Interpretable Temporal GANs for Imbalanced Multivariate Time Series Classification
Explore the source record for details and available documents.
97 MATHEMATICS AND COMPUTING↗
SEARCH · Engineering Papers
Results for “Multivariate time series”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
AI-Enabled Operations at Fermi Complex: Multivariate Time Series Prediction for Outage Prediction and Diagnosis
The Main Control Room of the Fermilab accelerator complex continuously gathers extensive time-series data from thousands of sensors monitoring the beam. However, unplanned events such as trips or voltage fluctuations often result in beam outages, causing operational downtime. This downtime not only consumes operator effort in diagnosing and addressing the issue but also leads to unnecessary energy consumption by idle machines awaiting beam restoration. The current threshold-based alarm system is reactive and faces challenges including frequent false alarms and inconsistent outage-cause labeling. To address these limitations, we propose an AI-enabled framework that leverages predictive analytics and automated labeling. Using data from $2,703$ Linac devices and $80$ operator-labeled outages, we evaluate state-of-the-art deep learning architectures, including recurrent, attention-based, and linear models, for beam outage prediction. Additionally, we assess a Random Forest-based labeling system for providing consistent, confidence-scored outage annotations. Our findings highlight the strengths and weaknesses of these architectures for beam outage prediction and identify critical gaps that must be addressed to fully harness AI for transitioning downtime handling from reactive to predictive, ultimately reducing downtime and improving decision-making in accelerator management.
Jain, Milan [PNL, Richland] (ORCID:000000021676111↗
Multivariate Time Series Clustering for HPC Performance Monitoring
Using DTW for HPC / LDMS data clustering
Schwaller, Benjamin↗
Learning the Temporal Effect in Infrared Thermal Videos With Long Short-Term Memory for Quality Prediction in Resistance Spot Welding
With the advances of sensing technology, in-situ infrared thermal videos can be collected from Resistance Spot Welding (RSW) processes. Each video records the formulation process of a weld nugget. The nugget evolution creates a “temporal effect” across the frames, which can be leveraged for real-time, nondestructive evaluation (NDE) of the weld quality. Currently, quality prediction with imaging data mainly focuses on optical feature extraction with Convolutional Neural Network (CNN) but does not make the most of such temporal effect. In this study, pixels corresponding to critical locations on the weld nugget surface are extracted from a video to form multivariate time series (MTS). Multivariate Adaptive Regression Splines (MARS) is used in MTS processing to remove noisy signals related to uninformative frames. A Stacked Long Short-Term Memory (LSTM) model is developed to learn from the processed MTS and then predicts weld nugget size and thickness in real-time NDE. Results from a case study on RSW of Boron steel demonstrates the improvement in prediction accuracy and computational time with the proposed method, as compared to CNN-based weld quality prediction.
Guo, Shenghan↗
Discrete Graph Structure Learning for Forecasting Multiple Time Series
Time series forecasting is an extensively studied subject in statistics, economics, and computer science. Exploration of the correlation and causation among the variables in a multivariate time series shows promise in enhancing the performance of a time series model. When using deep neural networks as forecasting models, we hypothesize that exploiting the pairwise information among multiple (multivariate) time series also improves their forecast. If an explicit graph structure is known, graph neural networks (GNNs) have been demonstrated as powerful tools to exploit the structure. In this work, we propose learning the structure simultaneously with the GNN if the graph is unknown. We cast the problem as learning a probabilistic graph model through optimizing the mean performance over the graph distribution. The distribution is parameterized by a neural network so that discrete graphs can be sampled differentiably through reparameterization. Empirical evaluations show that our method is simpler, more efficient, and better performing than a recently proposed bilevel learning approach for graph structure learning, as well as a broad array of forecasting models, either deep or non-deep learning based, and graph or non-graph based.
