Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Feature Space”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
NASA NTRS1992

On the asymptotic improvement of supervised learning by utilizing additional unlabeled samples - Normal mixture density case

The effect of additional unlabeled samples in improving the supervised learning process is studied in this paper. Three learning processes. supervised, unsupervised, and combined supervised-unsupervised, are compared by studying the asymptotic behavior of the estimates obtained under each process. Upper and lower bounds on the asymptotic covariance matrices are derived. It is shown that under a normal mixture density assumption for the probability density function of the feature space, the combined supervised-unsupervised learning is always superior to the supervised learning in achieving better estimates. Experimental results are provided to verify the theoretical concepts.

Shahshahani, Behzad M.↗
NASA NTRS1992

Using partially labeled data for normal mixture identification with application to class definition

The problem of estimating the parameters of a normal mixture density when, in addition to the unlabeled samples, sets of partially labeled samples are available is addressed. The density of the multidimensional feature space is modeled with a normal mixture. It is assumed that the set of components of the mixture can be partitioned into several classes and that training samples are available from each class. Since for any training sample the class of origin is known but the exact component of origin within the corresponding class is unknown, the training samples as considered to be partially labeled. The EM iterative equations are derived for estimating the parameters of the normal mixture in the presence of partially labeled samples. These equations can be used to combine the supervised and nonsupervised learning processes.

Shahshahani, Behzad M.↗
NASA NTRS2000

Access to Space Interactive Design Web Site

The Access To Space (ATS) Group at NASA's Goddard Space Flight Center (GSFC) supports the science and technology community at GSFC by facilitating frequent and affordable opportunities for access to space. Through partnerships established with access mode suppliers, the ATS Group has developed an interactive Mission Design web site. The ATS web site provides both the information and the tools necessary to assist mission planners in selecting and planning their ride to space. This includes the evaluation of single payloads vs. ride-sharing opportunities to reduce the cost of access to space. Features of this site include the following: (1) Mission Database. Our mission database contains a listing of missions ranging from proposed missions to manifested. Missions can be entered by our user community through data input tools. Data is then accessed by users through various search engines: orbit parameters, ride-share opportunities, spacecraft parameters, other mission notes, launch vehicle, and contact information. (2) Launch Vehicle Toolboxes. The launch vehicle toolboxes provide the user a full range of information on vehicle classes and individual configurations. Topics include: general information, environments, performance, payload interface, available volume, and launch sites.

Leon, John↗
NASA NTRS2009

Flightspeed Integral Image Analysis Toolkit

The Flightspeed Integral Image Analysis Toolkit (FIIAT) is a C library that provides image analysis functions in a single, portable package. It provides basic low-level filtering, texture analysis, and subwindow descriptor for applications dealing with image interpretation and object recognition. Designed with spaceflight in mind, it addresses: Ease of integration (minimal external dependencies) Fast, real-time operation using integer arithmetic where possible (useful for platforms lacking a dedicated floatingpoint processor) Written entirely in C (easily modified) Mostly static memory allocation 8-bit image data The basic goal of the FIIAT library is to compute meaningful numerical descriptors for images or rectangular image regions. These n-vectors can then be used directly for novelty detection or pattern recognition, or as a feature space for higher-level pattern recognition tasks. The library provides routines for leveraging training data to derive descriptors that are most useful for a specific data set. Its runtime algorithms exploit a structure known as the "integral image." This is a caching method that permits fast summation of values within rectangular regions of an image. This integral frame facilitates a wide range of fast image-processing functions. This toolkit has applicability to a wide range of autonomous image analysis tasks in the space-flight domain, including novelty detection, object and scene classification, target detection for autonomous instrument placement, and science analysis of geomorphology. It makes real-time texture and pattern recognition possible for platforms with severe computational restraints. The software provides an order of magnitude speed increase over alternative software libraries currently in use by the research community. FIIAT can commercially support intelligent video cameras used in intelligent surveillance. It is also useful for object recognition by robots or other autonomous vehicles

