Abstract: A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k-1 binary classifiers on top of the semi-supervised representations to obtain k-1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k-1 binary predictions by matching the inconsistent ones to consistent ones of the k-1 binary predictions. The method further includes aggregating the k-1 binary predictions to obtain an ordinal prediction.

Abstract: A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k?1 binary classifiers on top of the semi-supervised representations to obtain k?1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k?1 binary predictions by matching the inconsistent ones to consistent ones of the k?1 binary predictions. The method further includes aggregating the k?1 binary predictions to obtain an ordinal prediction.

Abstract: A method for system metric prediction and influential events identification by concurrently employing metric logs and event logs is presented. The method includes concurrently modeling multivariate metric series and individual events in event series by a multi-stream recurrent neural network (RNN) to improve prediction of future metrics, where the multi-stream RNN includes a series of RNNs, one RNN for each metric and one RNN for each event sequence and modeling causality relations between the multivariate metric series and the individual events in the event series by employing an attention mechanism to identify target events most responsible for fluctuations of one or more target metrics.

Abstract: Methods and systems of training and using a neural network model include training a time series embedding model and a text embedding model with unsupervised clustering to translate time series and text, respectively, to a shared latent space. The time series embedding model and the text embedding model are further trained using semi-supervised clustering that samples training data pairs of time series information and associated text for annotation.

Abstract: A computer implemented method is provided. The method includes jointly encoding, by a dual-channel feature extractor, a current time series segment with corresponding static statuses into a compact feature. The method further includes converting, by a binary code extractor, the compact feature into a binary code. The method also includes computing distances between the binary code and all binary codes stored in a binary code database. The method additionally includes retrieving the top relevant multivariate time series segments based on the distances.

Abstract: A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k?1 binary classifiers on top of the semi-supervised representations to obtain k?1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k?1 binary predictions by matching the inconsistent ones to consistent ones of the k?1 binary predictions. The method further includes aggregating the k?1 binary predictions to obtain an ordinal prediction.

Abstract: A first anomaly detection unit detects anomalous first monitored data from among a plurality of first monitored data obtained from a monitored system. A second anomaly detection unit operates in parallel with the first anomaly detection unit and detects anomalous second monitored data from among a plurality of second monitored data obtained from the monitored system. In a first storage unit, the anomalous first monitored data and the anomalous second monitored data detected before lapse of a given time from detection time of the anomalous first monitored data are stored in association with each other. A first determination unit, when the anomalous first monitored data is detected, retrieves the anomalous second monitored data associated with the detected anomalous first monitored data from the first storage unit and outputs a first anomaly detection result including the retrieved anomalous second monitored data and the detected anomalous first monitored data.

Abstract: Methods and systems for training a model include collecting unlabeled training data during operation of a device. A model is adapted to operational conditions of the device using the unlabeled training data. The model includes a shared encoder that is trained on labeled training data from multiple devices and further includes a device-specific decoder that is trained on labeled training data corresponding to the device.

Abstract: Systems and methods for updating a classification model of a neural network. The methods include selecting, as a set of landmarks, a limited number of data from a set of historical data used to train a classification model. Additionally, the methods generate new training data from recently collected data. Further, the methods update the classification model with the new training data and the set of landmarks to obtain an updated classification model having a loss function configured to capture similarities in the new training data and remember similarities in the historical data represented by the set of landmarks within a predefined tolerance.

Abstract: A computer-implemented method for ordinal classification of input data is provided. The method includes learning, by an encoder neural network, compact neural representations of the input data. The method further includes freezing the encoder neural network for downstream tasks. The method also includes training, by a hardware processor, K?1 ordinal classifiers on top of the compact neural representations to obtained trained K?1 ordinal classifiers. The method additionally includes generating, by the hardware processor, a predicted ordinal label by aggregating the trained K?1 ordinal classifiers.

