Search NASA⌕ Search

SEARCH · Search NASA

Results for “feature map”

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 37 records · Page 2

Sparse coding of pathology slides compared to transfer learning with deep neural networks

Background Histopathology images of tumor biopsies present unique challenges for applying machine learning to the diagnosis and treatment of cancer. The pathology slides are high resolution, often exceeding 1GB, have non-uniform dimensions, and often contain multiple tissue slices of varying sizes surrounded by large empty regions. The locations of abnormal or cancerous cells, which may constitute a small portion of any given tissue sample, are not annotated. Cancer image datasets are also extremely imbalanced, with most slides being associated with relatively common cancers. Since deep representations trained on natural photographs are unlikely to be optimal for classifying pathology slide images, which have different spectral ranges and spatial structure, we here describe an approach for learning features and inferring representations of cancer pathology slides based on sparse coding. Results We show that conventional transfer learning using a state-of-the-art deep learning architecture pre-trained on ImageNet (RESNET) and fine tuned for a binary tumor/no-tumor classification task achieved between 85% and 86% accuracy. However, when all layers up to the last convolutional layer in RESNET are replaced with a single feature map inferred via a sparse coding using a dictionary optimized for sparse reconstruction of unlabeled pathology slides, classification performance improves to over 93%, corresponding to a 54% error reduction. Conclusions We conclude that a feature dictionary optimized for biomedical imagery may in general support better classification performance than does conventional transfer learning using a dictionary pre-trained on natural images.

59 BASIC BIOLOGICAL SCIENCES↗

Yet Another Discriminant Analysis (YADA): A Probabilistic Model for Machine Learning Applications

This paper presents a probabilistic model for various machine learning (ML) applications. While deep learning (DL) has produced state-of-the-art results in many domains, DL models are complex and over-parameterized, which leads to high uncertainty about what the model has learned, as well as its decision process. Further, DL models are not probabilistic, making reasoning about their output challenging. In contrast, the proposed model, referred to as Yet Another Discriminate Analysis(YADA), is less complex than other methods, is based on a mathematically rigorous foundation, and can be utilized for a wide variety of ML tasks including classification, explainability, and uncertainty quantification. YADA is thus competitive in most cases with many state-of-the-art DL models. Ideally, a probabilistic model would represent the full joint probability distribution of its features, but doing so is often computationally expensive and intractable. Hence, many probabilistic models assume that the features are either normally distributed, mutually independent, or both, which can severely limit their performance. YADA is an intermediate model that (1) captures the marginal distributions of each variable and the pairwise correlations between variables and (2) explicitly maps features to the space of multivariate Gaussian variables. Numerous mathematical properties of the YADA model can be derived, thereby improving the theoretic underpinnings of ML. Validation of the model can be statistically verified on new or held-out data using native properties of YADA. However, there are some engineering and practical challenges that we enumerate to make YADA more useful.

