Abstract: A controller for controlling an operation of a system is disclosed. The controller receives an input signal indicative of the operation of the system and rotates a test signal multiple times with different circular shifts to produce different rotations of the test signal forming a matrix data structure with the input signal. The input signal and the test signal are time-series data having values monotonically measured over time. The controller is further configured to apply a sliding three-dimensional (3D) window method to the matrix data structure to produce statistics of the input signal with respect to the rotations of the test signal. The sliding 3D window method iteratively moves window over the matrix data structure to compute a value of the statistics for a segment of the matrix data structure within the window. Furthermore, the controller controls the operation of the system according to the statistics of the input signal.

Abstract: Provided is a data prediction system for predicting a future prediction value. The data prediction system has a data management device which manages data and a prediction operation device which models tendency of an error amount of a prediction operation result calculated on the basis of a correlation with a major explanatory variable and corrects a future prediction value. The data management device includes a storage unit which stores prediction target past measurement data observed with a time transition and explanatory factor data explaining the prediction target past measurement data.

Abstract: Methods and systems providing adaptive assessment of a physical subject to efficiently collect assessment data and modify an assessment schedule based on the analyses. The methods and systems can control the timing of each assessment in order to collect data at times and under conditions that are most informative about the physical subject. Such adaptive methods and systems significantly minimize the frequency of data collection without loss in accuracy or precision and can increase test reliability through reduction in redundancy. The ability to estimate an unknown, underlying function using a small number of free parameters that remain constant regardless of the number of data points being estimated substantially reduces the error of the function estimate. Because estimates of the measurement error are achieved with a minimum of sampled assessments, and with great accuracy, the statistical power of clinical trials, for example, can be greatly increased.

Abstract: A graph structure analysis apparatus 10 is an apparatus for analyzing a graph structure. The graph structure analysis apparatus 10 includes a range selection unit 11 that selects an analysis target range in the graph structure and a comparison target range to be compared with the analysis target range, and a feature representation extraction unit 12 that extracts a feature representation from data related to the analysis target range and the comparison target range, for each of the ranges.

Abstract: A device, system, and method use predictive analytics based on an application-centric approach. The method includes receiving a request from an interactive application interacting with a user utilizing a user device for action data indicating an action to be taken by the interactive application during a session with the user device, the request generated by the interactive application based on a decision point associated with the interactive application. The method includes receiving from the interactive application session data associated with the session and the user device. The method includes determining scoring package data associated with the request based on the session data, the scoring package data comprising a predictive model indicative of a plurality of actions to be performed by the interactive application. The method includes generating the action data based on the scoring package data and transmitting the action data to the interactive application.

Abstract: The driver Hamiltonian is modified in such a way that the quantum approximate optimization algorithm (QAOA) running on a circuit-model quantum computing facility (e.g., actual quantum computing device or simulator), may better solve combinatorial optimization problems than with the baseline/default choice of driver Hamiltonian. For example, the driver Hamiltonian may be chosen so that the overall Hamiltonian is non-stoquastic.

Abstract: Provided is a factor analysis device capable of obtaining more useful knowledge relating to the degree of influence of pieces of data. A factor analysis device according to one embodiment of the present invention is provided with: a classification unit for classifying a type of data into a first group or a second group; and an influence degree calculation unit for calculating, as the degree of influence on target data, the degree of influence of the data of the type classified into the second group on the data of the first group type.

Abstract: Provided is an olfactory data sharing terminal including a receiver configured to receive olfactory data obtained by sensing an odor of an object through an olfactory sensor; a preference determiner configured to determine whether a user prefers the received olfactory data, based on a user olfactory function fuser(x); and a display displaying a user preference for the received olfactory data.

Abstract: An object is to predict a microstructure of Al in an industrial process more accurately than conventional techniques. In an information processor (1), an inter-step information integration section supplies a PC(i) and an MS(i, 0) to each i-th step calculating section included in a step calculating section. Each i-th step calculating section supplies an MS(i, t) and a TMP(i, t) to a microstructure calculating section and thereby causes the microstructure calculating section to find an MS(i, tfi), and supplies the MS(i, tfi) to the inter-step information integration section (11). The inter-step information integration section (11) sets, as an MS(i+1, 0), the MS(i, tfi) received from the i-th step calculating section.

