Abstract: A method for executing a multi-task deep learning model for learning trends in multivariate time series is presented. The method includes collecting multi-variate time series data from a plurality of sensors, jointly learning both local and global contextual features for predicting a trend of the multivariate time series by employing a tensorized long short-term memory (LSTM) with adaptive shared memory (TLASM) to learn historical dependency of historical trends, and employing a multi-task one-dimensional convolutional neural network (1dCNN) to extract salient features from local raw time series data to model a short-term dependency between local time series data and subsequent trends.

Abstract: Systems and methods are provided for automated computer code editing. The method includes training a code-editing neural network model using a corpus of code editing data samples, including the pre-editing samples and post-editing samples, and parsing the pre-editing samples and post-editing samples into an Abstract Syntax Tree (AST). The method further includes using a grammar specification to transform the AST tree into a unified Abstract Syntax Description Language (ASDL) graph for different programming languages, and using a gated graph neural network (GGNN) to compute a vector representation for each node in the unified Abstract Syntax Description Language (ASDL) graph. The method further includes selecting and aggregating support samples based on a query code with a multi-extent ensemble method, and altering the query code iteratively using the pattern learned from the pre- and post-editing samples.

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 implementing electronic control unit (ECU) testing optimization includes capturing, within a neural network model, input-output relationships of a plurality of ECUs operatively coupled to a controller area network (CAN) bus within a CAN bus framework, including generating the neural network model by pruning a fully-connected neural network model based on comparisons of maximum values of neuron weights to a threshold, reducing signal connections of a plurality of collected input signals and a plurality of collected output signals based on connection weight importance, ranking importance of the plurality of collected input signals based on the neural network model, generating, based on the ranking, a test case execution sequence for testing a system including the plurality of ECUs to identify flaws in the system, and initiating the test case execution sequence for testing the system.

Abstract: Methods and systems for anomaly detection include training an anomaly detection histogram model using historical categorical value data. Training the anomaly detection histogram model includes generating a histogram template based on historical categorical data, converting the historical categorical data to a histogram using the histogram template, and determining a normal range and anomaly threshold for the categorical data using the histogram.

Abstract: The disclosure discloses a synthesis method of hexafluorophosphate, belonging to the technical field of chemical synthesis. The synthesis method of hexafluorophosphate is characterized by comprising the following steps: reacting a phosphorus pentahalide inert solvent solution obtained by dissolving phosphorus pentahalide into an inert solvent with an alkali metal fluoride salt hydrogen fluoride solution obtained by dissolving an alkali metal halide salt into anhydrous hydrogen fluoride in a reactor in a ratio to obtain a mixture consisting of hexafluorophosphate, hydrogen fluoride, the inert solvent and hydrogen halide, performing gas-liquid separation to remove a hydrogen halide gas, then heating and evaporating to recover hydrogen fluoride, finally performing solid-liquid separation to recover the inert solvent, and then drying the solid to obtain hexafluorophosphate.

Abstract: Methods and systems for anomaly correction include detecting an anomaly in a time series of categorical data values generated by a sensor, displaying a visual depiction of an anomalous time series, corresponding to the detected anomaly, on a user interface with a visual depiction of an expected normal behavior to contrast to the anomalous time series, and performing a corrective action responsive to the displayed detected anomaly. Detecting the anomaly includes framing the time series with a sliding window, generating a histogram for the categorical data values using a histogram template, generating an anomaly score for the time series using an anomaly detection histogram model on the generated histogram, and comparing the anomaly score to an anomaly threshold.

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 for computer intrusion detection. The method includes establishing a mapping from low-level system calls to user functions in computer programs. The user functions run in a user space of an operating system. The method further includes identifying, using a search algorithm inputting the mapping and a system-call trace captured at runtime, any of the user functions that trigger the low-level system calls in the system-call trace. The method further includes performing, by a processor device, intrusion detection responsive to a provenance graph with program contexts. The provenance graph has nodes formed from the user functions that trigger the low-level system calls in the system-call trace. Edges in the provenance graph have edge labels describing high-level system operations for low-level system call to high-level system operation correlation-based intrusion detection.

