Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “expectation maximization”

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.

At least 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2009

A Local Scalable Distributed Expectation Maximization Algorithm for Large Peer-to-Peer Networks

This paper offers a local distributed algorithm for expectation maximization in large peer-to-peer environments. The algorithm can be used for a variety of well-known data mining tasks in a distributed environment such as clustering, anomaly detection, target tracking to name a few. This technology is crucial for many emerging peer-to-peer applications for bioinformatics, astronomy, social networking, sensor networks and web mining. Centralizing all or some of the data for building global models is impractical in such peer-to-peer environments because of the large number of data sources, the asynchronous nature of the peer-to-peer networks, and dynamic nature of the data/network. The distributed algorithm we have developed in this paper is provably-correct i.e. it converges to the same result compared to a similar centralized algorithm and can automatically adapt to changes to the data and the network. We show that the communication overhead of the algorithm is very low due to its local nature. This monitoring algorithm is then used as a feedback loop to sample data from the network and rebuild the model when it is outdated. We present thorough experimental results to verify our theoretical claims.

Bhaduri, Kanishka↗
NASA NTRS2011

Coding for Parallel Links to Maximize the Expected Value of Decodable Messages

When multiple parallel communication links are available, it is useful to consider link-utilization strategies that provide tradeoffs between reliability and throughput. Interesting cases arise when there are three or more available links. Under the model considered, the links have known probabilities of being in working order, and each link has a known capacity. The sender has a number of messages to send to the receiver. Each message has a size and a value (i.e., a worth or priority). Messages may be divided into pieces arbitrarily, and the value of each piece is proportional to its size. The goal is to choose combinations of messages to send on the links so that the expected value of the messages decodable by the receiver is maximized. There are three parts to the innovation: (1) Applying coding to parallel links under the model; (2) Linear programming formulation for finding the optimal combinations of messages to send on the links; and (3) Algorithms for assisting in finding feasible combinations of messages, as support for the linear programming formulation. There are similarities between this innovation and methods developed in the field of network coding. However, network coding has generally been concerned with either maximizing throughput in a fixed network, or robust communication of a fixed volume of data. In contrast, under this model, the throughput is expected to vary depending on the state of the network. Examples of error-correcting codes that are useful under this model but which are not needed under previous models have been found. This model can represent either a one-shot communication attempt, or a stream of communications. Under the one-shot model, message sizes and link capacities are quantities of information (e.g., measured in bits), while under the communications stream model, message sizes and link capacities are information rates (e.g., measured in bits/second). This work has the potential to increase the value of data returned from spacecraft under certain conditions.

Klimesh, Matthew A.↗
DOE OSTI2024

Source shape estimation for neutron imaging systems using convolutional neural networks

Neutron imaging systems are important diagnostic tools for characterizing the physics of inertial confinement fusion reactions at the National Ignition Facility (NIF). In particular, neutron images give diagnostic information on the size, symmetry, and shape of the fusion hot spot and surrounding cold fuel. Images are formed via collection of neutron flux from the source using a system of aperture arrays and scintillator-based detectors. Currently, reconstruction of fusion source geometry from the collected neutron images is accomplished by solving a computationally intensive maximum likelihood estimation problem via expectation maximization. In contrast, it is often useful to have simple representations of the overall source geometry that can be computed quickly. In this work, we develop convolutional neural networks (CNNs) to reconstruct the outer contours of simple source geometries. We compare the performance of the CNN for penumbral and pinhole data and provide experimental demonstrations of our methods on both non-noisy and noisy data.