Thompson, David R.↗
NASA NTRS2010

Survey of Propulsion Technologies Applicable to Cubesats

At present, no Cubesat has flown in space featuring propulsion. This was acceptable as long as CubeSats were flown mostly as university experiments. As CubeSats become of interest to other users in the government and industry communities as well, a larger range of capabilities may be required than exhibited so far, while maintaining the uniqueness of the Cubesat platform. Propulsion capability is crucial in increasing mission capabilities of future CubeSats, such as orbit change and raising, formation flying, proximity operations, fine attitude control, or drag-make-up and de-orbit. While some of these tasks may be accomplished with propellantless devices, their applications are limited, applicable mostly to a single task, and bear their own risks. In this study, a survey was conducted of propulsion technologies applicable to CubeSats. Only few off-the-shelf design solutions exist today. The survey was thus expanded to such devices as well that are under significant development, and are approaching the required design envelope for CubeSats with respect to mass, volume, and power. In some cases, such as electric propulsion devices, CubeSat architectures themselves may need to be adapted, required to feature deployable solar arrays to increase power capabilities. Given the vast scope of this survey, only thruster technologies could be surveyed. However, valves and other feed system components, as well as their integration, are equally important, but have to be left to a future survey. Three major propulsion technology areas applicable to CubeSats emerged when conducting this review: (1) Existing technologies, such as butane systems, pulsed plasma thrusters, and vacuum arc thrusters are applicable to CubeSats today with no or only minor changes, (2) New thruster technologies under significant development, such as hydrazine monopropellant systems, ion engines, or colloid thrusters could be adapted to CubeSats with some further development, especially also in other subsystem areas such as feed systems and power processing units. They will also require increased power capabilities, and (3) emerging technologies, such as micro electrospray arrays and micro cavity discharge arrays that offer even higher flexibility due to scalability for CubeSats, and enable compact integration.

micropropulsion↗
NASA NTRS2010

Multi-Stage System for Automatic Target Recognition

A multi-stage automated target recognition (ATR) system has been designed to perform computer vision tasks with adequate proficiency in mimicking human vision. The system is able to detect, identify, and track targets of interest. Potential regions of interest (ROIs) are first identified by the detection stage using an Optimum Trade-off Maximum Average Correlation Height (OT-MACH) filter combined with a wavelet transform. False positives are then eliminated by the verification stage using feature extraction methods in conjunction with neural networks. Feature extraction transforms the ROIs using filtering and binning algorithms to create feature vectors. A feedforward back-propagation neural network (NN) is then trained to classify each feature vector and to remove false positives. The system parameter optimizations process has been developed to adapt to various targets and datasets. The objective was to design an efficient computer vision system that can learn to detect multiple targets in large images with unknown backgrounds. Because the target size is small relative to the image size in this problem, there are many regions of the image that could potentially contain the target. A cursory analysis of every region can be computationally efficient, but may yield too many false positives. On the other hand, a detailed analysis of every region can yield better results, but may be computationally inefficient. The multi-stage ATR system was designed to achieve an optimal balance between accuracy and computational efficiency by incorporating both models. The detection stage first identifies potential ROIs where the target may be present by performing a fast Fourier domain OT-MACH filter-based correlation. Because threshold for this stage is chosen with the goal of detecting all true positives, a number of false positives are also detected as ROIs. The verification stage then transforms the regions of interest into feature space, and eliminates false positives using an artificial neural network classifier. The multi-stage system allows tuning the detection sensitivity and the identification specificity individually in each stage. It is easier to achieve optimized ATR operation based on its specific goal. The test results show that the system was successful in substantially reducing the false positive rate when tested on a sonar and video image datasets.

Chao, Tien-Hsin↗
NASA NTRS2004

Fast Query-Optimized Kernel-Machine Classification

A recently developed algorithm performs kernel-machine classification via incremental approximate nearest support vectors. The algorithm implements support-vector machines (SVMs) at speeds 10 to 100 times those attainable by use of conventional SVM algorithms. The algorithm offers potential benefits for classification of images, recognition of speech, recognition of handwriting, and diverse other applications in which there are requirements to discern patterns in large sets of data. SVMs constitute a subset of kernel machines (KMs), which have become popular as models for machine learning and, more specifically, for automated classification of input data on the basis of labeled training data. While similar in many ways to k-nearest-neighbors (k-NN) models and artificial neural networks (ANNs), SVMs tend to be more accurate. Using representations that scale only linearly in the numbers of training examples, while exploring nonlinear (kernelized) feature spaces that are exponentially larger than the original input dimensionality, KMs elegantly and practically overcome the classic curse of dimensionality. However, the price that one must pay for the power of KMs is that query-time complexity scales linearly with the number of training examples, making KMs often orders of magnitude more computationally expensive than are ANNs, decision trees, and other popular machine learning alternatives. The present algorithm treats an SVM classifier as a special form of a k-NN. The algorithm is based partly on an empirical observation that one can often achieve the same classification as that of an exact KM by using only small fraction of the nearest support vectors (SVs) of a query. The exact KM output is a weighted sum over the kernel values between the query and the SVs. In this algorithm, the KM output is approximated with a k-NN classifier, the output of which is a weighted sum only over the kernel values involving k selected SVs. Before query time, there are gathered statistics about how misleading the output of the k-NN model can be, relative to the outputs of the exact KM for a representative set of examples, for each possible k from 1 to the total number of SVs. From these statistics, there are derived upper and lower thresholds for each step k. These thresholds identify output levels for which the particular variant of the k-NN model already leans so strongly positively or negatively that a reversal in sign is unlikely, given the weaker SV neighbors still remaining. At query time, the partial output of each query is incrementally updated, stopping as soon as it exceeds the predetermined statistical thresholds of the current step. For an easy query, stopping can occur as early as step k = 1. For more difficult queries, stopping might not occur until nearly all SVs are touched. A key empirical observation is that this approach can tolerate very approximate nearest-neighbor orderings. In experiments, SVs and queries were projected to a subspace comprising the top few principal- component dimensions and neighbor orderings were computed in that subspace. This approach ensured that the overhead of the nearest-neighbor computations was insignificant, relative to that of the exact KM computation.