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 method for implementing a self-attentive encoder-decoder transformer framework for anomaly detection in event sequences is presented. The method includes feeding event content information into a content-awareness layer to generate event representations, inputting, into an encoder, event sequences of two hierarchies to capture long-term and short-term patterns and to generate feature maps, adding, in the decoder, a special sequence token at a beginning of an input sequence under detection, during a training stage, applying a one-class objective to bound the decoded special sequence token with a reconstruction loss for sequence forecasting using the generated feature maps from the encoder, and during a testing stage, labeling any event representation whose decoded special sequence token lies outside a hypersphere as an anomaly.

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: An electrochromic device, comprising a first conductive base layer, an electrochromic layer and a second conductive base layer stacked in sequence. The first conductive base layer comprises a first transparent conductive layer and a first base material layer stacked in sequence; the first transparent conductive layer is adhered to one side of the electrochromic layer; the second conductive base layer comprises a second transparent conductive layer and a second base material layer stacked in sequence; the second transparent conductive layer is adhered to the other side of the electrochromic layer; a partition groove is provided in the second transparent conductive layer for partitioning the second transparent conductive layer into a first conductive area and a second conductive area independent of each other; a conduction member is provided on the second conductive area, and the first transparent conductive layer is electrically connected to the second conductive area by the conduction member.

Abstract: A method for multivariate time series prediction is provided. Each time series from among a batch of multiple driving time series and a target time series is decomposed into a raw component, a shape component, and a trend component. For each decomposed component, select a driving time series relevant thereto from the batch and obtain hidden features of the selected driving time series, by applying the batch to an input attention-based encoder of an Ensemble of Clustered dual-stage attention-based Recurrent Neural Networks (EC-DARNNS). Automatically cluster the hidden features in a hidden space using a temporal attention-based decoder of the EC-DARNNS. Each Clustered dual-stage attention-based RNN in the Ensemble is dedicated and applied to a respective one of the decomposed components. Predict a respective value of one or more future time steps for the target series based on respective prediction outputs for each of the decomposed components by the EC-DARNNS.

Abstract: Methods and systems for optimizing performance of a cyber-physical system include training a machine learning model, according to sensor data from the cyber-physical system, to generate one or more parameters for controllable sensors in the cyber-physical system that optimize a performance indicator. New sensor data is collected from the cyber-physical system. One or more parameters for the controllable sensors are generated using the trained machine learning module and the new sensor data. The one or more parameters are applied to the controllable sensors to optimize the performance of the cyber-physical system.

Abstract: A failure prediction system is provided. The system includes a model-based signature generator generating feature vectors from individual attributes of multi-variate time series data based on sequence importance and attribute importance. The system further includes a knowledge database storing feature vectors corresponding to a set of different failure types. The system also includes a set of similarity detectors. Each detect any of the feature vectors generated by the model-based signature generator that are similar to any of the feature vectors corresponding to a respective one of the different failure types stored in the knowledge database based on a similarity threshold and output the respective one of the different failure types and a likely time period when the respective one of the different failure types will occur.

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: A method for employing a differentiable ranking based graph sparsification (DRGS) network to use supervision signals from downstream tasks to guide graph sparsification is presented. The method includes, in a training phase, generating node representations by neighborhood aggregation operators, generating sparsified subgraphs by top-k neighbor sampling from a learned neighborhood ranking distribution, feeding the sparsified subgraphs to a task, generating a prediction, and collecting a prediction error to update parameters in the generating and feeding steps to minimize an error, and, in a testing phase, generating node representations by neighborhood aggregation operators related to testing data, generating sparsified subgraphs by top-k neighbor sampling from a learned neighborhood ranking distribution related to the testing data, feeding the sparsified subgraphs related to the testing data to a task, and outputting prediction results to a visualization device.