Machine learning, neutron imaging, source reconstr↗
DOE OSTI2026

Cohort organized learning: clustering through agreement

In this article we describe cohort organized learning (CoOL), a method for clustering data without explicit distance or similarity computations. Herein, we will describe CoOL, derive the gradients determined by expectation maximization to train the networks, show how to monitor convergence during training and evaluate the clusters after training, and discuss a series of examples and use cases. We also discuss CoOL’s limitations and future prospects on related tasks. Because CoOL uses neural networks to estimate the clusters, it can be used to cluster any data that can be made compatible and we illustrate this on vector data and images.

clustering↗
DOE OSTI2025

A Latent-Variable Formulation of the Poisson Canonical Polyadic Tensor Model: Maximum Likelihood Estimation and Fisher Information

We establish parameter inference for the Poisson canonical polyadic (PCP) tensor model through a latent-variable formulation. Our approach exploits the observation that any random PCP tensor can be derived by marginalizing an unobservable random tensor of one dimension larger. The loglikelihood of this larger dimensional tensor, referred to as the “complete” loglikelihood, is comprised of multiple rank one PCP loglikelihoods. Using this methodology, we first derive maximum likelihood estimators for the PCP model and demonstrate that several existing algorithms for fitting non-negative matrix and tensor factorizations are Expectation-Maximization algorithms. Next, we derive the observed and expected Fisher information matrices for the PCP model. The Fisher information provides us crucial insights into the well-posedness of the tensor model, such as the role that tensor rank plays in identifiability and indeterminacy. For the special case of rank one PCP models, we demonstrate that these results are greatly simplified.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Radiation image reconstruction and uncertainty quantification using a Gaussian process prior

We propose a complete framework for Bayesian image reconstruction and uncertainty quantification based on a Gaussian process prior (GPP) to overcome limitations of maximum likelihood expectation maximization (ML-EM) image reconstruction algorithm. The prior distribution is constructed with a zero-mean Gaussian process (GP) with a choice of a covariance function, and a link function is used to map the Gaussian process to an image. Unlike many other maximum a posteriori approaches, our method offers highly interpretable hyperparamters that are selected automatically with the empirical Bayes method. Furthermore, the GP covariance function can be modified to incorporate a priori structural priors, enabling multi-modality imaging or contextual data fusion. Lastly, we illustrate that our approach lends itself to Bayesian uncertainty quantification techniques, such as the preconditioned Crank–Nicolson method and the Laplace approximation. The proposed framework is general and can be employed in most radiation image reconstruction problems, and we demonstrate it with simulated free-moving single detector radiation source imaging scenarios. We compare the reconstruction results from GPP and ML-EM, and show that the proposed method can significantly improve the image quality over ML-EM, all the while providing greater understanding of the source distribution via the uncertainty quantification capability. Furthermore, significant improvement of the image quality by incorporating a structural prior is illustrated.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Statistical modelling and Bayesian inversion for a Compton imaging system: application to radioactive source localization

Abstract This paper presents a statistical forward model for a Compton imaging system, called Compton imager. This system, under development at the University of Illinois Urbana Champaign, is a variant of Compton cameras with a single type of sensors which can simultaneously act as scatterers and absorbers. This imager is convenient for imaging situations requiring a wide field of view. The proposed statistical forward model is then used to solve the inverse problem of estimating the location and energy of point-like sources from observed data. This inverse problem is formulated and solved in a Bayesian framework by using a Metropolis within Gibbs algorithm for the estimation of the location, and an expectation-maximization algorithm for the estimation of the energy. This approach leads to more accurate estimation when compared with the deterministic standard back-projection approach, with the additional benefit of uncertainty quantification in the low photon imaging setting.

Tarpau, Cécilia (ORCID:0000000286539490)↗
DOE OSTI2025

Reconstruction of beam parameters and betatron radiation spectra measured with a Compton spectrometer

The photon flux resulting from high-energy electron beam interactions with high-field systems, such as those found in the upcoming FACET-II experiments at the SLAC National Accelerator Laboratory, yields deep insight into the electron beam’s underlying dynamics during the interaction. However, extracting this information is an intricate process. To demonstrate how to approach this challenge using modern methods, this paper utilizes simulated data that models plasma wakefield acceleration-derived betatron radiation in experiments to determine reliable methods of reconstructing key beam and beam-plasma interaction properties. For betatron radiation measurements, translating the observed 200⁢ keV to 30⁢ MeV photon double-differential energy-angle spectra obtained from an advanced Compton spectrometer requires testing multiple methods to optimize the pipeline from its response to incident electron beam information. The paper compares maximum likelihood estimation and machine learning to refine the translation of photon spectra into precise electron beam metrics, such as spot size, energy, and emittance, enhancing the understanding of beam behavior within these dense, high-field environments. We also introduce machine learning and the expected maximization algorithm to reconstruct the primary photon spectrum, employing a multilayer neural network for regression analysis of the energy and angle spectra. With appropriate modifications, the advanced methods reproduce relevant incident beam parameters with high accuracy, even for beam sizes in the <10 μ⁢m range. This capacity is critical to understanding intense beam propagation and its optimization in plasma.

