifiers may be created from a plurality of trained ML classifiers. These initial ML classifiers may be trained using labeled data to generate predictions based on input data. When an unlabeled data stream is received, the unlabeled data stream may be provided as input to the ensemble to generate predictions. After obtaining labels for the received data, the labels and the unlabeled data stream may be used to train new ML classifiers. The new ML classifiers may replace older ML classifiers in the ensemble. In this manner, the ensemble of ML classifiers is used to perform predictions on high volume streaming data while being dynamically updated with ML classifiers that have learned changes in statistical distribution across more recent input data.

Abstract: The present disclosure includes a host device that is part of a patient monitoring system. The host device can provide an improved, organized, uncluttered, and graphically-rich display that presents an integrated display of real-time patient data and alarms from multiple integrated or non-integrated devices, such as patient monitors, ventilators, anesthesia gas machines, or intravenous (IV) pumps. The host device may provide a supplementary display for the patient data collected by the multiple devices and present information, such as comprehensive real-time patient status, historical trends, or alarm indicators, in an organized manner for particular clinical scenarios. The one or more displays can be central to a care team for a patient, and the care team can together simultaneously view and act upon the information presented.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for presenting a new machine learning model architecture. In some aspects, the methods include obtaining a training dataset with a plurality of training samples that includes feature variables and output variables. A first matrix is generated using the training dataset which is a sparse representation of the training dataset. Generating the first matrix can include generating a categorical representation of numeric features and an encoded representation of the categorical features. The methods further include generating a second, third and a fourth matrix. Each feature of the first matrix is then represented using a vector that includes a multiple adjustable parameters. The machine learning model can learn by adjusting values of the adjustable parameters using a combination of a loss function the fourth matrix, and the first matrix.

Abstract: A computer-implemented method for processing electronic medical images, the method including receiving a plurality of electronic medical images of a medical specimen associated with a single patient. The plurality of electronic medical images may be inputted into to a trained machine learning system, the trained machine learning system being trained to compare each of the plurality of electronic medical images to each other to determine whether each pair of the electronic medical images matches within a predetermined similarity threshold. The trained machine learning system may output whether each pair of the electronic medical images matches within a predetermined similarity threshold. The output may be stored.

Abstract: Aspects of the disclosure relate to smart sampling of noisy labels using artificial intelligence. A computing platform may receive a dataset of primarily unlabeled data points. The computing platform may apply undersampling to the unlabeled data points to reduce imbalance. The computing platform may assign a candidate label to each unlabeled data point in the dataset without a human manually labeling the unlabeled data points. The computing platform may compute a heuristic score for each data point and rank the data points based on the heuristic score. The computing platform may subsample the dataset by comparing the heuristic score for each data point against more than one threshold and applying a k-Nearest Neighbors (k-NN) algorithm, with two different k values, to identify untrustworthy labels. The computing platform may provide or transmit a trustworthy resulting dataset to a machine learning (ML) model.

Abstract: A natural language processor extracts features from batches of unstructured traffic. A feature weighted distance engine computes a distance matrix between pairs of feature vectors for sessions of unstructured traffic using a weight vector that assigns importance to relative placement of features in feature vectors. The distance function used to compute the distance matrix with the weight vector is conducive to generating high-quality clusters and patterns in unstructured traffic. The sessions of unstructured traffic are clustered according to the pairwise distance matrix. Generated clusters are merged with clusters for previously analyzed sessions of unstructured traffic. A pattern identification engine extracts patterns from the merged clusters that correspond to behavior of applications generating the unstructured traffic.

Abstract: An infotainment system for a motor vehicle includes a display screen positioned to be visible by a passenger of the motor vehicle. A storage arrangement stores a collection of video segments to be presented on the display screen. The storage arrangement also stores metadata in association with the video segments. A user interface receives inputs from the passenger. A sensor detects a characteristic of the passenger. A processing arrangement is communicatively coupled to each of the display screen, the collection of video segments, the user interface and the sensor. The processing arrangement selects one of the video segments to present on the display screen. The selecting of the one video segment is dependent upon inputs received from the passenger via the user interface, signals received from the sensor indicative of the characteristic of the passenger, and metadata associated with individual segments.

Abstract: A physiological monitor touchscreen interface presents interface constructs on a touchscreen display that are particularly adapted to finger gestures so to change at least one of a physiological monitor operating characteristic and a physiological touchscreen display characteristic.

Abstract: A controller of a QCCD-based quantum computer is configured to perform arbitrary angle two-qubit gates using global single-qubit gates and rotations of arbitrary angles and/or individual single-qubit gates that include two-qubit gate primitives, such as a phase-independent anti-symmetric two-qubit gate, and that are not individually addressed.

Abstract: A method displays a first data visualization according to user association of data fields with displayed data visualization properties. The data visualization includes visual data marks corresponding to data values for data fields in a dataset. A user selects a subset of the visual data marks. A popup summary is displayed that includes data value distributions for several data fields from the dataset. In the popup summary, a second user input is detected corresponding to a first data field whose data value distribution is displayed in the popup summary. The second user input associates the first data field with a first visualization property of the displayed data visualization properties. In response, a second data visualization is displayed according to association of data fields, including the first data field, with displayed data visualization properties.