Search NASA⌕ Search

SEARCH · Search NASA

Results for “nonparametric”

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
All sourcesNASA NTRSDOE OSTI
NASA NTRS1971

Nonparametric Bayer-risk estimation

Nonparametric Bayes risk estimation for measurement classification, using nearest neighbor error rate and Parzen probability density function estimators

Fralick, S. C.↗
NASA NTRS1975

A sequential nonparametric pattern classification algorithm based on the Wald SPRT

A sequential nonparametric pattern classification procedure is presented. The method presented is an estimated version of the Wald sequential probability ratio test (SPRT). This method utilizes density function estimates, and the density estimate used is discussed, including a proof of convergence in probability of the estimate to the true density function. The classification procedure proposed makes use of the theory of order statistics, and estimates of the probabilities of misclassification are given. The procedure was tested on discriminating between two classes of Gaussian samples and on discriminating between two kinds of electroencephalogram (EEG) responses.

Poage, J. L.↗
NASA NTRS1981

A nonparametric identification method for a class of non-linear systems

A relatively simple nonparametric method for the identification of a class of close-coupled nonlinear multi-degree-of-freedom systems has been developed. The identification of arbitrary memoryless nonlinearities is possible through knowledge of the accelerations, velocities, and displacements of the various masses. These quantities are used to obtain the surfaces of the restoring forces as functions of the intermass displacements and velocities. The method was demonstrated by application to a four-degree-of-freedom system to identify the restoring forces. It is found that the identification results are relatively insensitive to measurement noise.

Udwadia, F. E.↗
NASA NTRS1981

Nonparametric identification of a class of nonlinear close-coupled dynamic systems

A nonparametric identification technique for the identification of close coupled dynamic systems with arbitrary memoryless nonlinearities is presented. The method utilizes noisy recorded data (acceleration, velocity and displacement) to identify the restoring forces in the system. The masses in the system are assumed to be known (or fairly well estimated from the design drawings). The restoring forces are expanded in a series of orthogonal polnomials and the coefficients of these polynomial expansions are obtained by using least square fit method. A particularly simple and computationally efficient method is proposed for dealing with separable restoring forces. The identified results are found to be relatively insensitive to measurement noise. An analysis of the effects of measurement noise on the quality of the estimates is given. The computations are shown to be relatively quick (when compared say to the Wiener identification method) and the core storage required relatively small, making the method suitable for onboard identification of large space structures.

Udwadia, F. E.↗
NASA NTRS1984

Parametric and Nonparametric Analysis of LANDSAT TM and MSS Imagery for Detecting Submerged Plant Communities

The spatial, spectral and radiometric characteristics of LANDSAT TM and MSS imagery for detecting submerged aquatic vegetation are assessed. The problem is approached from two perspectives; purely stochastic or nonparametric in a radiative sense and theoretical in which radiative transfer equations are used to predict upwelling radiance at satellite altitude. The spectral and radiometric aspects of the theoretical approach are addressed with which a submerged plant canopy is distinguished from a surrounding bottom of sand or mud.

Ackleson, S. G.↗
NASA NTRS1985

Nonparametric solutions to the variational principle of ideal magnetohydrodynamics

In an effort to gain a better understanding of MHD equilibria in three dimensions, the lower dimensional cases are studied. The solution of the three-dimensional problem is based on the classical variational principle of ideal magnetohydrodynamics. The crucial assumption for the numerical method is the existence of a nested set of toroidal flux surfaces, which is then used as a coordinate. This paper studies the nonparametric solutions to this variational problem in those cases when the direct solution is known to have islands. A form of the variational principle for the slab geometry is described; the one-dimensional problem is analyzed; and asymptotic expansions and numerical solutions to the two-dimensional problem are discussed. An example is presented which shows that the assumption of nested flux surfaces need not rule out the occurrence of islands.

Betancourt, O. L.↗
NASA NTRS1988

A nonparametric software reliability growth model

Miller and Sofer have presented a nonparametric method for estimating the failure rate of a software program. The method is based on the complete monotonicity property of the failure rate function, and uses a regression approach to obtain estimates of the current software failure rate. This completely monotone software model is extended. It is shown how it can also provide long-range predictions of future reliability growth. Preliminary testing indicates that the method is competitive with parametric approaches, while being more robust.

Miller, Douglas R.↗
NASA NTRS1991

A nonparametric software-reliability growth model

The authors (1985) previously introduced a nonparametric model for software-reliability growth which is based on complete monotonicity of the failure rate. The authors extend the completely monotone software model by developing a method for providing long-range predictions of reliability growth, based on the model. They derive upper and lower bounds on extrapolation of the failure rate and the mean function. These are then used to obtain estimates for the future software failure rate and the mean future number of failures. Preliminary evaluation indicates that the method is competitive with parametric approaches, while being more robust.

Sofer, Ariela↗
NASA NTRS1993

Classification of multispectral image data by the Binary Diamond neural network and by nonparametric, pixel-by-pixel methods

The classification of multispectral image data obtained from satellites has become an important tool for generating ground cover maps. This study deals with the application of nonparametric pixel-by-pixel classification methods in the classification of pixels, based on their multispectral data. A new neural network, the Binary Diamond, is introduced, and its performance is compared with a nearest neighbor algorithm and a back-propagation network. The Binary Diamond is a multilayer, feed-forward neural network, which learns from examples in unsupervised, 'one-shot' mode. It recruits its neurons according to the actual training set, as it learns. The comparisons of the algorithms were done by using a realistic data base, consisting of approximately 90,000 Landsat 4 Thematic Mapper pixels. The Binary Diamond and the nearest neighbor performances were close, with some advantages to the Binary Diamond. The performance of the back-propagation network lagged behind. An efficient nearest neighbor algorithm, the binned nearest neighbor, is described. Ways for improving the performances, such as merging categories, and analyzing nonboundary pixels, are addressed and evaluated.

Salu, Yehuda↗
NASA NTRS2018

Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding

As spacecraft send back increasing amounts of telemetry data, improved anomaly detection systems are needed to lessen the monitoring burden placed on operations engineers and reduce operational risk. Current spacecraft monitoring systems only target a subset of anomaly types and often require costly expert knowledge to develop and maintain due to challenges involving scale and complexity. We demonstrate the effectiveness of Long Short-Term Memory (LSTMs) networks, a type of Recurrent Neural Network (RNN), in overcoming these issues using expert-labeled telemetry anomaly data from the Soil Moisture Active Passive (SMAP) satellite and the Mars Science Laboratory (MSL) rover, Curiosity. We also propose a complementary unsupervised and nonparametric anomaly thresholding approach developed during a pilot implementation of an anomaly detection system for SMAP, and offer false positive mitigation strategies along with other key improvements and lessons learned during development.

Soderstrom, Tom↗