SEARCH · Engineering Papers

Results for “classification problem”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 577 records · Page 32

All sources NASA NTRS DOE OSTI

NASA NTRSDate not supplied

Feature Selection in High-Dimensional Space with Applications to Gene Expression Data

Recent years have seen rapid growth in high-dimensional datasets. Most existing machine learning (ML) algorithms fail in high-dimensional settings where many features could be redundant. A critical process of feature selection is thus applied in such a setting that helps in identifying the most relevant features while removing redundant ones. With the increase in high dimensionality, one is also faced with problems of efficiency and interpretation in performing such selection methods. Therefore, this paper proposes a “novel” feature selection framework that uses an ensemble of interpretable ML algorithms to perform feature selection and the ranking of final features. Finally, this framework is applied to a gene expression dataset obtained through collaboration with the National Aeronautics and Space Administration (NASA)’s Biological and Physical Sciences (BPS) team and helps identify important and relevant genes contributing to specific target attributes through classification tasks.

Nishan Pantha↗

DOE OSTI2024

MedNAS: Multiscale Training-Free Neural Architecture Search for Medical Image Analysis

Deep neural networks have demonstrated impressive results in medical image analysis, but designing suitable architectures for each specific task is expertise dependent and time consuming. Neural architecture search (NAS) offers an effective means of discovering architectures. It has been highly successful in numerous applications, particularly in natural image classification. Yet, medical images possess unique characteristics, such as small regions and a wide variety of lesion sizes, that differentiate them from natural images. Furthermore, most current NAS methods struggle with high computational costs, especially when dealing with high-resolution image datasets. In this article, we present a novel evolutionary NAS method called multiscale training-free neural architecture search (MSTF-NAS) to address these challenges. Specifically, to accommodate the broad range of lesion region sizes in disease diagnosis, we develop a new reduction cell search space that enables the search algorithm to explicitly identify the optimal scale combination for multiscale feature extraction. Further, to overcome the issue of high computational costs, we utilize training-free indicators as performance measures for candidate architectures, which allows us to search for the optimal architecture more efficiently. More specifically, by considering the capability and simplicity of various networks, we formulate a multiobjective optimization problem that involves two training-free indicators and model complexity for candidate architectures. Extensive experiments on a large medical image benchmark and a publicly available breast cancer detection dataset are conducted. The empirical results demonstrate that our MSTF-NAS outperforms both human-designed architectures and current state-of-the-art NAS algorithms on both datasets, indicating the effectiveness of our proposed method.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2023

Revealing topology in metals using experimental protocols inspired by K-theory

Topological metals are conducting materials with gapless band structures and nontrivial edge-localized resonances. Their discovery has proven elusive because traditional topological classification methods require band gaps to define topological robustness. Inspired by recent theoretical developments that leverage techniques from the field of C*-algebras to identify topological metals, here, we directly observe topological phenomena in gapless acoustic crystals and realize a general experimental technique to demonstrate their topology. Specifically, we not only observe robust boundary-localized states in a topological acoustic metal, but also re-interpret a composite operator—mathematically derived from the K-theory of the problem—as a new Hamiltonian whose physical implementation allows us to directly observe a topological spectral flow and measure the topological invariants. Our observations and experimental protocols may offer insights for discovering topological behaviour across a wide array of artificial and natural materials that lack bulk band gaps.

36 MATERIALS SCIENCE↗

NASA NTRS1975

The mixture problem in computer mapping of terrain: Improved techniques for establishing spectral signature, atmospheric path radiance, and transmittance

The results of LANDSAT and Skylab research programs on the effects of the atmosphere on computer mapping of terrain include: (1) the concept of a ground truth map needs to be drastically revised; (2) the concept of training areas and test areas is not as simple as generally thought because of the problem of pixels that represent a mixture of terrain classes; (3) this mixture problem needs to be more widely recognized and dealt with by techniques of calculating spectral signatures of mixed classes, or by other methods; (4) atmospheric effects should be considered in computer mapping of terrain and in monitoring changes; and (5) terrain features may be used as calibration panels on the ground, from which atmospheric conditions can be determined and monitored. Results are presented of a test area in mountainous terrain of south-central Colorado for which an initial classification was made using simulated mixture-class spectral signatures and actual LANDSAT-1-MSS data.