Abstract: A quantum state visualization device comprising at least a portion of a spherical shell and a support structure affixed to the spherical shell. A portion of the support structure can intersect a center of the spherical shell. The quantum state visualization device further comprising a indicator pivotally attached to the support structure at the portion of the support structure intersecting the center of the spherical shell. The indicator is representative of a quantum state based on its position relative to the spherical shell.

Abstract: The present disclosure relates to a system, method, and computer program for automatically providing similar product recommendations for sold-out products promoted on non-merchant publisher sites, wherein the similar product recommendations are filtered for publisher preferences. A computer system with a product database provides a platform that enables non-merchant publishers to search products in the database, create call-to-actions on publisher sites for products in the database, and automatically receive similar product recommendations when end users of the publisher sites attempt to purchase promoted products that are now sold out. Once a publisher creates a call-to-action for a product that subsequently becomes sold out, similar product recommendations are provided without requiring any action on the publisher's part to change the publisher's site. Similar product recommendations are tailored to each publisher to account for publisher preferences.

Abstract: A system and process extract software application performance data from disparate ownership sources and make the various source data compatible for comparison data. A software application's performance in the marketplace may be compared to other applications in a same group with comparable data information. A M2M (mobile-to-mobile) technology is an interface layer connection to a backend server that builds machine learning pipelines and may use artificial intelligence to turn massive datasets into identifiable patterns, algorithms and statistical models. This layer is capable of cleaning, aggregating, and organizing data from disparate sources to produce meaningful conclusions to complex problems to inform strategic business decisions.

Abstract: In some embodiments, one or more unitary-valued functions are generated by a classical computer generating using projectors with a predetermined number of significant bits. A quantum computing device is then configured to implement the one or more unitary-valued functions. In further embodiments, a quantum circuit description for implementing quantum signal processing that decomposes complex-valued periodic functions is generated by a classical computer, wherein the generating further includes representing approximate polynomials in a Fourier series with rational coefficients. A quantum computing device is then configured to implement a quantum circuit defined by the quantum circuit description.

Abstract: An information processing apparatus includes a controller that causes learning data learned by an artificial intelligence to be recorded in a recording unit in such manner that influencing learning data that has influenced performance of an artificial intelligence and non-influencing learning data that has not influenced performance of an artificial intelligence are distinguishable.

Abstract: The present disclosure relates to methods for estimating an accuracy and robustness of a model and devices thereof. According to an embodiment of the present disclosure, the method comprises calculating a parameter representing a possibility that a sample in the first dataset appears in the second dataset; calculating an accuracy score of the model with respect to the sample in the first dataset; calculating a weighted accuracy score of the model with respect to the sample in the first dataset, based on the accuracy score, by taking the parameter as a weight; and calculating, as the estimation accuracy of the model with respect to the second dataset, an adjusted accuracy of the model with respect to the first dataset according to the weighted accuracy score.

Abstract: A computer-implemented method for refining a qubit calibration model is described. The method comprises receiving, at a learning module, training data, wherein the training data comprises a plurality of calibration data sets, wherein each calibration data set is derived from a system comprising one or more qubits, and a plurality of parameter sets, each parameter set comprising extracted parameters obtained using a corresponding calibration data set, wherein extracting the parameters includes fitting a qubit calibration model to the corresponding calibration data set using a fitter algorithm. The method further comprises executing, at the learning module, a supervised machine learning algorithm which processes the training data to learn a perturbation to the qubit calibration model that captures one or more features in the plurality of calibration data sets that are not captured by the qubit calibration model, thereby to provide a refined qubit calibration model.

Abstract: Techniques for ensuring the security of cognitive insights are disclosed. A request to generate a cognitive insight is received from a requestor. The requestor is associated with a requestor data security level. The cognitive insight is generated using a first machine learning model and a plurality of data sources, each data source associated with a respective data security level. An insight data security level for the generated cognitive insight is identified based on the insight and the plurality of data sources. A first data security level associated with a data source of the plurality of data sources is modified, based on the identified insight data security level. It is determined, based on the requestor data security level and the insight data security level, that the requestor is authorized to access the generated insight. In response the generated insight is provided to the requestor.