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: A factor, other than an external factor, having an influence on a state change of a system can be correctly identified even when an external factor having a strong correlation with the state change of the system exists. In an analysis system 1, an external factor identification unit 310 identifies a first explanatory time series among a plurality of explanatory time series. A differential time series generation unit 340 generates a difference time series between a value of an objective time series and a prediction value of the objective time series calculated based on a value of the first explanatory time series. An effect degree calculation unit 420 calculates, based on second explanatory time series among the plurality of explanatory time series and the difference time series, an influence degree of each of the second explanatory time series on a value change of the difference time series.

Abstract: Methods and systems for detecting and correcting anomalies includes generating historical binary codes from historical time series segments. The historical time series segments are each made up of measurements from respective sensors. A latest binary code is generated from a latest time series segment. It is determined that the latest time series segment represents anomalous behavior, based on a comparison of the latest binary code to the historical binary codes. The sensors are ranked, based on a comparison of time series data of the sensors in the latest time series segment to respective time series data of the historical time series, to generate a sensor ranking. A corrective action is performed responsive to the detected anomaly, prioritized according to the sensor ranking.

Abstract: A system for cross-modal data retrieval is provided that includes a neural network having a time series encoder and text encoder which are jointly trained using an unsupervised training method which is based on a loss function. The loss function jointly evaluates a similarity of feature vectors of training sets of two different modalities of time series and free-form text comments and a compatibility of the time series and the free-form text comments with a word-overlap-based spectral clustering method configured to compute pseudo labels for the unsupervised training method. The computer processing system further includes a database for storing the training sets with feature vectors extracted from encodings of the training sets. The encodings are obtained by encoding a training set of the time series using the time series encoder and encoding a training set of the free-form text comments using the text encoder.

Abstract: A method for explaining sensor time series data in natural language is presented. The method includes training a neural network model with text-annotated time series data, the neural network model including a time series encoder and a text generator, allowing a human operator to select a time series segment from the text-annotated time series data, the time series segment processed by the time series encoder, outputting, from the time series encoder, a sequence of hidden state vectors, one for each timestep, and generating readable explanatory texts for the human operator based on the selected time series segment, the readable explanatory texts being a set of comment texts explaining and interpreting the selected time series segment in a plurality of different ways.

Abstract: Methods and systems for training a model include training a feature extraction model to extract a feature vector from a multivariate time series segment, based on a set of training data corresponding to measurements of a system in a first domain. Adapting the feature extraction model to a second domain, based on prototypes of the training data in the first domain and new time series data corresponding to measurements of the system in a second domain.

Abstract: Methods and systems for training a neural network include training models for respective sensor groups in a cyber-physical system. Combinations of sensor groups and operational modes are sampled. A combination model is trained for each of the sampled combinations. A best combination model is determined based on performance measured during training. The best combination model is fine-tuned.

Abstract: Methods and systems for training a neural network include collecting model exemplar information from edge devices, each model exemplar having been trained using information local to the respective edge devices. The collected model exemplar information is aggregated together using federated averaging. Global model exemplars are trained using federated constrained clustering. The trained global exemplars are transmitted to respective edge devices.

Abstract: An information processing device 100 of the present invention includes an analysis unit 121 and an encoding unit 122. The analysis unit 121 extracts a partial time-series data set obtained by dividing a time-series data set that is a set of time-series data including a plurality of elements at given time intervals, and calculates correlation data representing a correlation between elements of time-series data included in the partial time-series data set. The encoding unit 122 generates coded data based on the time-series data of the partial time-series data set and the correlation data.

Abstract: A method for system metric prediction and influential events identification by concurrently employing metric logs and event logs is presented. The method includes concurrently modeling multivariate metric series and individual events in event series by a multi-stream recurrent neural network (RNN) to improve prediction of future metrics, where the multi-stream RNN includes a series of RNNs, one RNN for each metric and one RNN for each event sequence and modeling causality relations between the multivariate metric series and the individual events in the event series by employing an attention mechanism to identify target events most responsible for fluctuations of one or more target metrics.