Shang, Chao↗
PlasmoData.jl — A Julia framework for modeling and analyzing complex data as graphs
Datasets encountered in scientific and engineering applications appear in complex formats (e.g., images, multivariate time series, molecules, video, text strings, networks). Graph theory provides a unifying framework to model such datasets and enables the use of powerful tools that can help analyze, visualize, and extract value from data. In this work, we present PlasmoData.jl, an open-source, Julia framework that uses concepts of graph theory to facilitate the modeling and analysis of complex datasets. The core of our framework is a general data modeling abstraction, which we call a DataGraph. We show how the abstraction and software implementation can be used to represent diverse data objects as graphs and to enable the use of tools from topology, graph theory, and machine learning (e.g., graph neural networks) to conduct a variety of tasks. We illustrate the versatility of the framework by using real datasets: (i) an image classification problem using topological data analysis to extract features from the graph model to train machine learning models; (ii) a disease outbreak problem where we model multivariate time series as graphs to detect abnormal events; and (iii) a technology pathway analysis problem where we highlight how we can use graphs to navigate connectivity. Further, our discussion also highlights how PlasmoData.jl leverages native Julia capabilities to enable compact syntax, scalable computations, and interfaces with diverse packages. Overall, we show that the DataGraph abstraction and PlasmoData.jl Julia package are able to model data within graphs and enable useful analysis.
96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
Short-term Classification of Strong Solar Energetic Particle Events Using Multivariate Time-series Classifiers
Explore the source record for details and available documents.
Sumanth A. Rotti↗
Long-term missing value imputation for time series data using deep neural networks
We present an approach that uses a deep learning model, in particular, a MultiLayer Perceptron, for estimating the missing values of a variable in multivariate time series data. We focus on filling a long continuous gap (e.g., multiple months of missing daily observations) rather than on individual randomly missing observations. Our proposed gap filling algorithm uses an automated method for determining the optimal MLP model architecture, thus allowing for optimal prediction performance for the given time series. We tested our approach by filling gaps of various lengths (three months to three years) in three environmental datasets with different time series characteristics, namely daily groundwater levels, daily soil moisture, and hourly Net Ecosystem Exchange. We compared the accuracy of the gap-filled values obtained with our approach to the widely used R-based time series gap filling methods ImputeTS and mtsdi. The results indicate that using an MLP for filling a large gap leads to better results, especially when the data behave nonlinearly. Thus, our approach enables the use of datasets that have a large gap in one variable, which is common in many long-term environmental monitoring observations.
97 MATHEMATICS AND COMPUTING↗
Using Signal Clustering Similarity for Detecting CAN Masquerade Attacks
The computer code assumes that time series representing the physical signals of the vehicle have been extracted from the CAN bus. The main input of the computer code is the multivariate time series representation of the signals in the CAN bus. The computer code cluster these time series using agglomerative hierarchical clustering from benign and attack datasets. Based on this, it generates probability distributions from the similarity of the obtained clusters based in each scenario---benign and attack---using the CluSim method (https://github.com/Hoosier-Clusters/clusim). Finally, it compares how a new data collection compares with the previous distribution to provide and probability score for an intrusion.
Moriano, Pablo↗
TICC Clustering Library v.1.0
SAND2024-01234O TICC is a clustering algorithm that labels a sequence of data points according to numerical properties. This library is a Python implementation of the algorithm described in "Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data" (Hallac et al. 2017). It includes documentation, performance improvements, examples, and test coverage. This library allows users to automatically segment a series of multivariate data points according to their covariance—that is, the way the values at each data point are changing in relation to one another. This is useful for identifying periods in which a system is behaving. For example, if a sensor is measuring a car's velocity, steering wheel angle, braking and acceleration, TICC can determine when the car was stopped, beginning/exiting a turn, slowing or accelerating at an intersection, or driving on straight or curved roads. TICC can be applied to measure multiple quantities at known times. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525
Dalbey, Keith↗
Studies in Astronomical Time Series Analysis. VI. Bayesian Block Representations
This paper addresses the problem of detecting and characterizing local variability in time series and other forms of sequential data. The goal is to identify and characterize statistically significant variations, at the same time suppressing the inevitable corrupting observational errors. We present a simple nonparametric modeling technique and an algorithm implementing it-an improved and generalized version of Bayesian Blocks [Scargle 1998]-that finds the optimal segmentation of the data in the observation interval. The structure of the algorithm allows it to be used in either a real-time trigger mode, or a retrospective mode. Maximum likelihood or marginal posterior functions to measure model fitness are presented for events, binned counts, and measurements at arbitrary times with known error distributions. Problems addressed include those connected with data gaps, variable exposure, extension to piece- wise linear and piecewise exponential representations, multivariate time series data, analysis of variance, data on the circle, other data modes, and dispersed data. Simulations provide evidence that the detection efficiency for weak signals is close to a theoretical asymptotic limit derived by [Arias-Castro, Donoho and Huo 2003]. In the spirit of Reproducible Research [Donoho et al. (2008)] all of the code and data necessary to reproduce all of the figures in this paper are included as auxiliary material.