97 MATHEMATICS AND COMPUTING↗

Wearable Sensor Application for Integrated Early Warning and Health Surveillance

Objective: The Wearable Sensor Application developed by Pacific Northwest National Laboratory (PNNL) provides an early warning system for stressors to individual and group health using physiologic and environmental indicators. The application integrates health monitoring parameters from wearable sensors, e.g., temperature and heart rate, with relevant environmental parameters, e.g., weather and landscape data, and calculates the corresponding physiological strain index. The information is presented to the analyst in a group and individual view with real-time alerting of abnormal health parameters. This application is the first of its kind being developed for integration into the Defense Threat Reduction Agency's Biosurveillance Ecosystem (BSVE).Introduction: Wearable devices are a low cost, minimally invasive way to monitor health. Sensor data provides real-time physiological indictors of an individual’s health status without the requirement of health care professionals or facilities. Information gleamed from wearable sensors can be used to better understand physiological stressors and prodromal symptoms. In addition, this data can be used to monitor individuals that are in high risk of health-related problems.However, raw data from wearable sensors can be overwhelming to process and laborious to monitor for an individual and, even more so, for a group of individuals. Often specific combination of ranges of sensor readings are indicative of changes to health status and need to be evaluated together or used to calculate specific signal parameters. In addition, the environment surrounding the individual needs to be considered when interpreting the data. To address these issues, PNNL has developed an application that collects, analyzes, and integrates wearable sensor data with geographic landscape and weather information to provide a real-time early alert and situational awareness tool for monitoring the health of groups and individuals.Methods: The prototype application described here was a product of PNNL’s BSVE Application Development Competition. The final product that will be deployed in the BSVE is currently under development by PNNL and will vary slightly in the exact design and architecture described.Data. Wearable sensor data was collected from the Rim2Rim (R2R) Watch Study of individuals hiking the Grand Canyon in Arizona [1]. Weather information was obtained from nearby weather stations and mapping features were derived from Google Maps.Calculations. A physiological Strain Index (PSI) was calculated using core temperature estimates derived through a Kalman Filter approach and heart rate [2,3].Application. The prototype backend application development was based in Python with a MongoDB. The front-end development was built using a scalable architecture and modular approach with components in React and D3.Results: A prototype application was developed this past summer through the PNNL BSVE App Competition (Fig 1). The application was aimed at visualizing wearable sensor data from the Grand Canyon R2R hike dataset. Simulated real-time analysis was used to calculate health status of individuals hiking based on measured physiological parameters and to alert to individuals with signs of physiologic health stress. Visualization tools were incorporated to enable sensor data for individuals and the group to be viewed simultaneously along with pertinent weather, geographic, and elevation data.Many features described in the prototype application will be incorporated into the final BSVE application. The key changes will be 1) the ability to select given time periods for viewing historical data as well as the real-time data collection, 2) environmental data and map view will come from BSVE internal data sources, and 3) the alerts will provide more information and have their own page for reviewing.Conclusions: The Wearable Sensor Application developed by PNNL for integration into the BSVE provides an early warning system for individual and group health using physiologic and environmental parameters. The application highlights health status from wearable sensors and relevant environmental parameters while monitoring a calculated physiological strain index. With this tool, an analyst can easily monitor the health of individuals and groups with the aid of real-time alerting tool for early detection of abnormal health parameters.

Early Warning↗

Dynamics of McMillan mappings III. Symmetric map with mixed nonlinearity

This article extends the study of the dynamical properties of the symmetric McMillan map, emphasizing its utility in understanding and modeling complex nonlinear systems. Although the map features six parameters, we demonstrate that only two are irreducible: the linearized rotation number at the fixed point and a nonlinear parameter representing the ratio of terms in the biquadratic invariant. Through a detailed analysis, we classify regimes of stable motion, provide exact solutions to the mapping equations, and derive a canonical set of action-angle variables, offering analytical expressions for the rotation number and nonlinear tune shift. We further establish connections between general standard-form mappings and the symmetric McMillan map, using the area-preserving Hénon map and accelerator lattices with thin sextupole magnet as representative case studies. Our results show that, despite being a second-order approximation, the symmetric McMillan map provides a highly accurate depiction of dynamics across a wide range of system parameters, demonstrating its practical relevance in both theoretical and applied contexts.

43 PARTICLE ACCELERATORS↗

SEVEN-YEAR WILKINSON MICROWAVE ANISOTROPY PROBE (WMAP ) OBSERVATIONS: ARE THERE COSMIC MICROWAVE BACKGROUND ANOMALIES?