Abstract: An electronic device for a first session of a user, for each of a plurality of lists of media content items, determines a respective value for each objective of a first set of objectives and a second set of objectives by accessing contextual data for the first session of the user. The first set of objectives corresponds to the user and the second set of objectives corresponds to a second party distinct from the user. The electronic device, using a multi-arm bandit model, identifies a first list of media content items, from the plurality of lists of media content items, to present to the user, including: calculating a score for each list in the plurality of lists of media items; and probabilistically selecting the first list of media content items according to the respective scores corresponding to the respective lists in the plurality of lists of media items.

Abstract: A live streaming system 10 identifies, with regard to a plurality of users each wearing an HMD 100 to watch same content, types of emotions that the plurality of users are experiencing based on information associated with the plurality of users, the information being detected by a predetermined apparatus. The live streaming system 10 generates, as an image to be displayed on the HMD 100 of a certain user of the plurality of users, an image including the content and at least one of a plurality of avatars corresponding to the plurality of users. The live streaming system 10 changes display appearances of the plurality of avatars depending on the types of emotions that the plurality of users are experiencing.

Abstract: Embodiments disclosed herein provide a system, method, and computer program product for providing a triage classification system. The triage classification system uses a computer model that is developed using historical patient data. The developed computer model is applied to collected patient attribute data from a patient in a pre-hospital setting to generate a triage category. Based on the generated triage category, health care professionals can take desired actions, such as transporting the patient to a facility matching the generated triage category.

Abstract: Techniques for quantum data post-processing are provided. In one example, a system includes a quantum programming component and a post-processing component. The quantum programming component receives quantum output data that includes a set of quantum results for a quantum circuit in response to simulation of the quantum circuit. The post-processing component adjusts the quantum output data associated with the quantum circuit based on client system data indicative of information for a client system that consumes the quantum output data.

Abstract: The present disclosure provides methods and systems for quantifying item performance in a digital shelf. A method for quantifying item performance in a digital shelf may comprise: calculating a value associated with a shelf share of the given item; determining a set of factors for calculating a score indicative of the item performance on the digital shelf, wherein the set of factors includes the shelf share; generating, using a trained machine learning algorithm, the score based on the set of factors; and displaying the score within a graphical user interface (GUI) on an electronic device.

Abstract: A machine learning system for training a data model to predict data states in medical orders is described. The machine learning system is configured to train a data model to predict whether a medical order requires prior authorization (“PA”) for medical orders within a medical order data set so that related systems may process incoming medical orders with PA determinations predicted by the data model. The machine learning system includes a first data warehouse system. The first prescription processing system generates a data model of historical orders and payer responses, apply a predictive machine learning model to the data model to generate a trained predictor of whether a medical order requires PA, associated with order data, apply the trained predictor to a plurality of production orders to determine PA for each of the plurality of production orders, and process the plurality of production orders with each associated PA determination.

Abstract: Input data, such as audio and/or video data, may be captured from a first room, for example via microphones and/or cameras within the first room. A first quantity of people within the first room may be determined based at least in part on the input data. An alert may be provided when the first quantity of people exceeds a threshold quantity of people. Additionally, locations of people within the room may also be detected based at least in part on the input data. A first proximity of a first person in the room to a second person in the room may be determined. An alert may also be provided when the first proximity is less than a threshold proximity.

Abstract: Collaborative-filtered content recommendations with justification in real-time is described. A recommendation system determines these recommendations, in part, by identifying digital content items of a catalog that are associated with a single attribute used to describe digital content. The attribute used for the identification is based on affinity scores computed for a client device user to which the recommendations are being provided. These affinity scores indicate the client device user's affinity for different attributes used to describe the digital content. Once the digital content items are identified based on the one attribute, the recommendation system is then limited to ranking and selecting from the identified digital content items to provide the recommendations. The recommendation system does not process the entire catalog of digital content items at once to rank and select the items.