Smedes, H. W.↗

NASA NTRS2003

A Step Beyond Simple Keyword Searches: Services Enabled by a Full Content Digital Journal Archive

The problems of managing and searching large archives of scientific journal articles can potentially be addressed through data mining and statistical techniques matured primarily for quantitative scientific data analysis. A journal paper could be represented by a multivariate descriptor, e.g., the occurrence counts of a number key technical terms or phrases (keywords), perhaps derived from a controlled vocabulary ( e . g . , the American Meteorological Society's Glossary of Meteorology) or bootstrapped from the journal archive itself. With this technique, conventional statistical classification tools can be leveraged to address challenges faced by both scientists and professional societies in knowledge management. For example, cluster analyses can be used to find bundles of "most-related" papers, and address the issue of journal bifurcation (when is a new journal necessary, and what topics should it encompass). Similarly, neural networks can be trained to predict the optimal journal (within a society's collection) in which a newly submitted paper should be published. Comparable techniques could enable very powerful end-user tools for journal searches, all premised on the view of a paper as a data point in a multidimensional descriptor space, e.g.: "find papers most similar to the one I am reading", "build a personalized subscription service, based on the content of the papers I am interested in, rather than preselected keywords", "find suitable reviewers, based on the content of their own published works", etc. Such services may represent the next "quantum leap" beyond the rudimentary search interfaces currently provided to end-users, as well as a compelling value-added component needed to bridge the print-to-digital-medium gap, and help stabilize professional societies' revenue stream during the print-to-digital transition.

Boccippio, Dennis J.↗

DOE OSTI2020

Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data

In this paper we discuss recent advances in deep convolutional neural networks (CNN) for sequence learning, which allow identifying long-range, multi-scale phenomena in long sequences, such as those found in fusion plasmas. We point out several benefits of these deep CNN architectures, such as not requiring experts such as physicists to hand-craft input data features, the ability to capture longer range dependencies compared to the more common sequence neural networks (recurrent neural networks like long short-term memory (LSTM) networks), and the comparative computational efficiency. We apply this neural network architecture to the popular problem of disruption prediction in fusion energy tokamaks, utilizing raw data from a single diagnostic, the Electron Cyclotron Emission imaging (ECEi) diagnostic from the DIII-D tokamak. Initial results trained on a large ECEi dataset show promise, achieving an F 1 -score of ~91% on individual time-slices using only the ECEi data. This indicates the ECEi diagnostic by itself can be sensitive to a number of pre-disruption markers useful for predicting disruptions on timescales not only for mitigation but also avoidance. Future opportunities for utilizing these deep CNN architectures with fusion data are outlined, including impact of recent upgrades to the ECEi diagnostic.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2022

Group-Invariant Quantum Machine Learning

Quantum machine learning (QML) models are aimed at learning from data encoded in quantum states. Recently, it has been shown that models with little to no inductive biases (i.e., with no assumptions about the problem embedded in the model) are likely to have trainability and generalization issues, especially for large problem sizes. As such, it is fundamental to develop schemes that encode as much information as available about the problem at hand. In this work we present a simple, yet powerful, framework where the underlying invariances in the data are used to build QML models that, by construction, respect those symmetries. These so-called group-invariant models produce outputs that remain invariant under the action of any element of the symmetry group $\mathfrak{G}$ associated with the dataset. We present theoretical results underpinning the design of $\mathfrak{G}$-invariant models, and exemplify their application through several paradigmatic QML classification tasks, including cases when $\mathfrak{G}$ is a continuous Lie group and also when it is a discrete symmetry group. Notably, our framework allows us to recover, in an elegant way, several well-known algorithms for the literature, as well as to discover new ones. Taken together, we expect that our results will help pave the way towards a more geometric and group-theoretic approach to QML model design.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1991

Two papers on feed-forward networks

Connectionist feed-forward networks, trained with back-propagation, can be used both for nonlinear regression and for (discrete one-of-C) classification, depending on the form of training. This report contains two papers on feed-forward networks. The papers can be read independently. They are intended for the theoretically-aware practitioner or algorithm-designer; however, they also contain a review and comparison of several learning theories so they provide a perspective for the theoretician. The first paper works through Bayesian methods to complement back-propagation in the training of feed-forward networks. The second paper addresses a problem raised by the first: how to efficiently calculate second derivatives on feed-forward networks.