A simple six-parameter {Lambda}CDM model provides a successful fit to WMAP data. This holds both when the WMAP data are analyzed alone or in combination with other cosmological data. Even so, it is appropriate to examine the data carefully to search for hints of deviations from the now standard model of cosmology, which includes inflation, dark energy, dark matter, baryons, and neutrinos. The cosmological community has subjected the WMAP data to extensive and varied analyses. While there is widespread agreement as to the overall success of the six-parameter {Lambda}CDM model, various 'anomalies' have been reported relative to that model. In this paper we examine potential anomalies and present analyses and assessments of their significance. In most cases we find that claimed anomalies depend on posterior selection of some aspect or subset of the data. Compared with sky simulations based on the best-fit model, one can select for low probability features of the WMAP data. Low probability features are expected, but it is not usually straightforward to determine whether any particular low probability feature is the result of the a posteriori selection or non-standard cosmology. Hypothesis testing could, of course, always reveal an alternative model that is statistically favored, but there is currently no model that is more compelling. We find that two cold spots in the map are statistically consistent with random cosmic microwave background (CMB) fluctuations. We also find that the amplitude of the quadrupole is well within the expected 95% confidence range and therefore is not anomalously low. We find no significant anomaly with a lack of large angular scale CMB power for the best-fit {Lambda}CDM model. We examine in detail the properties of the power spectrum data with respect to the {Lambda}CDM model and find no significant anomalies. The quadrupole and octupole components of the CMB sky are remarkably aligned, but we find that this is not due to any single map feature; it results from the statistical combination of the full-sky anisotropy fluctuations. It may be due, in part, to chance alignments between the primary and secondary anisotropy, but this only shifts the coincidence from within the last scattering surface to between it and the local matter density distribution. While this alignment appears to be remarkable, there was no model that predicted it, nor has there been a model that provides a compelling retrodiction. We examine claims of a hemispherical or dipole power asymmetry across the sky and find that the evidence for these claims is not statistically significant. We confirm the claim of a strong quadrupolar power asymmetry effect, but there is considerable evidence that the effect is not cosmological. The likely explanation is an insufficient handling of beam asymmetries. We conclude that there is no compelling evidence for deviations from the {Lambda}CDM model, which is generally an acceptable statistical fit to WMAP and other cosmological data.

79 ASTRONOMY AND ASTROPHYSICS↗

Modeling forest site productivity using mapped geospatial attributes within a South Carolina Landscape, USA

Spatially explicit mapping of forest productivity is important to assess many forest management alternatives. We assessed the relationship between mapped variables and site index of forests ranging from southern pine plantations to natural hardwoods on a 74,000-ha landscape in South Carolina, USA. Mapped features used in the analysis were soil association, land use condition in 1951, depth to groundwater, slope and aspect. Basal area, species composition, age and height were the tree variables measured. Linear modelling identified that plot basal area, depth to groundwater, soils association and the interactions between depth to groundwater and forest group, and between land use in 1951 and forest group were related to site index (SI) (R 2 =0.37), but this model had regression attenuation. We then used structural equation modeling to incorporate error-in-measurement corrections for basal area and groundwater to remove bias in the model. We validated this model using 89 independent observations and found the 95% confidence intervals for the slope and intercept of an observed vs. predicted site index error-corrected regression included zero and one, respectively, indicating a good fit. With error in measurement incorporated, only basal area, soil association, and the interaction between forest groups and land use were important predictors (R2 =0.57). Thus, we were able to develop an unbiased model of SI that could be applied to create a spatially explicit map based primarily on soils as modified by past (land use and forest type) and recent forest management (basal area).

54 ENVIRONMENTAL SCIENCES↗

Machine-learning error models for approximate solutions to parameterized systems of nonlinear equations

Here, this work proposes a machine-learning framework for constructing statistical models of errors incurred by approximate solutions to parameterized systems of nonlinear equations. These approximate solutions may arise from early termination of an iterative method, a lower-fidelity model, or a projection-based reduced-order model, for example. The proposed statistical model comprises the sum of a deterministic regression-function model and a stochastic noise model. The method constructs the regression-function model by applying regression techniques from machine learning (e.g., support vector regression, artificial neural networks) to map features (i.e., error indicators such as sampled elements of the residual) to a prediction of the approximate-solution error. The method constructs the noise model as a mean-zero Gaussian random variable whose variance is computed as the sample variance of the approximate-solution error on a test set; this variance can be interpreted as the epistemic uncertainty introduced by the approximate solution. This work considers a wide range of feature-engineering methods, data-set-construction techniques, and regression techniques that aim to ensure that (1) the features are cheaply computable, (2) the noise model exhibits low variance (i.e., low epistemic uncertainty introduced), and (3) the regression model generalizes to independent test data. Finally, numerical experiments performed on several computational-mechanics problems and types of approximate solutions demonstrate the ability of the method to generate statistical models of the error that satisfy these criteria and significantly outperform more commonly adopted approaches for error modeling.