Mazzoni, Dominic↗
NASA NTRS2011

Multiclass Continuous Correspondence Learning

We extend the Structural Correspondence Learning (SCL) domain adaptation algorithm of Blitzer er al. to the realm of continuous signals. Given a set of labeled examples belonging to a 'source' domain, we select a set of unlabeled examples in a related 'target' domain that play similar roles in both domains. Using these 'pivot samples, we map both domains into a common feature space, allowing us to adapt a classifier trained on source examples to classify target examples. We show that when between-class distances are relatively preserved across domains, we can automatically select target pivots to bring the domains into correspondence.

correspondence learning↗
NASA NTRSDate not supplied

Multi-Class Anomaly Detection in Flight Data using Semi-Supervised Explainable Deep Learning Model

Identifying precursor for safety incidents in aviation data is a crucial task, yet extremely challenging. The main approach, in practice, leverages domain expertise to define expected tolerances in system’s behavior and alarm exceedance from such safety margins. However, this approach is incapable of identifying unknown risk and vulnerabilities. Machine learning has been long studied and deployed to identify precursors for such anomalies, with the great challenge of the need for sufficient labelled set of data to achieve a reliable and accurate performance. In this article, we develop an explainable deep semi-supervised model for anomaly detection in aviation, building upon recent advancements in the machine learning literature. The proposed model combines feature engineering and classification in the feature space, while leveraging all available data (labelled and unlabeled). Validating on two case studies of anomaly detection in take-off and landing phases of commercial aircraft, we show that our model is able to outperform state-of-the-art supervised anomaly detection model and reach significantly high accuracy and low false alarm with minimum amount of available labelled data.

Anomaly Detection↗
NASA NTRS2021

Spectral Synthesis for Geostationary Satellite-to-Satellite Translation

Earth-observing satellites carrying multispectral sensors are widely used to monitor the physical and biological states of the atmosphere, land, and oceans. These satellites have different vantage points above the Earth and different spectral imaging bands resulting in inconsistent imagery from one to another. This presents challenges in building downstream applications. What if we could generate synthetic bands for existing satellites from the union of all domains? We tackle the problem of generating synthetic spectral imagery for multispectral sensors as an unsupervised image-to-image translation problem modeled with a variational autoencoder (VAE) and generative adversarial network (GAN) architecture. Our approach introduces a novel shared spectral reconstruction loss to constrain the high-dimensional feature space of multispectral images. Simulated experiments performed by dropping one or more spectral bands show that cross-domain reconstruction outperforms measurements obtained from a second vantage point. Our proposed approach enables the synchronization of multispectral data and provides a basis for more homogeneous remote sensing datasets.

Geostationary satellites↗
NASA NTRS2023

A Global Land Cover Training Dataset From 1984 to 2020

State-of-the-art cloud computing platforms such as Google Earth Engine (GEE) enable regional-to-global land cover and land cover change mapping with machine learning algorithms. However, collection of high-quality training data, which is necessary for accurate land cover mapping, remains costly and labor-intensive. To address this need, we created a global database of nearly 2 million training units spanning the period from 1984 to 2020 for seven primary and nine secondary land cover classes. Our training data collection approach leveraged GEE and machine learning algorithms to ensure data quality and biogeographic representation. We sampled the spectral-temporal feature space from Landsat imagery to efficiently allocate training data across global ecoregions and incorporated publicly available and collaborator-provided datasets to our database. To reflect the underlying regional class distribution and post-disturbance landscapes, we strategically augmented the database. We used a machine learning-based cross-validation procedure to remove potentially mis-labeled training units. Our training database is relevant for a wide array of studies such as land cover change, agriculture, forestry, hydrology, urban development, among many others.