Beam code development & simulation techniques↗
NASA NTRS1991

The NASA Lewis Research Center electric propulsion program

The Lewis Research Center conducts an electric propulsion program aimed at a broad class of space missions. The program is structured in an evolutionary fashion in order to both maximize expectations for the acceptance of developed concepts and accommodate anticipated developments of critical system technologies. Recent efforts have assisted in the acceptance of low power electric rockets. Primary electric propulsion concepts are also being developed for both Solar Electric Propulsion Systems and Nuclear Electric Propulsion Systems class space missions, and the paper briefly describes the concepts under evaluation for potential Space Exploration Initiative missions.

Byers, David C.↗
NASA NTRS1993

Mixed data/goal driven intelligent real-time assessment and control

We describe work in progress to develop model-based systems for real-time assessment and control of complex systems. Intelligent real-time processing must balance accuracy and response-time requirements to maximize expected performance. We use brief (probability) and goal (utility) information to guide construction of an approximate system model on which we then apply approximate inference procedures to yield timely, effective assessments and control decisions.

Dambrosio, Bruce↗
NASA NTRS1993

Power console development for NASA's electric propulsion outreach program

NASA LeRC is developing a 30 cm diameter xenon ion thruster for auxiliary and primary propulsion applications. To maximize expectations for user-acceptance of ion propulsion technology, NASA LeRC, through their Electric Propulsion Outreach Program, is providing sectors of industry with portable power consoles for operation of 5 KW-class xenon ion thrusters. This power console provides all necessary functions to permit thruster operations over a 0.5-5 KW envelope under both manual and automated control. These functions include the following: discharge, cathode heater, neutralizer keeper, and neutralizer heater currents, screen and accelerator voltages, and a gas feed system to regulate and control propellant flow to the thruster. An electronic circuit monitors screen and accelerator currents and controls arcing events. The power console was successfully integrated with the NASA 30 cm thruster.

Pinero, Luis R.↗
NASA NTRS1996

Software For Multivariate Bayesian Classification

PHD general-purpose classifier computer program. Uses Bayesian methods to classify vectors of real numbers, based on combination of statistical techniques that include multivariate density estimation, Parzen density kernels, and EM (Expectation Maximization) algorithm. By means of simple graphical interface, user trains classifier to recognize two or more classes of data and then use it to identify new data. Written in ANSI C for Unix systems and optimized for online classification applications. Embedded in another program, or runs by itself using simple graphical-user-interface. Online help files makes program easy to use.

Saul, Ronald↗
NASA NTRS1996

The NASA Electric Propulsion Program

Nearly all space missions require on-board propulsion systems and these systems typically have a major impact on spacecraft mass and cost. Electric propulsion systems offer major performance advantages over conventional chemical systems for many mission functions and the NASA Office of Space Access and Technology (OSAT) supports an extensive effort to develop the technology for high-performance, on-board electric propulsion system options to enhance and enable near- and far-term US space missions. This program includes research and development efforts on electrothermal, electrostatic, and electromagnetic propulsion system technologies to cover a wide range of potential applications. To maximize expectations of technology transfer, the program emphasizes strong interaction with the user community through a variety of cooperative and contracted approaches. This paper provides an overview of the OSAT electric propulsion program with an emphasis on recent progress and future directions.