97 MATHEMATICS AND COMPUTING↗

Time-series machine-learning error models for approximate solutions to parameterized dynamical systems

This work proposes a machine-learning framework for modeling the error incurred by approximate solutions to parameterized dynamical systems. In particular, we extend the machine-learning error models (MLEM) framework proposed in Ref. Freno and Carlberg (2019) to dynamical systems. The proposed Time-Series Machine-Learning Error Modeling (T-MLEM) method constructs a regression model that maps features – which comprise error indicators that are derived from standard a posteriori error-quantification techniques – to a random variable for the approximate-solution error at each time instance. The proposed framework considers a wide range of candidate features, regression methods, and additive noise models. We consider primarily recursive regression techniques developed for time-series modeling, including both classical time-series models (e.g., autoregressive models) and recurrent neural networks (RNNs), but also analyze standard non-recursive regression techniques (e.g., feed-forward neural networks) for comparative purposes. Finally, numerical experiments conducted on multiple benchmark problems illustrate that the long short-term memory (LSTM) neural network, which is a type of RNN, outperforms other methods and yields substantial improvements in error predictions over traditional approaches.

42 ENGINEERING↗

Large Eddy Simulations of the Atmospheric Boundary Layer Over Satellite‐Sensed Sea Ice Maps

Surface heterogeneity in the marginal ice zone (MIZ) causes multiscale secondary atmospheric circulations that are challenging to model or observe. The absence or inadequate representation of these circulations in ocean‐atmosphere exchange schemes in climate models is partially responsible for the underestimation of Arctic sea ice loss. Observationally, such circulations obfuscate the interpretation of polar atmospheric chemistry measurements, among others. To address this open challenge, large‐eddy simulations are conducted over real‐world satellite‐sensed sea ice maps with an ice‐sea temperature contrast, as well as over idealizations of these maps that alter the ice pattern but conserve its fraction, showing that the ice fraction of a surface is not sufficient to predict the surface heat flux. In a second suite of simulations, three other heterogeneity metrics (representing the surface fragmentation, patch edge tortuosity, and patch size variability) are introduced to complement the ice fraction in describing the surface. Simulations varying these parameters suggest that they also significantly impact surface‐air interactions. A roughness contrast is then added to the surface temperature contrast, indicating that the contribution of roughness changes to the resulting atmospheric circulations is less pronounced than that of thermal heterogeneity. Based on these results, we illustrate, using a multi‐linear regression on these map features, that MIZ surface parameterizations in Earth Systems Models can be improved if they account for these various characteristics of the sea‐ice patterns.

54 ENVIRONMENTAL SCIENCES↗

Rapid and flexible segmentation of electron microscopy data using few-shot machine learning

Abstract Automatic segmentation of key microstructural features in atomic-scale electron microscope images is critical to improved understanding of structure–property relationships in many important materials and chemical systems. However, the present paradigm involves time-intensive manual analysis that is inherently biased, error-prone, and unable to accommodate the large volumes of data produced by modern instrumentation. While more automated approaches have been proposed, many are not robust to a high variety of data, and do not generalize well to diverse microstructural features and material systems. Here, we present a flexible, semi-supervised few-shot machine learning approach for segmentation of scanning transmission electron microscopy images of three oxide material systems: (1) epitaxial heterostructures of SrTiO 3 /Ge, (2) La 0.8 Sr 0.2 FeO 3 thin films, and (3) MoO 3 nanoparticles. We demonstrate that the few-shot learning method is more robust against noise, more reconfigurable, and requires less data than conventional image analysis methods. This approach can enable rapid image classification and microstructural feature mapping needed for emerging high-throughput characterization and autonomous microscope platforms.

36 MATERIALS SCIENCE↗

HUNTING FOR YOUNG DISPERSING STAR CLUSTERS IN IC 2574

Dissolving stellar groups are very difficult to detect using traditional surface photometry techniques. We have developed a method to find and characterize non-compact stellar systems in galaxies where the young stellar population can be spatially resolved. By carrying out photometry on individual stars, we are able to separate the luminous blue stellar population from the star field background. The locations of these stars are used to identify groups by applying the HOP algorithm, which are then characterized using color-magnitude and stellar density radial profiles to estimate age, size, density, and shape. We test the method on Hubble Space Telescope Advanced Camera for Surveys archival images of IC 2574 and find 75 dispersed stellar groups. Of these, 20 highly dispersed groups are good candidates for dissolving systems. We find few compact systems with evidence of dissolution, potentially indicating that star formation in this galaxy occurs mostly in unbound clusters or groups. These systems indicate that the dispersion rate of groups and clusters in IC 2574 is at most 0.45 pc Myr{sup -1}. The location of the groups found with HOP correlate well with H I contour map features. However, they do not coincide with H I holes, suggesting that those holes were not created by star-forming regions.