Radost Stanimirova↗
NASA NTRS1990

Miniaturized, 9-12 micron heterodyne spectrometer with space qualifiable design features

A demonstration-prototype CO2-laser heterodyne spectrometer operating at 9-12 microns and suitable for long-term space missions is described and illustrated with extensive diagrams, drawings, photographs, and graphs of test performance data. The spectrometer has total volume 0.63 cu m, mass 30 kg, and power requirement 60-70 W, compatible with miniature-class Space Shuttle experiment payload specifications. It comprises three modules: (1) an optical front end with reflecting optics, a 2-GHz BW HgCdTe photomixer, and a 0-2-GHz 40-dB RF preamplifier; (2) a local oscillator with an RF-excited waveguide CO2 laser, a 75-percent-efficiency RF amplifier, a stepper-driven grating mode selector, and an etalon stabilized for over 30,000 h of use; and (3) an RF-filter-bank spectral-line receiver with a 25-MHz RF channel, 1.6-GHz IF spectral coverage, onboard instrument control, a serial link to the host computer, and highly integrated design.

Glenar, D. A.↗
NASA NTRS2011

Performance Characterization of Loctite (Registered Trademark) 242 and 271 Liquid Locking Compounds (LLCs) as a Secondary Locking Feature for International Space Station (ISS) Fasteners

Several International Space Station (ISS) hardware components use Loctite (and other polymer based liquid locking compounds (LLCs)) as a means of meeting the secondary (redundant) locking feature requirement for fasteners. The primary locking method is the fastener preload, with the application of the Loctite compound which when cured is intended to resist preload reduction. The reliability of these compounds has been questioned due to a number of failures during ground testing. The ISS Program Manager requested the NASA Engineering and Safety Center (NESC) to characterize and quantify sensitivities of Loctite being used as a secondary locking feature. The findings and recommendations provided in this investigation apply to the anaerobic LLCs Loctite 242 and 271. No other anaerobic LLCs were evaluated for this investigation. This document contains the findings and recommendations of the NESC investigation

Dube, Michael J.↗
NASA NTRS1989

The detection and observation of meteoroid and space debris impact features on the Solar Max satellite

The results of optical observations on the entire population of impact pits and holes discovered on nearly all of the returned parts of the Solar Maximum Mission satellite are described. Some statistically significant new results on impact dynamics are obtained as well as new number vs. size distributions for craters and holes ranging from 40 to 900 microns. The local spacecraft geometric shielding corrections are calculated and applied to the data. Some selected compositional results are presented which indicate that the Space Shuttle can be a source of impacting debris.

Warren, J. L.↗
NASA NTRS1985

Concepts, strategies and potentials using hypo-g and other features of the space environment for commercialization using higher plants

Opportunities for releasing, capturing, constructing and/or fixing the differential expressions or response potentials of the higher plant genome in the hypo-g environment for commercialization are explored. General strategies include improved plant-growing, crop and forestry production systems which conserve soil, water, labor and energy resources, and nutritional partitioning and mobilization of nutrients and synthates. Tissue and cell culture techniques of commercial potential include the growing and manipulation of cultured plant cells in vitro in a bioreactor to produce biologicals and secondary plants of economic value. The facilitation of plant breeding, the cloning of specific pathogen-free materials, the elimination of growing point or apex viruses, and the increase of plant yield are other O-g applications. The space environment may be advantageous in somatic embryogenesis, the culture of alkaloids, and the development of completely new crop plant germ plasm.

Krikorian, A. D.↗
NASA NTRS2014

In-situ Microwave Brightness Temperature Variability from Ground-based Radiometer Measurements at Dome C in Antarctica Induced by Wind-formed Features

Space-borne microwave radiometers are among the most useful tools to study snow and to collect information on the Antarctic climate. They have several advantages over other remote sensing techniques: high sensitivity to snow properties of interest (temperature, grain size, density), subdaily coverage in the polar regions, and their observations are independent of cloud conditions and solar illumination. Thus, microwave radiometers are widely used to retrieve information over snow-covered regions. For the Antarctic Plateau, many studies presenting retrieval algorithms or numerical simulations have assumed, explicitly or not, that the subpixel-scale heterogeneity is negligible and that the retrieved properties were representative of whole pixels. In this presentation, we investigate the spatial variations of brightness temperature over arange of a few kilometers in the Dome C area (Antarctic Plateau).

Antarctica↗