Callahan, Lisa Wood↗
NASA NTRS1994

Operations for Learning with Graphical Models

This paper is a multidisciplinary review of empirical, statistical learning from a graphical model perspective. Well-known examples of graphical models include Bayesian net- works, directed graphs representing a Markov chain, and undirected networks representing a Markov field. These graphical models are extended to model data analysis and empirical learning using the notation of plates. Graphical operations for simplifying and manipulating a problem are provided including decomposition, differentiation, and the manipulation of probability models from the exponential family. These operations adapt existing techniques from statistics and automatic differentiation to graphs. Two standard algorithm schemes for learning are reviewed in a graphical framework: Gibbs sampling and the expectation maximization algorithm. Some algorithms are developed in this graphical framework including a generalized version of linear regression, techniques for feed-forward networks, and learning Gaussian and discrete Bayesian networks from data. The paper concludes by sketching some implications for data analysis and summarizing some popular algorithms that fall within the framework presented. The main original contributions here are the decomposition techniques and the demonstration that graphical models provide a framework for understanding and developing complex learning algorithms.

Buntine, Wray L.↗
NASA NTRS2000

On the Spatial Distribution of High Velocity Al-26 Near the Galactic Center

We present results of simulations of the distribution of 1809 keV radiation from the decay of Al-26 in the Galaxy. Recent observations of this emission line using the Gamma Ray Imaging Spectrometer (GRIS) have indicated that the bulk of the AL-26 must have a velocity of approx. 500 km/ s. We have previously shown that a velocity this large could be maintained over the 10(exp 6) year lifetime of the Al-26 if it is trapped in dust grains that are reaccelerated periodically in the ISM. Here we investigate whether a dust grain velocity of approx. 500 km/ s will produce a distribution of 1809 keV emission in latitude that is consistent with the narrow distribution seen by COMPTEL. We find that dust grain velocities in the range 275 - 1000 km/ s are able to reproduce the COMPTEL 1809 keV emission maps reconstructed using the Richardson-Lucy and Maximum Entropy image reconstruction methods while the emission map reconstructed using the Multiresolution Regularized Expectation Maximization algorithm is not well fit by any of our models. The Al-26 production rate that is needed to reproduce the observed 1809 keV intensity yields in a Galactic mass of Al-26 of approx. 1.5 - 2 solar mass which is in good agreement with both other observations and theoretical production rates.

Sturner, Steven J.↗
NASA NTRS1999

Brain segmentation and the generation of cortical surfaces

This paper describes methods for white matter segmentation in brain images and the generation of cortical surfaces from the segmentations. We have developed a system that allows a user to start with a brain volume, obtained by modalities such as MRI or cryosection, and constructs a complete digital representation of the cortical surface. The methodology consists of three basic components: local parametric modeling and Bayesian segmentation; surface generation and local quadratic coordinate fitting; and surface editing. Segmentations are computed by parametrically fitting known density functions to the histogram of the image using the expectation maximization algorithm [DLR77]. The parametric fits are obtained locally rather than globally over the whole volume to overcome local variations in gray levels. To represent the boundary of the gray and white matter we use triangulated meshes generated using isosurface generation algorithms [GH95]. A complete system of local parametric quadratic charts [JWM+95] is superimposed on the triangulated graph to facilitate smoothing and geodesic curve tracking. Algorithms for surface editing include extraction of the largest closed surface. Results for several macaque brains are presented comparing automated and hand surface generation. Copyright 1999 Academic Press.

NASA Discipline Neuroscience↗
NASA NTRS2004

Statistical analysis of geodetic networks for detecting regional events

We present an application of hidden Markov models (HMMs) to analysis of geodetic time series in Southern California. Our model fitting method uses a regularized version of the deterministic annealing expectation-maximization algorithm to ensure that model solutions are both robust and of high quality.

geodetic networks↗
NASA NTRS2004

Symmetric normal mixtures

We consider mixture density estimation under the symmetry constraint x = Az for an orthogonal matrix A. This distributional constraint implies a corresponding constraint on the mixture parameters. Focusing on the gaussian case, we derive an expectation-maximization (EM) algorithm to enforce the constraint and show results for modeling of image feature vectors.

symmetry constraint↗