79 ASTRONOMY AND ASTROPHYSICS↗

Integration of Ag-CBRAM crossbars and Mott ReLU neurons for efficient implementation of deep neural networks in hardware

In-memory computing with emerging non-volatile memory devices (eNVMs) has shown promising results in accelerating matrix-vector multiplications. However, activation function calculations are still being implemented with general processors or large and complex neuron peripheral circuits. Here, we present the integration of Ag-based conductive bridge random access memory (Ag-CBRAM) crossbar arrays with Mott rectified linear unit (ReLU) activation neurons for scalable, energy and area-efficient hardware (HW) implementation of deep neural networks. We develop Ag-CBRAM devices that can achieve a high ON/OFF ratio and multi-level programmability. Compact and energy-efficient Mott ReLU neuron devices implementing ReLU activation function are directly connected to the columns of Ag-CBRAM crossbars to compute the output from the weighted sum current. We implement convolution filters and activations for VGG-16 using our integrated HW and demonstrate the successful generation of feature maps for CIFAR-10 images in HW. Our approach paves a new way toward building a highly compact and energy-efficient eNVMs-based in-memory computing system.

Mott insulators↗

Numerical evidence against advantage with quantum fidelity kernels on classical data

Quantum machine learning techniques are commonly considered one of the most promising candidates for demonstrating practical quantum advantage. In particular, quantum kernel methods have been demonstrated to be able to learn certain classically intractable functions efficiently if the kernel is well aligned with the target function. In the more general case, quantum kernels are known to suffer from exponential “flattening” of the spectrum as the number of qubits grows, preventing generalization and necessitating the control of the inductive bias by hyperparameters. We show that the general-purpose hyperparameter-tuning techniques proposed to improve the generalization of quantum kernels lead to the kernel becoming well approximated by a classical kernel, removing the possibility of quantum advantage. We provide extensive numerical evidence for this phenomenon utilizing multiple previously studied quantum feature maps and both synthetic and real data. Our results show that unless novel techniques are developed to control the inductive bias of quantum kernels, they are unlikely to provide a quantum advantage on classical data that lacks special structure.

Quantum Information, Science & Technology↗

Fault Detection via Occupation Kernel Principal Component Analysis

Reliable operation of automatic systems is heavily dependent on the ability to detect faults in the underlying dynamics. While traditional model-based methods have been widely used for fault detection, data-driven approaches have garnered increasing attention due to their ease of deployment and minimal need for expert knowledge. In this letter, we present a novel principal component analysis (PCA) method that uses occupation kernels. Occupation kernels result in feature maps that are tailored to the measured data, have inherent noise-robustness due to the use of integration, and can utilize irregularly sampled system trajectories of variable lengths for PCA. The occupation kernel PCA method is used to develop a reconstruction error approach to fault detection and its efficacy is validated using numerical simulations.

42 ENGINEERING↗

Real-Time Ecodriving Control in Electrified Connected and Autonomous Vehicles Using Approximate Dynamic Programing

Connected and automated vehicles (CAVs), particularly those with a hybrid electric powertrain, have the potential to significantly improve vehicle energy savings in real-world driving conditions. In particular, the ecodriving problem seeks to design optimal speed and power usage profiles based on available information from connectivity and advanced mapping features to minimize the fuel consumption over an itinerary. This paper presents a hierarchical multilayer model predictive control (MPC) approach for improving the fuel economy of a 48 V mild-hybrid powertrain in a connected vehicle environment. Approximate dynamic programing (DP) is used to solve the receding horizon optimal control problem, whose terminal cost is approximated with the base policy obtained from the long-term optimization. The controller was tested virtually (with deterministic and Monte Carlo simulation) across multiple real-world routes, demonstrating energy savings of more than 20%. The controller was then deployed on a test vehicle equipped with a rapid prototyping embedded controller. In-vehicle testing confirm the energy savings obtained in simulation and demonstrate the real-time ability of the controller.