Abstract: Prediction of outcomes of disruptive treatments are enabled utilizing sequenced training of a machine learning model over ordered bins of treatment candidates. Treatment candidates may be assigned to candidate characterization bins with an ordering, and the model may be trained with a sequence of training steps corresponding to the ordering of the candidate characterization bins, in each training step the model having untreated candidate features from a corresponding bin and aggregate metrics from one or more previous steps as input. The predicted outcome for a selected bin may be generated with the trained model having treated candidate features and aggregate metrics from one or more previous steps as input. The predicted outcome may be a counterfactual prediction for a bin with insufficient control candidates, and may represent a nonlinear extrapolation from control data in prior bins in the bin ordering.

Abstract: Techniques are described herein for determining a predicted intent of a user and displaying additional content selected based on the predicted intent of the user. A method includes: receiving information identifying a webpage that a user is visiting and a navigational path of the user in navigating to the webpage; determining a predicted intent of the user based on the information identifying the webpage that the user is visiting and the navigational path of the user in navigating to the webpage; selecting additional content based upon the predicted intent of the user; and displaying an overlay, on a portion of the webpage, that includes the additional content.

Abstract: In an example, a method includes receiving object model data describing at least a portion of an object to be generated by additive manufacturing. Object generation instructions for generating the object in its entirety may be derived based on the object model data. Where it is determined that the object model data comprises a data deficiency for deriving the object generation instructions, at least one attribute for the object may be inferred and object generation instructions may be derived based on the object model data and the inferred attribute.

Abstract: A method and a system for model training are provided. The method can include training a first classifier, a second classifier, and a third classifier with subsets of a labeled dataset. The method can also include predicting a pseudo labeled dataset from an unlabeled dataset using the first classifier, the second classifier, and the third classifier. The method further includes assigning a role to the first classifier, to the second classifier, and to the third classifier. The method can further include selecting a teaching sample dataset from the pseudo labeled dataset based on the role assigned to the third classifier, wherein the third classifier is assigned a role of a student. The method can also include retraining the third classifier with the teaching sample dataset in conjunction with a subset of the labeled dataset.

Abstract: A variational quantum algorithm is solved using two types of quantum processing units (QPU) with different performance metrics (e.g., speed, size and fidelity). One type of quantum processing unit (QPU) is used to optimize some or all of the circuit parameters in a first stage, and these are then used with a different type QPU in a second stage to solve the target problem. The different performance metrics permit tradeoffs between the two stages.

Abstract: An information recommendation method and a related device. The method includes: receiving first recommended information recommended by a server in a first time period, the first recommended information being information associated with a first type of information associated with viewed information of a user with a viewed amount not less than a first threshold and determined according to a first behavior record of the user; receiving second recommended information recommended by the server in a second time period; and receiving third recommended information recommended by the server in a third time period, the third recommended information being information associated with a second type of information associated with second viewed information of the user with a second viewed amount not less than a second threshold and determined according to a second behavior record of the user.

Abstract: A pervasive user experience capable of integrating robo-advising with human advising is discussed. Conversations and other inputs may be actively captured to identify issues with which the system may be able to assist. Inputs from multiple conversations separated in time may be correlated to identify relevant needs and goals. Recommendations and strategies may be developed and presented to the customer. When it is determined that human advising is appropriate for one or more issues, the customer may be connected to an advisor for assistance with particular issues. Transitions may be facilitated to allow customers to more efficiently return to robo-advising until human advising is again deemed appropriate.

Abstract: Techniques for artificial intelligence assisted story generation includes training a neural network with first training data that indicates text for one or more portions of a training story and second training data that indicates text for a subset of text for an immediately following portion and third training data that indicates full text for the same portion. First data is retrieved that indicates text for a first one or more portions of a different new story. Second data is also received that indicates text for a cued subset of a next portion of the new story. Third data is generated that indicates full text for the next portion of the new story based on the first data and the second data and the neural network. The third data is concatenated to the first data to produce output data that is stored.

Abstract: Aspects of the present disclosure relate to neural-based ontology generation and refinement. A set of input data can be received. A set of entities can be extracted from the set of input data using a named-entity recognition (NER) process, each entity having a corresponding label, the corresponding labels making up a label set. The label set can be compared to concepts in a set of reference ontologies. Labels that match to concepts in the set of reference ontologies can be selected as a candidate concept set. Relations associated with the candidate concepts within the set of reference ontologies can be identified as a candidate relation set. An ontology can then be generated using the candidate concept set and candidate relation set.