Buntine, Wray L.↗

DOE OSTI2020

Artificial Intelligence Application to D and D - 20492

As aging facilities across the DOE complex await decommissioning, there is an ongoing need to understand any changes in the structural conditions. Many of these facilities were built over 50 years ago and, in some cases, these facilities have gone beyond the expected operational lifetime. Many facilities have been placed in a state of 'cold and dark,' sitting unused and awaiting decommissioning. Especially challenging are the aging facilities that provide unique operational/production capabilities to support critical DOE missions and cannot be shut down. In any of these scenarios, the structural integrity of these facilities may become compromised as time passes. It is critical that adequate inspections be performed on a continual basis and that the data collected undergoes sufficient analysis to support timely identification of any new or worsening structural issues as well as prompt needed maintenance and repairs to maintain the facilities in a safe condition. In recent days, Artificial Intelligence (AI) [1] and its application to various domains are growing at fast speed. FIU is performing research in this area and exploring the associated technologies to solve nuclear decommissioning problems. Artificial intelligence refers to the capability of a program to autonomously act, react and adapt to the working environment. AI enables the machine to behave like humans and perform the cognitive functions such as 'learning' and 'problem solving'. AI systems gradually moving from traditional approaches (algorithms and expert systems) towards more efficient and advanced technologies (machine learning [1] and deep learning [2] [3]). AI is the study of algorithms and statistical models that is being used by computers to perform specific tasks without using explicit instructions. FIU is working to develop a pilot-scale infrastructure to implement structural health monitoring using AI technologies with focus on machine learning, deep learning. This research is focused on Computer Vision/Image Classification area of AI applications. This can also be expanded to other areas of AI related to Object Recognition and Character Recognition in images. In addition to utilizing existing data sets, FIU will collect and investigate image and video data using FIU test-bed mockups to monitor structural health of the facility. Resulting data will be processed and analyzed using machine learning/deep learning technologies. The proposed pilot system is intended to serve as a starting point to engage the DOE field sites on related data sets and their decision making needs. It is anticipated that proposed machine learning/deep learning technologies can be effectively employed using anomaly detection to solve EM challenges in surveillance and maintenance of the D and D facilities. FIU will work with research stakeholders to identify applications at various sites and other DOE facilities. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

NASA NTRS2005

A Parallel Processing Algorithm for Remote Sensing Classification

A current thread in parallel computation is the use of cluster computers created by networking a few to thousands of commodity general-purpose workstation-level commuters using the Linux operating system. For example on the Medusa cluster at NASA/GSFC, this provides for super computing performance, 130 G(sub flops) (Linpack Benchmark) at moderate cost, $370K. However, to be useful for scientific computing in the area of Earth science, issues of ease of programming, access to existing scientific libraries, and portability of existing code need to be considered. In this paper, I address these issues in the context of tools for rendering earth science remote sensing data into useful products. In particular, I focus on a problem that can be decomposed into a set of independent tasks, which on a serial computer would be performed sequentially, but with a cluster computer can be performed in parallel, giving an obvious speedup. To make the ideas concrete, I consider the problem of classifying hyperspectral imagery where some ground truth is available to train the classifier. In particular I will use the Support Vector Machine (SVM) approach as applied to hyperspectral imagery. The approach will be to introduce notions about parallel computation and then to restrict the development to the SVM problem. Pseudocode (an outline of the computation) will be described and then details specific to the implementation will be given. Then timing results will be reported to show what speedups are possible using parallel computation. The paper will close with a discussion of the results.

