Methods and systems to provide a form of probabilistic labeling to associate an outage with a disturbance, which could itself be either known based on the available data or unknown. In the latter case, labeling is especially challenging, as it necessitates the discovery of the disturbance. One approach incorporates a statistical change-point analysis to time-series events that correspond to service tickets in the relevant geographic sub-regions. The method is calibrated to separate the regular periods from the environmental disturbance periods, under the assumption that disturbances significantly increase the rate of loss-causing events. To obtain the probability that a given loss-causing event is related to an environmental disturbance, the method leverages the difference between the rate of events expected in the absence of any disturbances (baseline) and the rate of actually observed events. In the analysis, the local disturbances are identified and estimators of their duration and magnitude are provided.

A computer system accurately selects learning data for improving a prediction accuracy of a predictor, and is connected to a database that stores a plurality of pieces of learning data and information for managing a plurality of predictors generated under different learning conditions. A target predictor is selected, an influence degree representing strength of an influence of the learning data on a prediction accuracy of the target predictor for test data is calculated for each of a plurality of pieces of test data, an influence score of the learning data is calculated for the plurality of predictors based on a plurality of influence degrees of the learning data associated with the predictors, and the learning data to be used is selected from the plurality of pieces of learning data on the basis of a plurality of the influence scores of each of the plurality of pieces of learning data.

Methods and systems are disclosed for generating optimal data predictions in time series data signals based on empirically-optimized model selection, noise filtering, and window size selection using machine learning models. For example, the system may receive a first subset of time series data. The system may receive a prediction horizon. The system may generate a feature input based on the first subset of time series data and the prediction horizon. The system may input the feature input into a machine learning model, wherein the machine learning model includes multiple components. The system may receive an output from the machine learning model. The system may generate for display, on a user interface, a prediction for the first subset of time series data at the prediction horizon based on the output.

According to an embodiment, an information processing device includes processors. The processors receive input of a plurality of pieces of input data obtained during K time periods. K is an integer equal to or greater than two. The processors estimate K first models. Each of the K first models receives input of input data and outputs output data. Each of the K first models is estimated for each period of the K time periods, using a plurality of pieces of input data obtained during the each period. The processors estimate a second model that indicates a relationship between first time parameters related to times of the K time periods, and the K first models. The processors estimate a first model corresponding to a specified second time parameter, based on the estimated second model.

A method and system for screening spectral indexes of rice resistant to bacterial. The method includes: processing spectral data of a test sample by a threshold segmentation algorithm to obtain average spectral information of each spectral image and a proportion of lesions corresponding to each spectral image; training a deep learning algorithm model based on a self-attention mechanism by using the average spectral information of each spectral image and the proportion of the corresponding lesions to construct a regression model for evaluating an area of the lesions; determining an optimal band combination and a weight value corresponding to each band in the optimal band combination based on the regression model for evaluating the area of the lesions, and then determining the spectral indexes; and identifying differences between rice of different genotypes at different times of infection by using the spectral indexes, and screening rice varieties resistant to bacterial blight.

A people flow prediction device includes a training data selection unit configured to select, in accordance with a prediction condition including a target prediction period subject to prediction, training data related to people flow data of a plurality of dates and times corresponding to the target prediction period, a prediction model creation unit configured to train, in accordance with the training data being selected, and store, in a model storage unit, a prediction model having a predetermined feature and for predicting people flow data of a predetermined date and time, and a prediction unit configured to select the prediction model from the model storage unit in accordance with the prediction condition and a permission condition related to a feature of the prediction model, and to predict people flow data under the prediction condition in accordance with the prediction model being selected.

An apparatus for predicting a body temperature is provided. The apparatus includes an external environment/activity estimation neural network configured to detect at least one facial region as a region of interest from an input thermal image of a target person to be measured, and estimate an environmental type including an external temperature and participation in physical activity based on a temperature of the at least one region of interest. The apparatus further includes a body temperature prediction neural network configured to predict a body temperature of the target person based on the environmental type estimated by the external environment/activity estimation neural network and the temperature of the at least one region of interest.

A system includes: a sequential image string input unit configured to input a sequential image string having sequentiality; a reference image selection unit configured to select one or more images from the sequential image string as reference images; a variation calculation unit configured to select an adjacent reference image adjacent to the reference image from the sequential image string and calculate a variation between the reference image and the adjacent reference image; an image information regression unit configured to calculate class confidence by regression processing with the reference image as an input; a difference image information regression unit configured to calculate class confidence by regression processing with the variation as an input; a confidence integration unit configured to integrate class confidence calculated by the image information regression unit and class confidence calculated by the difference image information regression unit; and an output unit configured to output the integrated class confidence.

A method, computer system, and computer program product are provided for detecting drift in predictive models for network devices and traffic. A plurality of streams of time-series telemetry data are obtained, the time-series telemetry data generated by network devices of a data network. The plurality of streams are analyzed to identify a subset of streams, wherein each stream of the subset of streams includes telemetry data that is substantially empirically distributed. The subset of streams of time-series data are analyzed to identify a change point. In response to identifying the change point, additional time-series data is obtained from one or more streams of the plurality of streams of time-series telemetry data. A predictive model is trained using the additional time-series data to update the predictive model and provide a trained predictive model.

A method for behavior vectorization of information de-identification, through which data concerning browsing traces, link paths, trigger events, clicks, and operation behaviors of network users on the Internet are selected by a server, a client device, or an edge device for performing a conversion/integration process. Then, the integrated data are converted into a vector. The vector represents the profile of the usage behavior of the network users. Moreover, because vectors can be quickly grouped and classified to find similar groups, it can quickly identify the network users. The server uses the supervised learning method as the base method, and uses pre-defined network behaviors for training. Also, the semi-supervised learning method or the unsupervised learning method can be employed to modify undefined network behaviors to better conform to the profile description of the network users.