signal detection↗
Long–short-term memory encoder–decoder with regularized hidden dynamics for fault detection in industrial processes
The ability of recurrent neural networks (RNN) to model nonlinear dynamics of high dimensional process data has enabled data-driven RNN-based fault detection algorithms. Previous studies have focused on detecting faults by identifying the discrepancies in data distribution between the faulty and normal data, as reflected in prediction errors generated by RNN models. However, in industrial processes, variations in data distribution can also result from changes in normal control setpoints and compensatory control adjustments in response to disturbances, making it hard to differentiate between normal and faulty conditions. This paper proposes a fault detection method utilizing a long short-term memory (LSTM) encoder–decoder structure with regularized hidden dynamics and reversible instance normalization (RevIN) to compactly represent high-dimensional measurements for effective monitoring. During training, the hidden states of the model are regularized to form a low-dimensional latent space representation of the original multivariate time series data. As a result, the prediction errors of the latent states can be used to monitor the abnormal dynamic variations, while the reconstruction errors of the measured variables are used to monitor the abnormal static variations. Furthermore, the proposed indices can reflect operating conditions, even when the distribution of test data changes, which helps distinguish faults from normal adjustments and disturbances that controllers can settle. Here, data from numerical simulation and the Tennessee Eastman process are used to illustrate the effectiveness of the proposed fault detection method.
42 ENGINEERING↗
Data augmentation for disruption prediction via robust surrogate models
The goal of this work is to generate large statistically representative data sets to train machine learning models for disruption prediction provided by data from few existing discharges. Such a comprehensive training database is important to achieve satisfying and reliable prediction results in artificial neural network classifiers. Here, we aim for a robust augmentation of the training database for multivariate time series data using Student t process regression. We apply Student t process regression in a state space formulation via Bayesian filtering to tackle challenges imposed by outliers and noise in the training data set and to reduce the computational complexity. Thus, the method can also be used if the time resolution is high. We use an uncorrelated model for each dimension and impose correlations afterwards via colouring transformations. We demonstrate the efficacy of our approach on plasma diagnostics data of three different disruption classes from the DIII-D tokamak. To evaluate if the distribution of the generated data is similar to the training data, we additionally perform statistical analyses using methods from time series analysis, descriptive statistics and classic machine learning clustering algorithms.
70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
CHMMPP: A c++ library for constrained Hidden Markov Models
SAND2024-13027O The CHMMPP: A c++ Library for Constrained Hidden Markov Models (HMM) software supports the analysis of multivariate time series data to detect patterns using HMM. Many applications involve the detection and characterization of hidden or latent states in a complex system using observable states and variables. This software supports inference of latent states integrating both an HMM and application-specific constraints that reflect known relationships in hidden states. The CHMMPP software supports application-specific and generic methods for constrained inference. This includes a framework for customized Viterbi methods, constrained inference of hidden states with A* and integer programming methods, and various constraint-informed methods for learning HMM model parameters. CHMMPP focuses on supporting generic methods that enable the agile expression of complex sets of constraints that naturally arise in many real-world applications.
