Abstract: An approach to time-series data point anomaly detection is presented. Data point anomalies in time-series data can cause a cascade of incorrect predictions in a time-series data prediction model. Presented herein is an approach to decompose a time-series training data set into elementary components, such as seasonal, trend and residual. The approach determines one or more confidence intervals for elementary components of data points including level shift, variance, and outlier. From these confidence intervals, new data points are analyzed and identified as anomaly data points. The approach also prevents anomaly data points from being incorporated into a time series data prediction model, reducing prediction error in the prediction model.

Abstract: Computer implemented methods, systems, and computer program products include program code executing on a processor(s) identifies a query with low performance. The program code generates a small data environment for use in optimizing the query. The program code identifies table(s) and field(s) related to the query with low performance. The program code samples a portion of each table of the one or more tables based on, for each table, parameters of the one or more fields in each table, where the portion sampled comprises records from each table with common data traits to a whole of each table. The program code generates a small data environment comprising the portion of each table. The program code performance tests an optimized version of the query by executing it on the small data environment.

Abstract: A static multiview display and method of static multiview display operation include micro-slit scattering elements configured to reflectively scatter out the guided light from the light guide as a corresponding plurality of directional light beams that encode view pixels of a static multiview image. The static multiview display includes a light guide configured to guide light and a plurality of the micro-slit scattering elements, each micro-slit scattering element of the micro-slit scattering element plurality is configured to reflectively scatter out a different one of directional light beams having a relative intensity and a direction that encode a corresponding view pixel of the static multiview image. The micro-slit scattering elements each comprise a sloped reflective sidewall having a slope angle that is tilted away from the propagation direction of the guided light that provides the reflective scattering.

Abstract: A process includes receiving a set of static characteristics, a set of dynamic characteristics, and a health objective of a target object. A set of reference object data is retrieved and includes multiple reference objects of the same type as the target object. The reference object data includes the same data as the target object data. The dynamic data of the target object and the reference objects is parameterized over time. Each a set of dynamic characteristics for each reference object is split into a plurality of reference profiles. A set of similar reference profiles having a higher similarity metric than a remainder of the reference profiles is identified. A goal difference between the health objective of the target object and an end state of the similar reference profiles is determined. The reference profile having the smallest goal difference is identified and a corresponding health regimen is implemented.

Abstract: A display panel of a 2D/multiview switchable lenticular display may provide pixels of a composite image that includes a multiview image and a 2D image. A switchable lenticular lens array of the 2D/multiview switchable lenticular display may form the composite image from the pixels. Each switchable lenticular lens of the switchable lenticular lens array may be switchable between an ON state and an OFF state. The composite image may be provided either by using temporal mixing or by using zonal mixing. The temporal mixing may include time-multiplexing ON and OFF states of the switchable lenticular lenses of the switchable lenticular lens array. The zonal mixing may include switching different subsets of the switchable lenticular lenses corresponding to different zones of the composite image to the ON state to provide the multiview image or to the OFF state to provide the 2D image.

Abstract: A time-multiplexed multiview backlight, display, and method of time-multiplexed multiview backlight operation provide one or both of enhanced spatial resolution and enhanced angular resolution using time-multiplexing. The time-multiplexed multiview backlight includes a light guide configured to guide light as time-multiplexed guided light having different directions during different time intervals and an array of multibeam elements configured to scatter the time-multiplexed guided light as directional light beams. A first set of multibeam elements is configured to selectively scatter out the time-multiplexed guided light having the first direction and a second set of multibeam elements of the multibeam element array is configured to selectively scatter out the time-multiplexed guided light having the second direction.

Abstract: Aspects of the disclosure relate to a heat pump system having a selectable bypass flow path that allows a refrigerant to bypass an accumulator of the heat pump system. The bypass flow path may be used, for example, to reduce a pressure drop in a refrigerant, and may provide a cooling boost for a passenger compartment of a vehicle, particularly in high ambient temperature and/or solar load environments and/or during fast charging of a vehicle battery.

Abstract: A computer-implemented method for anomaly detection for a time series data is provided. Aspects include receiving a time series data including a plurality of sequential data points, calculating an expected next value for the time series data based on the plurality of sequential data points, and receiving an actual next value corresponding to the time series data. Aspects also include calculating an anomaly strength estimate based on the expected next value and the actual next value, identifying one of a plurality of anomaly detection pipelines based on the anomaly strength estimate and a portrait associated with each of the plurality of anomaly detection pipelines, and obtaining an anomaly prediction by inputting the time series data and the actual next value into the one of the plurality of anomaly detection pipelines.

Abstract: A method for improving a query performance of a query of a database application using rewrite includes introducing a database query into a database application to obtain a query result, analyzing the database query to identify index columns and a predicate column; identifying associated columns by determining if any associations exist between the index columns and the predicate column, calculating a confidence score value for each of the associated columns responsive to the associated columns and the predicate column, generating a list of associated columns with the confidence score values, generating a rewritten query by rewriting the database query based on the list of associated columns and the confidence score values and validating the rewritten query.