Abstract: Systems and associated methods are described for determining popularity of new content. The system analyzes a content item to identify at least a first and a second attribute associated with the content item. The system also identifies previously posted content items associated with the first and the second attributes. The system then determines levels of user activity associated with the previously posted content item corresponding to the first attribute over a first past time period and associated with the previously posted content item corresponding to the second attribute over a second past time period. The system then extrapolates a levels of user activity for a future time period based on the first past time period and on the second past time period. The system further determines an anticipated level of user activity associated with the content item for the future time period based on the extrapolated levels of user activity.

Abstract: Information technology resource forecasting based on time series analysis is described. A system creates multiple forecasts for an information technology resource by applying corresponding multiple time series models to first data associated with the information technology resource. The system selects a model of the multiple time series models by comparing the multiple forecasts for the information technology resource to second data associated with the information technology resource. The system outputs a forecast that is created by applying the selected model to third data associated with the information technology resource.

Abstract: The example embodiments are directed to a system and method for deploying a machine learning model using a parse-free memory allocation. In one example, the method may include one or more of receiving a request to deploy a machine learning model, in response to receiving the request, creating a memory map comprising a mapping of a data structure for storing an unpacked flat representation of the machine learning model, allocating a contiguous block of memory of the data structure that is mapped by the memory map, loading data blocks of the unpacked flat representation of the machine learning model into the allocated contiguous blocks of memory of the data structure, and storing an offset associated with the contiguous block of memory in storage.

Abstract: In some embodiments, an apparatus includes a geometric aggregator that receives data for a set of time periods and a location. The data has a first set of first metric values and a set of second metric values for each time period and lacks a mixture of Gaussian distributions. The geometric aggregator calculates a geometric aggregation of the data for each time period to produce a first metric value from a second set of first metric values, having a mixture of Gaussian distributions. The apparatus includes a Gaussian mixture model that predicts a set of Gaussian distributions, each uniquely associated with a season, within a set of histogram values for the data based on the second set of first metric values. The apparatus includes a presentation portion that produces a set of adjusted first metric values based on the set of histogram values, each uniquely associated with a season.

Abstract: A deployment manager includes storage for storing a state repository including a state transitions associated with event descriptions generated by a computing device and a computing device manager. The computing device manager obtains a new event description associated with the computing device, and a workload performed by the computing device; in response to obtaining the new event description: matches the new event description to a state transition of the state transitions; and manages the workload based on a predicted next state associated with the state transition.

Abstract: A method for executing a service sequence, comprising: selecting, by a service orchestrator, a service that is part of the service sequence; detecting, by the service orchestrator, whether a load metric exceeds a threshold; when the load metric does not exceed the threshold, executing the service to obtain a real response, and continuing execution of the service sequence based on the real response; when the load metric exceeds the threshold, identifying, by the service orchestrator, a deviation behavior identifier that is associated with the service, obtaining an estimated response for the service based on the deviation behavior identifier, and continuing execution of the service sequence based on the estimated response.

Abstract: A dynamic, distributed directed activity network comprising a directed activity control program specifying tasks to be executed including required individual task inputs and outputs, the required order of task execution, permitted parallelism in task execution, task adjacency to subsequent tasks, and reachability from each task to other tasks; a plurality of task execution agents, individual of said agents having a set of dynamically changing agent attributes and capable of executing different required tasks; a plurality of task execution controllers, each controller associated with one or more of the task execution agents with access to dynamically changing agent attributes; a directed activity controller for communicating with said task execution controllers for directing execution of said activity control program; and, a communications network supporting communication between said directed activity controller and task execution controllers for directing execution of said directed activity control program u

Abstract: A media system employs techniques to create a framework for evaluating gameplay content in a vector-space. These techniques include monitoring frames for content streams that correspond to gameplay in a game environment, determining feature-values for features associated with the frames, mapping the content streams to position vectors in the vector-space based on the feature-values, and assigning a set of position vectors in the vector-space to an area in the game environment based on a relative proximity of the set of position vectors in the vector-space.

