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: Systems and methods for fault detection in a sensor network include receiving sensor data from sensors in the sensor network with a communication device. The sensor data is analyze to determine if the sensor data is indicative of a fault with a fault detection model, the fault detection model including; predicting the sensor data with an autoencoder by encoding the sensor data and decoding encoded the sensor data, autoregressively model the sensor data with an autoregressor, combining the modeled sensor data and the predicted sensor data with a combiner to produce reconstructed sensor data, and comparing the reconstructed sensor data to the sensor data with an anomaly evaluator to determine anomalies. An anomaly classification is produced by comparing the anomalies to historical anomalies with an anomaly classifier. Faults in the sensor network are automatically mitigated with a processing device based on the anomaly classification.

Abstract: A method is provided. Intermediate audio features are generated from respective segments of an input acoustic time series for a same scene. Using a nearest neighbor search, respective segments of the input acoustic time series are classified based on the intermediate audio features to generate a final intermediate feature as a classification for the input acoustic time series. Each respective segment corresponds to a respective different acoustic window. The generating step includes learning the intermediate audio features from Multi-Frequency Cepstral Component (MFCC) features extracted from the input acoustic time series, dividing the same scene into the different windows having varying MFCC features, and feeding the MFCC features of each window into respective LSTM units such that a hidden state of each respective LSTM unit is passed through an attention layer to identify feature correlations between hidden states at different time steps corresponding to different ones of the different windows.

Abstract: Systems and methods for augmenting data sets is provided. The systems and methods includes feeding an original document into a data augmentation generator to produce one or more augmented documents; calculating a contrastive loss between the original document and the one or more augmented documents; and using the original document and the one or more augmented documents to train a neural network.

Abstract: A synthetic method of 9,9-bis[4-(2-hydroxyethoxy)phenyl]fluorene, belonging to the technical field of chemical synthesis. 9-fluorenone, phenoxyethanol, a catalyst and a cocatalyst are stiffed in an alkane solvent and heated until refluxing, the generated water is removed from the reaction solution via an azeotropic method while reacting, the reaction solution is diluted with water after the reaction is ended, uniformly stirred and cooled to separate out crystals and then filtered, a filter cake is rinsed and dried to obtain a 9,9-bis[4-(2-hydroxyethoxy)phenyl]fluorene finished product; the filtered crystallization mother liquor is subjected to standing and layering, a water phase is removed, then an organic phase is distilled to recycle the alkane solvent, and the concentrate is rectified to recycle phenoxyethanol.

Abstract: Systems and methods for implementing sequence data based temporal behavior analysis (SDTBA) to extract features for characterizing temporal behavior of network traffic are provided. The method includes extracting communication and profile data associated with one or more devices to determine sequences of data associated with the devices. The method includes generating temporal features to model anomalous network traffic. The method also includes inputting, into an anomaly detection process for anomalous network traffic, the temporal features and the sequences of data associated with the devices and formulating a list of prediction results of anomalous network traffic associated with the devices.

Abstract: A computer-implemented method for securing software installation through deep graph learning includes extracting a new software installation graph (SIG) corresponding to a new software installation based on installation data associated with the new software installation, using at least two node embedding models to generate a first vector representation by embedding the nodes of the new SIG and inferring any embeddings for out-of-vocabulary (OOV) words corresponding to unseen pathnames, utilizing a deep graph autoencoder to reconstruct nodes of the new SIG from latent vector representations encoded by the graph LSTM, wherein reconstruction losses resulting from a difference of a second vector representation generated by the deep graph autoencoder and the first vector representation represent anomaly scores for each node, and performing anomaly detection by comparing an overall anomaly score of the anomaly scores to a threshold of normal software installation.

Abstract: A small integrated free space circulator, comprising a first polarizing beam splitter (1), a half-wave plate (2), a Faraday rotating plate (3), a beam splitter (4), a quarter-wave plate (5), and a pair of reflective plates (6, 7), wherein the first polarizing beam splitter (1), the half-wave plate (2), the Faraday rotating plate (3), and the beam splitter (4) are sequentially arranged, the quarter-wave plate (5) and the reflective plate (6) are sequentially attached to a side surface of the first polarizing beam splitter (1) adjacent to the half-wave plate (2), and the reflective plate (7) is arranged on a side surface of the beam splitter (4, 8) adjacent to or opposite to the Faraday rotating plate (3); when the reflective plate (7) is arranged on the side surface of the beam splitter (8) opposite to the Faraday rotating plate (3), the reflective plate (7) partially covers the side surface of the beam splitter (8) opposite to the Faraday rotating plate (3).

Abstract: A method for vehicle fault detection is provided. The method includes training, by a cloud module controlled by a processor device, an entity-shared modular and a shared modular connection controller. The entity-shared modular stores common knowledge for a transfer scope, and is formed from a set of sub-networks which are dynamically assembled for different target entities of a vehicle by the shared modular connection controller. The method further includes training, by an edge module controlled by another processor device, an entity-specific decoder and an entity-specific connection controller. The entity-specific decoder is for filtering entity-specific information from the common knowledge in the entity-shared modular by dynamically assembling the set of sub-networks in a manner decided by the entity specific connection controller.