Automation & Control Systems↗

Scalable Regression Tree Learning on Hadoop using OpenPlanet

As scientific and engineering domains attempt to effectively analyze the deluge of data arriving from sensors and instruments, machine learning is becoming a key data mining tool to build prediction models. Regression tree is a popular learning model that combines decision trees and linear regression to forecast numerical target variables based on a set of input features. Map Reduce is well suited for addressing such data intensive learning applications, and a proprietary regression tree algorithm, PLANET, using MapReduce has been proposed earlier. In this paper, we describe an open source implement of this algorithm, OpenPlanet, on the Hadoop framework using a hybrid approach. Further, we evaluate the performance of OpenPlanet using realworld datasets from the Smart Power Grid domain to perform energy use forecasting, and propose tuning strategies of Hadoop parameters to improve the performance of the default configuration by 75% for a training dataset of 17 million tuples on a 64-core Hadoop cluster on FutureGrid.

Yin, Wei↗

PARETO UI 1.1.0 Release

PARETO is an open-source Python-based software package for oilfield produced water management and beneficiary reuse optimization. PARETO supports produced water industry by providing cost-effective water management solutions. This version introduced an updated User Interface (UI) which makes it easier to navigate and understand the solution for industry users. New Features: - Map files are added for visualization - Added output export function button - Water residual view added - Workflow was streamlined - File extension was expanded - Minor bugfix

AS↗

Statistical Exploration of Electronic Structure of Molecules from Quantum Monte-Carlo Simulations

In this report, we present results from analysis of Quantum Monte Carlo (QMC) simulation data with the goal of determining internal structure of a 3N-dimensional phase space of an N-electron molecule. We are interested in mining the simulation data for patterns that might be indicative of the bond rearrangement as molecules change electronic states. We examined simulation output that tracks the positions of two coupled electrons in the singlet and triplet states of an H2 molecule. The electrons trace out a trajectory, which was analyzed with a number of statistical techniques. This project was intended to address the following scientific questions: (1) Do high-dimensional phase spaces characterizing electronic structure of molecules tend to cluster in any natural way? Do we see a change in clustering patterns as we explore different electronic states of the same molecule? (2) Since it is hard to understand the high-dimensional space of trajectories, can we project these trajectories to a lower dimensional subspace to gain a better understanding of patterns? (3) Do trajectories inherently lie in a lower-dimensional manifold? Can we recover that manifold? After extensive statistical analysis, we are now in a better position to respond to these questions. (1) We definitely see clustering patterns, and differences between the H2 and H2tri datasets. These are revealed by the pamk method in a fairly reliable manner and can potentially be used to distinguish bonded and non-bonded systems and get insight into the nature of bonding. (2) Projecting to a lower dimensional subspace ({approx}4-5) using PCA or Kernel PCA reveals interesting patterns in the distribution of scalar values, which can be related to the existing descriptors of electronic structure of molecules. Also, these results can be immediately used to develop robust tools for analysis of noisy data obtained during QMC simulations (3) All dimensionality reduction and estimation techniques that we tried seem to indicate that one needs 4 or 5 components to account for most of the variance in the data, hence this 5D dataset does not necessarily lie on a well-defined, low dimensional manifold. In terms of specific clustering techniques, K-means was generally useful in exploring the dataset. The partition around medoids (pam) technique produced the most definitive results for our data showing distinctive patterns for both a sample of the complete data and time-series. The gap statistic with tibshirani criteria did not provide any distinction across the 2 dataset. The gap statistic w/DandF criteria, Model based clustering and hierarchical modeling simply failed to run on our datasets. Thankfully, the vanilla PCA technique was successful in handling our entire dataset. PCA revealed some interesting patterns for the scalar value distribution. Kernel PCA techniques (vanilladot, RBF, Polynomial) and MDS failed to run on the entire dataset, or even a significant fraction of the dataset, and we resorted to creating an explicit feature map followed by conventional PCA. Clustering using K-means and PAM in the new basis set seems to produce promising results. Understanding the new basis set in the scientific context of the problem is challenging, and we are currently working to further examine and interpret the results.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