Abstract: One embodiment provides a method, including: receiving a multi-variate time-series dataset comprising a plurality of time-dependent datasets; for each of the plurality of time-dependent datasets, segmenting each of the plurality of time-dependent datasets at a transition point; clustering segments of the plurality of time-dependent datasets into clusters having similar lengths of segments; for each cluster (i) selecting a representative segment length and (ii) identifying a feature subset in that cluster; identifying, across the feature subsets, subset transition points, wherein each of the subset transition points corresponds to a change in value that meets a predetermined threshold within its corresponding feature subset; and determining, by applying a threshold test to the subset transition points, a segment length to be used in segmenting the entire multi-variate time-series dataset.

Abstract: According to some aspects, disclosed methods and systems may include having a user input one or more speech commands into an input device of a user device. The user device may communicate with one or more components or devices at a local office or headend. The local office or the user device may transcribe the speech commands into language transcriptions. The local office or the user device may determine a mood for the user based on whether any of the speech commands may have been repeated. The local office or the user device may determine, based on the mood of the user, which content asset or content service to make available to the user device.

Abstract: A method, computer program product, and computer system for applying deductive artificial intelligence (AI) attribution and auditability to data inputs, wherein the deductive AI may account for ontologies and competing system information, and wherein the deductive AI attribution and auditability may be applied to the data inputs by user workflow. The data inputs applied with the deductive AI attribution and auditability may be processed via a feedback loop to align a sense-understand-decide-act (SUDA) understanding with an inductive AI understanding. The inductive AI may be automated via the feedback loop based upon, at least in part, an AI expert system processing of the data inputs. One or more policy based rules may be developed for user automation authorization based upon, at least in part, the feedback loop.

Abstract: A subgraph storage memory stores subgraphs populated with data classified into features based on data title; each of the subgraphs has a plurality of elements; each of the elements has a features with different values. For each subfeature of a plurality of subfeatures, the different values assigned to a combination of one of the elements and one or more features are used to create a method to evaluate the subgraphs on the one or more features, as a subfeature which provides scoring information on a subgraph. For each metafeature, plural subfeatures among the plurality of subfeatures are selected to be composited into the metafeature; and for each subgraph, the plural subfeatures of each metafeature are composited to provide metafeature scores. Selected subgraphs in a universe of subgraphs with metafeature scores are presented as context for comparing the selected subgraphs; each of the selected subgraphs has different selections of elements.

Abstract: A method for identifying a category of offerings can include receiving, by a data management platform (DMP) executing on a computing platform, user data for a user of an end-user device. The method can also include mapping, by the DMP, identifiers (IDs) from received user data for the user to a plurality of different categories of offerings, wherein a particular category of offerings of the plurality of different categories of offerings corresponds to a leading commerce stream executed by the user. The method can also include matching, by the DMP, the category of the leading commerce stream to a second category of offerings for a following commerce stream based on commerce data characterizing a plurality of commerce streams executed in a window of time. The method can further include providing, by the DMP, the second category of offerings.

Abstract: A method, a structure, and a computer system for tangible mixed reality. Exemplary embodiments may include identifying one or more real objects within an environment and identifying one or more interactions between the one or more real objects, one or more reactive objects, and one or more animations therebetween. The exemplary embodiments may further include generating one or more learning activities for a user of a mixed reality headset that include at least one of the one or more interactions, and deploying the one or more learning activities to the mixed reality headset.

Abstract: A method for analyzing neuropharmacology of a drug, including the steps of providing a set of brain activity maps representing changes of a brain activity of a living species under an influence of a plurality of known drugs each consisting of a known chemical structure; clustering the set of brain activity maps to form a plurality of functional classifiers; and classifying a brain activity map associated with a chemical compound using the functional classifiers so as to predict a neuropharmacology of the chemical compound.

Abstract: An unsteadiness detection device (30) is provided which is capable of detecting the operation state of facilities using binary digital signals, the unsteadiness detection device including: a model generation unit (313) to generate a normal model for determining operation states of a plurality of facilities (11) on the basis of operation data which are binary digital signals obtained from the facilities (11) in their steady operation states; an expectation value calculation unit (315) to calculate an expectation value of operation data by applying the normal model to past operation data of the facilities (11); and an unsteadiness detection unit (316) to detect whether or not an operation state of one of the facilities (11) is unsteady by comparing the expectation value of the operation data and a measured value of the operation data.