Hart, William↗
Latent Stochastic Differential Equations for Modeling Quasar Variability and Inferring Black Hole Properties
Quasars are bright and unobscured active galactic nuclei (AGN) thought to be powered by the accretion of matter around supermassive black holes at the centers of galaxies. The temporal variability of a quasar’s brightness contains valuable information about its physical properties. The UV/optical variability is thought to be a stochastic process, often represented as a damped random walk described by a stochastic differential equation (SDE). Upcoming wide-field telescopes such as the Rubin Observatory Legacy Survey of Space and Time (LSST) are expected to observe tens of millions of AGN in multiple filters over a ten year period, so there is a need for efficient and automated modeling techniques that can handle the large volume of data. Latent SDEs are machine learning models well suited for modeling quasar variability, as they can explicitly capture the underlying stochastic dynamics. In this work, we adapt latent SDEs to jointly reconstruct multivariate quasar light curves and infer their physical properties such as the black hole mass, inclination angle, and temperature slope. Our model is trained on realistic simulations of LSST ten year quasar light curves, and we demonstrate its ability to reconstruct quasar light curves even in the presence of long seasonal gaps and irregular sampling across different bands, outperforming a multioutput Gaussian process regression baseline. Our method has the potential to provide a deeper understanding of the physical properties of quasars and is applicable to a wide range of other multivariate time series with missing data and irregular sampling.
79 ASTRONOMY AND ASTROPHYSICS↗
Joint Modeling of Quasar Variability and Accretion Disk Reprocessing Using Latent Stochastic Differential Equations
Quasars are bright active galactic nuclei powered by the accretion of matter around supermassive black holes at the center of galaxies. Their stochastic brightness variability depends on the physical properties of the accretion disk and black hole. The upcoming Rubin Observatory Legacy Survey of Space and Time (LSST) is expected to observe tens of millions of quasars, so there is a need for efficient techniques like machine learning that can handle the large volume of data. Quasar variability is believed to be driven by an X-ray corona, which is reprocessed by the accretion disk and emitted as UV/optical variability. We are the first to introduce an auto-differentiable simulation of the accretion disk and reprocessing. We use the simulation as a direct component of our neural network to jointly model the driving variability and reprocessing, trained with supervised learning on simulated LSST-like 10 yr quasar light curves. We encode the light curves using a transformer encoder, and the driving variability is reconstructed using latent stochastic differential equations, a physically motivated generative deep learning method that can model continuous-time stochastic dynamics. By embedding the physical processes of the driving signal and reprocessing into our network, we achieve a model that is more robust and interpretable. We demonstrate that our model outperforms a Gaussian process regression baseline and can infer accretion disk parameters and time delays between wave bands, even for out-of-distribution driving signals. Our approach provides a powerful framework that can be adapted to solve other inverse problems in multivariate time series.
Fagin, Joshua [City Univ. of New York (CUNY), NY (↗
Data augmentation for disruption prediction via robust surrogate models
The goal of this work is to generate large statistically representative datasets to train machine learning models for disruption prediction provided by data from few existing discharges. Such a comprehensive training database is important to achieve satisfying and reliable prediction results in artificial neural network classifiers. Here, we aim for a robust augmentation of the training database for multivariate time series data using Student-t process regression. We apply Student-t process regression in a state space formulation via Bayesian filtering to tackle challenges imposed by outliers and noise in the training data set and to reduce the computational complexity. Thus, the method can also be used if the time resolution is high. We use an uncorrelated model for each dimension and impose correlations afterwards via coloring transformations. We demonstrate the efficacy of our approach on plasma diagnostics data of three different disruption classes from the DIII-D tokamak. To evaluate if the distribution of the generated data is similar to the training data, we additionally perform statistical analyses using methods from time series analysis, descriptive statistics, and classic machine learning clustering algorithms.
97 MATHEMATICS AND COMPUTING↗
Spatial estimation from remotely sensed data via empirical Bayes models
Multichannel satellite image data, available as LANDSAT imagery, are recorded as a multivariate time series (four channels, multiple passovers) in two spatial dimensions. The application of parametric empirical Bayes theory to classification of, and estimating the probability of, each crop type at each of a large number of pixels is considered. This theory involves both the probability distribution of imagery data, conditional on crop types, and the prior spatial distribution of crop types. For the latter Markov models indexed by estimable parameters are used. A broad outline of the general theory reveals several questions for further research. Some detailed results are given for the special case of two crop types when only a line transect is analyzed. Finally, the estimation of an underlying continuous process on the lattice is discussed which would be applicable to such quantities as crop yield.
Hill, J. R.↗