Gualtieri, J. Anthony↗

NASA NTRS1977

Utility of correlation techniques in gravity and magnetic interpretation

Internal correspondence uses Poisson's Theorem in a moving-window linear regression analysis between the anomalous first vertical derivative of gravity and total magnetic field reduced to the pole. The regression parameters provide critical information on source characteristics. The correlation coefficient indicates the strength of the relation between magnetics and gravity. Slope value gives delta j/delta sigma estimates of the anomalous source. The intercept furnishes information on anomaly interference. Cluster analysis consists of the classification of subsets of data into groups of similarity based on correlation of selected characteristics of the anomalies. Model studies are used to illustrate implementation and interpretation procedures of these methods, particularly internal correspondence. Analysis of the results of applying these methods to data from the midcontinent and a transcontinental profile shows they can be useful in identifying crustal provinces, providing information on horizontal and vertical variations of physical properties over province size zones, validating long wavelength anomalies, and isolating geomagnetic field removal problems.

Chandler, V. W.↗

NASA NTRS1979

Adaptive remote sensing technology for feature recognition and tracking

A technology development plan designed to reduce the data load and data-management problems associated with global study and monitoring missions is described with a heavy emphasis placed on developing mission capabilities to eliminate the collection of unnecessary data. Improved data selectivity can be achieved through sensor automation correlated with the real-time needs of data users. The first phase of the plan includes the Feature Identification and Location Experiment (FILE) which is scheduled for the 1980 Shuttle flight. The FILE experiment is described with attention given to technology needs, development plan, feature recognition and classification, and cloud-snow detection/discrimination. Pointing, tracking and navigation received particular consideration, and it is concluded that this technology plan is viewed as an alternative to approaches to real-time acquisition that are based on extensive onboard format and inventory processing and reliance upon global-satellite-system navigation data.

Wilson, R. G.↗

NASA NTRS1987

Survey on large scale system control methods

The problem inherent to large scale systems such as power network, communication network and economic or ecological systems were studied. The increase in size and flexibility of future spacecraft has put those dynamical systems into the category of large scale systems, and tools specific to the class of large systems are being sought to design control systems that can guarantee more stability and better performance. Among several survey papers, reference was found to a thorough investigation on decentralized control methods. Especially helpful was the classification made of the different existing approaches to deal with large scale systems. A very similar classification is used, even though the papers surveyed are somehow different from the ones reviewed in other papers. Special attention is brought to the applicability of the existing methods to controlling large mechanical systems like large space structures. Some recent developments are added to this survey.

Mercadal, Mathieu↗

DOE OSTI2023

Finding simplicity: unsupervised discovery of features, patterns, and order parameters via shift-invariant variational autoencoders *

Abstract Recent advances in scanning tunneling and transmission electron microscopies (STM and STEM) have allowed routine generation of large volumes of imaging data containing information on the structure and functionality of materials. The experimental data sets contain signatures of long-range phenomena such as physical order parameter fields, polarization, and strain gradients in STEM, or standing electronic waves and carrier-mediated exchange interactions in STM, all superimposed onto scanning system distortions and gradual changes of contrast due to drift and/or mis-tilt effects. Correspondingly, while the human eye can readily identify certain patterns in the images such as lattice periodicities, repeating structural elements, or microstructures, their automatic extraction and classification are highly non-trivial and universal pathways to accomplish such analyses are absent. We pose that the most distinctive elements of the patterns observed in STM and (S)TEM images are similarity and (almost-) periodicity, behaviors stemming directly from the parsimony of elementary atomic structures, superimposed on the gradual changes reflective of order parameter distributions. However, the discovery of these elements via global Fourier methods is non-trivial due to variability and lack of ideal discrete translation symmetry. To address this problem, we explore the shift-invariant variational autoencoders (shift-VAEs) that allow disentangling characteristic repeating features in the images, their variations, and shifts that inevitably occur when randomly sampling the image space. Shift-VAEs balance the uncertainty in the position of the object of interest with the uncertainty in shape reconstruction. This approach is illustrated for model 1D data, and further extended to synthetic and experimental STM and STEM 2D data. We further introduce an approach for training shift-VAEs that allows finding the latent variables that comport to known physical behavior. In this specific case, the condition is that the latent variable maps should be smooth on the length scale of the atomic lattice (as expected for physical order parameters), but other conditions can be imposed. The opportunities and limitations of the shift VAE analysis for pattern discovery are elucidated.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1988