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: Systems and methods for evaluating another computer system using temporal discrete event analytics are provided. The method includes generating sentences of discrete event sequences for multiple sensors. The method also includes building a sensor relationship network in response to generating the sentences of discrete event sequences. The sensor relationship network is analyzed to determine relationships between the multiple sensors. The method further includes performing fault diagnosis based on the sensor relationship network and the relationships between the multiple sensors.

Abstract: Systems and methods for contextual event sequence analysis of system failure that analyzes heterogeneous system event record logs are disclosed. The disclosure relates to analyzing event sequences for system failure in ICT and other computerized systems and determining their causes and propagation chains.

Abstract: Systems and methods for implementing a system architecture to support a trusted execution environment (TEE) with computational acceleration are provided. The method includes establishing a first trusted channel between a user application stored on an enclave and a graphics processing unit (GPU) driver loaded on a hypervisor. Establishing the first trusted channel includes leveraging page permissions in an extended page table (EPT) to isolate the first trusted channel between the enclave and the GPU driver in a physical memory of an operating system (OS). The method further includes establishing a second trusted channel between the GPU driver and a GPU device. The method also includes launching a unified TEE that includes the enclave and the hypervisor with execution of application code of the user application.

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 for detecting anomalies in a plurality of showcases are provided. A system can obtain a corresponding table between each of the plurality of showcases and at least one corresponding sensor. The system obtains information for showcase clustering. The system can include a processor device that can determine at least one cluster of showcases based on the information for showcase clustering and the corresponding table between each of the plurality of showcases and the at least one corresponding sensor. The system can build at least one model for each of the at least one cluster of showcases and detect at least one anomaly based on data from the at least one cluster of showcases and the at least one model.

Abstract: A computer-implemented method for simultaneous metric learning and variable selection in non-linear regression is presented. The computer-implemented method includes introducing a dataset and a target variable, creating a univariate neighborhood probability map for each reference point of the dataset, and determining a pairwise distance between each reference point and other points within the dataset. The computer-implemented method further includes computing a Hessian matrix of a quadratic programming (QP) problem, performing optimization of the QP problem, re-weighing data derived from the optimization of the QP problem, and performing non-linear regression on the re-weighed data.

Abstract: A method for early warning is provided. The method clusters normal historical data of normal cars into groups based on the car subsystem to which they belong. The method extracts (i) features based on group membership and (ii) feature correlations based on correlation graphs formed from the groups. The method trains an Auto-Encoder and Auto Decoder (AE&AD) model based on the features and the feature correlations to reconstruct the normal historical data with minimum reconstruction errors. The method reconstructs, using the trained AE&AD model, historical data of specific car fault types with reconstruction errors, normalizes the reconstruction errors, and selects features of the car faults with a top k large errors as fault signatures. The method reconstructs streaming data of monitored cars using the trained AE&AD model to determine streaming reconstruction errors, comparing the streaming reconstruction errors with the fault signatures to predict and provide alerts for impending known faults.

Abstract: A method for employing meta-learning based feature disentanglement to extract transferrable knowledge in an unsupervised setting is presented. The method includes identifying how to transfer prior knowledge data from a plurality of source domains to one or more target domains, extracting domain dependence features and domain agnostic features from the prior knowledge data, via a disentangle meta-controller, by discovering factors of variation within the prior knowledge data received from a data stream, and obtaining an evaluation for a downstream task, via a child network, to obtain an optimal child model and a feature disentangle strategy.

Abstract: A computer-implemented method is provided for cross-lingual transfer. The method includes randomly masking a source corpus and a target corpus to obtain a masked source corpus and a masked target corpus. The method further includes tokenizing, by pretrained Natural Language Processing (NLP) models, the masked source corpus and the masked target corpus to obtain source tokens and target tokens. The method also includes transforming the source tokens and the target tokens into a source dependency parsing tree and a target dependency parsing tree. The method additionally includes inputting the source dependency parsing tree and the target dependency parsing tree into a graph encoder pretrained on a translation language modeling task to extract common language information for transfer. The method further includes fine-tuning the graph encoder and a down-stream network for a specific NLP down-stream task.

Abstract: A method classifies missing labels. The method computes, using a neural network model trained on training data, rank-based statistics of a feature of a time series segment to attempt to select two candidate labels from the training data that the segment most likely belongs to. The method classifies the segment using k-NN-based classification applied to the training data, responsive to the two candidate labels being present in the training data. The method classifies the segment by hypothesis testing, responsive to only one candidate label being present in the training data. The method classifies the segment into a class with higher values of the rank-based statistics from among a plurality of classes with different values of the rank-based statistics, responsive to no candidate labels being present in the training data. The method corrects a prediction by an applicable one of the classifying steps by majority voting with time windows.