Abstract: Methods and systems for anomaly detection include encoding a multivariate time series and a multi-type event sequence using respective transformers and an aggregation network to generate a feature vector. Anomaly detection is performed using the feature vector to identify an anomaly within a system. A corrective action is performed responsive to the anomaly to correct or mitigate an effect of the anomaly. The detected anomaly can be used in a healthcare context to support decision making by medical professionals with respect to the treatment of a patient. The encoding may include machine learning models to implement the transformers and the aggregation network using deep learning.

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 computer-implemented method for identifying root cause failure and fault events is provided. The method includes detecting a trigger point, converting, via an encoder, previous system state data, new batch data in a next system state, and a causal graph to system state-invariant embeddings and system state-dependent embeddings, generating a learned causal graph, via a graph generation layer, by integrating state-invariant and state-dependent information, and predicting, by a prediction layer, future time-series data on the learned causal graph.

Abstract: A computer-implemented method for employing a graph-based adaptive domain generation framework is provided. The method includes, in a training phase, performing domain prototypical network training on source domains, constructing an autoencoding domain relation graph by applying a graph autoencoder to produce domain node embeddings, and performing, via a domain-adaptive classifier, domain-adaptive classifier training to make an informed decision. The method further includes, in a testing phase, given testing samples from a new source domain, computing a prototype by using a pretrained domain prototypical network, inferring node embedding, and making a prediction by the domain-adaptive classifier based on the domain node embeddings.

Abstract: A computer-implemented method for locating root causes is provided. The method includes detecting a trigger point from entity metrics data and key performance indicator (KPI) data, generating a learned causal graph by fusing a state-invariant causal graph with a state-dependent causal graph, and locating the root causes by employing a random walk-based technique to estimate a probability score for each of the entity metrics data by starting from a KPI node.

Abstract: A computer-implemented method for detecting trigger points to identify root cause failure and fault events is provided. The method includes collecting, by a monitoring agent, entity metrics data and system key performance indicator (KPI) data, integrating the entity metrics data and the KPI data, constructing an initial system state space, detecting system state changes by calculating a distance between current batch data and an initial state, and dividing a system status into different states.

Abstract: A method interprets a convolutional sequence model. The method converts an input data sequence having input segments into output features. The method clusters the input segments into clusters using respective resolution-controllable class prototypes allocated to each of classes. Each respective class prototype includes a respective output feature subset characterizing a respective associated class. The method calculates, using the clusters, similarity scores that indicate a similarity of an output feature to a respective class prototypes responsive to distances between the output feature and the respective class prototypes. The method concatenates the similarity scores to obtain a similarity vector. The method performs a prediction and prediction support operation that provides a value of prediction and an interpretation for the value responsive to the input segments and similarity vector.

Abstract: A method interprets a convolutional sequence model. The method converts an input data sequence having input segments into output features. The method clusters the input segments into clusters using respective resolution-controllable class prototypes allocated to each of classes. Each respective class prototype includes a respective output feature subset characterizing a respective associated class. The method calculates, using the clusters, similarity scores that indicate a similarity of an output feature to a respective class prototypes responsive to distances between the output feature and the respective class prototypes. The method concatenates the similarity scores to obtain a similarity vector. The method performs a prediction and prediction support operation that provides a value of prediction and an interpretation for the value responsive to the input segments and similarity vector.

Abstract: A method interprets a convolutional sequence model. The method converts an input data sequence having input segments into output features. The method clusters the input segments into clusters using respective resolution-controllable class prototypes allocated to each of classes. Each respective class prototype includes a respective output feature subset characterizing a respective associated class. The method calculates, using the clusters, similarity scores that indicate a similarity of an output feature to a respective class prototypes responsive to distances between the output feature and the respective class prototypes. The method concatenates the similarity scores to obtain a similarity vector. The method performs a prediction and prediction support operation that provides a value of prediction and an interpretation for the value responsive to the input segments and similarity vector.