Extrema principles of entrophy production and energy dissipation in fluid mechanics

A survey is presented of several extrema principles of energy dissipation as applied to problems in fluid mechanics. An exact equation is derived for the dissipation function of a homogeneous, isotropic, Newtonian fluid, with terms associated with irreversible compression or expansion, wave radiation, and the square of the vorticity. By using entropy extrema principles, simple flows such as the incompressible channel flow and the cylindrical vortex are identified as minimal dissipative distributions. The principal notions of stability of parallel shear flows appears to be associated with a maximum dissipation condition. These different conditions are consistent with Prigogine's classification of thermodynamic states into categories of equilibrium, linear nonequilibrium, and nonlinear nonequilibrium thermodynamics; vortices and acoustic waves appear as examples of dissipative structures. The measurements of a typical periodic shear flow, the rectangular wall jet, show that direct measurements of the dissipative terms are possible.

Horne, W. Clifton↗

NASA NTRS1988

Extrema principles of entropy production and energy dissipation in fluid mechanics

A survey is presented of several extrema principles of energy dissipation as applied to problems in fluid mechanics. An exact equation is derived for the dissipation function of a homogeneous, isotropic, Newtonian fluid, with terms associated with irreversible compression or expansion, wave radiation, and the square of the vorticity. By using entropy extrema principles, simple flows such as the incompressible channel flow and the cylindrical vortex are identified as minimal dissipative distributions. The principal notions of stability of parallel shear flows appear to be associated with a maximum dissipation condition. These different conditions are consistent with Prigogine's classification of thermodynamic states into categories of equilibrium, linear nonequilibrium, and nonlinear nonequilibrium thermodynamics; vortices and acoustic waves appear as examples of dissipative structures. The measurements of a typical periodic shear flow, the rectangular wall jet, show that direct measurements of the dissipative terms are possible.

Horne, W. Clifton↗

NASA NTRS1994

The 1994 International Geoscience and Remote Sensing Symposium (IGARSS 1994)

The papers presented at the symposium focus on remote sensing, particularly on global monitoring of the earth with emphasis on the solution of environmental problems. Topics discussed include remote sensing of clouds and earth troposphere, sea ice remote sensing, optical remote sensing, land monitoring and thermal sensing, atmospheric sounding and monitoring, atmospheric correction, and satellite imaging data. Other subject areas are ecosystems and vegetation monitoring; ocean winds and surface scattering; ocean waves, currents and bathymetry; satellite oceanography; SAR for remote sensing; neural nets application to remote sensing; geographical information systems; and electromagnetic wave propagation. Also discussed environmental monitoring using ERS-1; Topex/Poseidon results; spaceborne instruments; image processing and classification algorithms; and future space missions.

Source record↗

DOE OSTI2023

Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools

Methods for model explainability have become increasingly critical for testing the fairness and soundness of deep learning. Concept-based interpretability techniques, which use a small set of human-interpretable concept exemplars in order to measure the influence of a concept on a model's internal representation of input, are an important thread in this line of research. In this work we show that these explainability methods can suffer the same vulnerability to adversarial attacks as the models they are meant to analyze. We demonstrate this phenomenon on two well-known concept-based interpretability methods: TCAV and faceted feature visualization. We show that by leveraging the geometry of the problem and carefully perturbing the examples of the concept that is being investigated, we can radically change the output of the interpretability method. The attacks that we propose can either induce positive interpretations (polka dots are an important concept for a model when classifying zebras) or negative interpretations (stripes are not an important factor in identifying images of a zebra). Our work highlights the fact that in safety-critical applications, there is need for security around not only the machine learning pipeline but also the model interpretation process.

Brown, Davis R.↗