Abstract: Diffractive backlight fabrication employs a diffraction grating to scatter light from a light guide and define a reflective island that is aligned with the diffraction grating. A method of fabricating a diffractive backlight includes providing the light guide having the diffraction grating, diffractively scattering guided light out of the light guide using the diffraction grating to selectively expose photoresist and provide an opening in the photoresist, and depositing a reflective material into the opening to form a reflective island that is aligned with the diffraction grating. A reflective diffraction grating element of the diffractive backlight includes the diffraction grating and reflective island.

Abstract: A computer-implemented method for treating post-modeling data includes computing, sequentially for each category of a feature, a category importance (CI) value. The CI value is based on a model accuracy change when records of a category being examined are reassigned to a remaining set of categories of the feature according to a cumulative distribution of records among the remaining set of categories of the feature, wherein the remaining set of categories include all categories of the feature, except for the category being examined. A post-modeling category is performed to merge of each category having the CI value less than a CI value threshold.

Abstract: A computer-implemented method for model selection is provided. The computer-implemented method includes building models for predicting characteristics of pipeline models, receiving user specifications for pipeline model performance, defining a metric for weighing the characteristics of the pipeline models, using the metric to iteratively reduce a number of the pipeline models capable of meeting the user specifications to a reduced number of the pipeline models, determining which one pipeline model of the reduced number of the pipeline models exhibits a best capability of meeting the user specifications and deploying the one pipeline model.

Abstract: An approach to time-series data point anomaly detection may be presented. Data point anomalies in time-series data can cause a cascade of incorrect predictions in a time-series data prediction model. Presented herein may be an approach to decompose a time-series training data set into elementary components, such as seasonal, trend and residual. The approach may determine one or more confidence intervals for elementary components of data points including level shift, variance, and outlier. From these confidence intervals, new data points can be analyzed and identified as anomaly data points. The approach may also prevent anomaly data points from being incorporated into a time series data prediction model, reducing prediction error in the prediction model.

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to determining time series model stability and robustness in refreshment. The computer-implemented system can comprise a memory that can store computer executable components. The computer-implemented system can further comprise a processor that can execute the computer executable components stored in the memory, wherein the computer executable components can comprise a computation component that can employ weighted model evaluation to compute stability of time series pipelines over respective holdout datasets and a determination component that can select, based on the computed pipeline stabilities, a most stable time series pipeline.

Abstract: In an approach for post-modeling data visualization and analysis, a processor presents a first visualization of a training dataset in a first plot. Responsive to receiving a selection of a data group of the training dataset to analyze, a processor identifies three or fewer key model features of the data group of the training dataset. A processor ascertains a representative record of each key model feature of the three or fewer key model features using a Local Interpretable Model-Agnostic Explanation technique. A processor presents a second visualization of the three or fewer key model features and the representative record of each key model feature in a second plot.

Abstract: Determining whether synthetic data is sufficient for utilization in connection with one or more machine learning models. The computing device accesses a protected batch of data associated with a machine learning model. The computing device accesses a simulated batch of data, the simulated batch of data based upon but anonymizing the protected batch of data. The computing device accesses one or more comparisons of one or more variables in the protected batch of data and the simulated batch of data to obtain a similarity value. The computing device performs a machine learning function utilizing at least in-part the simulated batch of data if the similarity value exceeds a similarity threshold.

Abstract: The present disclosure provides a copper alloy material, a preparation method therefor and use thereof, and belong to the technical field of additive manufacturing. The copper alloy material provided by the present disclosure includes the following components by mass percentage: 2.0-7.0% of Cr, 1.0-5.0% of Nb, 0.1-2.0% of Ag, 0.1-0.7% of Zr, 0.02-0.3% of RE, and the balance of Cu. The RE includes the following components by mass percentage: 88-93% of La, 6-9% of Ce, 1.5-1.9% of Pr, and Nd less than or equal to 0.3%, and a sum of mass is 100%. By means of the synergistic effect among RE, Cr, Nb, Ag, Zr and Cu in the present disclosure, thermal conductivity, high-temperature creep property, high-temperature strength, and high-temperature fatigue of the copper alloy material are effectively improved, and the problem of poor high-temperature mechanical properties of a copper alloy material in the prior art is solved.

Abstract: An embodiment configures a plurality of parameters, the parameters being usable to generate artificial data from original data, the configuring adjusting a level of privacy in the artificial data. An embodiment fits a distribution type to a variable of the original data. An embodiment adjusts, using a desired level of privacy and the distribution type, a level of noise, wherein the level of noise corresponds to the desired level of privacy. An embodiment generates, using the distribution type and the level of noise, the artificial data, the artificial data achieving the desired level of privacy by including noise data corresponding to the level of noise.

Abstract: An in-situ robot material-reducing processing method and system for a hydraulic turbine top cover are provided. The method includes: S1, obtaining frequency response data of an end of a cutter controlled by a robot by performing an impact hammer test; S2, obtaining a modal parameter of the end of the cutter controlled by the robot by using a modal analysis software; S3, obtaining a damping matrix [C] and a stiffness matrix [K] by using a free vibration equation of a damped system; S4, establishing a dynamic model of a three-degree-of-freedom robot processing system; S5, obtaining a milling force coefficient of the cutter by performing a calibration experiment; S6, solving a dynamic equation; S7, drawing a lobe diagram of flutter stability of a milling process performed by the robot; and S8, obtaining stable milling process parameters according to the lobe diagram of flutter stability.