Abstract: A method for detecting pod and node candidates from cloud computing systems representing potential root causes of failure or fault activities is presented. The method includes collecting, by a monitoring agent, multi-modality data including key performance indicator (KPI) data, metrics data, and log data, employing a feature extractor and representation learner to convert the log data to time series data, applying a metric prioritizer based on extreme value theory to prioritize metrics for root cause analysis and learn an importance of different metrics, ranking root causes of failure or fault activities by using a hierarchical graph neural network, and generating one or more root cause reports outlining the potential root causes of failure or fault activities.

Abstract: A method for employing root cause analysis is presented. The method includes embedding, by an embedding layer, a sequence of events into a low-dimension space, employing a feature extractor and representation learner to convert log data from the sequence of events to time series data, the feature extractor including an auto-encoder model and a language model, and detecting root causes of failure or fault activities from the time series data.

Abstract: A method for detecting an origin of a computer attack given a detection point based on multi-modality data is presented. The method includes monitoring a plurality of hosts in different enterprise system entities to audit log data and metrics data, generating causal dependency graphs to learn statistical causal relationships between the different enterprise system entities based on the log data and the metrics data, detecting a computer attack by pinpointing attack detection points, backtracking from the attack detection points by employing the causal dependency graphs to locate an origin of the computer attack, and analyzing computer attack data resulting from the backtracking to prevent present and future computer attacks.

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: 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: Methods and systems for anomaly detection include determining whether a system is in a stable state or a dynamic state based on input data from one or more sensors in the system, using reconstruction errors from a respective stable model and dynamic model. It is determined that the input data represents anomalous operation of the system, responsive to a determination that the system is in a stable state, using the reconstruction errors. A corrective operation is performed on the system responsive to a determination that the input data represents anomalous operation of the system.

Abstract: Systems and methods for defect detection for vehicle operations, including collecting a multiple modality input data stream from a plurality of different types of vehicle sensors, extracting one or more features from the input data stream using a grid-based feature extractor, and retrieving spatial attributes of objects positioned in any of a plurality of cells of the grid-based feature extractor. One or more anomalies are detected based on residual scores generated by each of cross attention-based anomaly detection and time-series-based anomaly detection. One or more defects are identified based on a generated overall defect score determined by integrating the residual scores for the cross attention-based anomaly detection and the time-series based anomaly detection being above a predetermined defect score threshold. Operation of the vehicle is controlled based on the one or more defects identified.

Abstract: A method for employing a unified semi-supervised deep learning (DL) framework for turbulence forecasting is presented. The method includes extracting historical and forecasted weather features of a spatial region, calculating turbulence indexes to fill feature cubes, each feature cube representing a grid-based 3D region, and building an encoder-decoder framework based on convolutional long short-term memory (ConvLSTM) to model spatio-temporal correlations or patterns causing turbulence. The method further includes employing a dual label guessing component to dynamically integrate complementary signals from a turbulence forecasting network and a turbulence detection network to generate pseudo-labels, reweighing the generated pseudo-labels by a heuristic label quality detector based on KL-Divergence, applying a hybrid loss function to predict turbulence conditions, and generating a turbulence dataset including the predicted turbulence conditions.

Abstract: Systems and methods for data fusion and analysis of vehicle sensor data, including receiving a multiple modality input data stream from a plurality of different types of vehicle sensors, determining latent features by extracting modality-specific features from the input data stream, and aligning a distribution of the latent features of different modalities by feature-level data fusion. Classification probabilities can be determined for the latent features using a fused modality scene classifier. A tree-organized neural network can be trained to determine path probabilities and issue driving pattern judgments, with the tree-organized neural network including a soft tree model and a hard decision leaf. One or more driving pattern judgments can be issued based on a probability of possible driving patterns derived from the modality-specific features.

Abstract: A computer-implemented method for multi-model representation learning is provided. The method includes encoding, by a trained time series (TS) encoder, an input TS segment into a TS-shared latent representation and a TS-private latent representation. The method further includes generating, by a trained text generator, a natural language text that explains the input TS segment, responsive to the TS-shared latent representation, the TS-private latent representation, and a text-private latent representation.