Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Misclassification”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS1977

A procedure used for a ground truth study of a land use map of North Alabama generated from LANDSAT data

A land use map of a five county area in North Alabama was generated from LANDSAT data using a supervised classification algorithm. There was good overall agreement between the land use designated and known conditions, but there were also obvious discrepancies. In ground checking the map, two types of errors were encountered - shift and misclassification - and a method was developed to eliminate or greatly reduce the errors. Randomly selected study areas containing 2,525 pixels were analyzed. Overall, 76.3 percent of the pixels were correctly classified. A contingency coefficient of correlation was calculated to be 0.7 which is significant at the alpha = 0.01 level. The land use maps generated by computers from LANDSAT data are useful for overall land use by regional agencies. However, care must be used when making detailed analysis of small areas. The procedure used for conducting the ground truth study together with data from representative study areas is presented.

Downs, S. W., Jr.↗
NASA NTRS1976

Number of signatures necessary for accurate classification

This paper presents a procedure for determining the number of signatures to use in classifying multispectral scanner data. A large initial set of signatures is obtained by clustering the training points within each category (such as 'wheat' or 'other') to be recognized. These clusters are then combined into broader signatures by a program that considers each pair of signatures within a category, combines the best pair in the light of certain criteria, saves the combined signature and repeats the procedure until there is one signature for each category. The result is a collection of sets of signatures, one set for each number between the number of initial clusters and the number of categories. With the aid of statistics such as an estimate of the probability of misclassification between categories, the user can choose the smallest set satisfying his requirements for classification accuracy.

Richardson, W.↗
NASA NTRS1977

Tabular data base construction and analysis from thematic classified Landsat imagery of Portland, Oregon

A systematic verification of Landsat data classifications of the Portland, Oregon metropolitan area has been undertaken on the basis of census tract data. The degree of systematic misclassification due to the Bayesian classifier used to process the Landsat data was noted for the various suburban, industrialized and central business districts of the metropolitan area. The Landsat determinations of residential land use were employed to estimate the number of automobile trips generated in the region and to model air pollution hazards.

Bryant, N. A.↗
NASA NTRS1972

ISODATA: Thresholds for splitting clusters

The author has identified the following significant results. The parameter AD (average distance) as used in the ISODATA program was critically examined. Thresholds of AD to decide on the splitting of clusters were obtained. For the univariate case, 0.84 was established as a sound choice, after examining several simple, as well as composite, distributions and also after investigating the probability of misclassification when points have to be reassigned to the newly identified clusters. For the multivariate case, the empirical threshold (N-0.16)/square root of N was extrapolated. A final criticism on AD was that AD would lose its effectiveness as a discriminative measure for the present purpose when N was large.

Kan, E. P. F.↗
NASA NTRS1977

Speech as a pilot input medium

The speech recognition system under development is a trainable pattern classifier based on a maximum-likelihood technique. An adjustable uncertainty threshold allows the rejection of borderline cases for which the probability of misclassification is high. The syntax of the command language spoken may be used as an aid to recognition, and the system adapts to changes in pronunciation if feedback from the user is available. Words must be separated by .25 second gaps. The system runs in real time on a mini-computer (PDP 11/10) and was tested on 120,000 speech samples from 10- and 100-word vocabularies. The results of these tests were 99.9% correct recognition for a vocabulary consisting of the ten digits, and 99.6% recognition for a 100-word vocabulary of flight commands, with a 5% rejection rate in each case. With no rejection, the recognition accuracies for the same vocabularies were 99.5% and 98.6% respectively.

Plummer, R. P.↗
NASA NTRS1979

Uniform color space analysis of LACIE image products

The author has identified the following significant results. Analysis and comparison of image products generated by different algorithms show that the scaling and biasing of data channels for control of PFC primaries lead to loss of information (in a probability-of misclassification sense) by two major processes. In order of importance they are: neglecting the input of one channel of data in any one image, and failing to provide sufficient color resolution of the data. The scaling and biasing approach tends to distort distance relationships in data space and provides less than desirable resolution when the data variation is typical of a developed, nonhazy agricultural scene.

Nalepka, R. F.↗
NASA NTRS1979

Linear feature selection with applications

Several ways in which feature selection techniques were used in LACIE are discussed. In all cases, the methods require some a priori information and assumptions; in most, the classification procedure (Bayes optimal) was chosen in advance. The transformations used for dimensionality reduction are linear, that is, the variables in feature space are always linear combinations of the original measurements. Several numerically tractable criteria developed for LACIE, which provide information about the probability of misclassification, are discussed. Recent results on linear feature selection techniques are included. Their use in LACIE is discussed. Related open questions are mentioned.

Decell, H. P., Jr.↗
NASA NTRS1980

Utilizing LANDSAT imagery to monitor land-use change - A case study in Ohio

A study, performed in Ohio, of the nature and extent of interpretation errors in the application of Landsat imagery to land-use planning and modeling is reported. Potential errors associated with the misalignment of pixels after geometric correction and with misclassification of land cover or land use due to spectral similarities were identified on interpreted computer-compatible tapes of a portion of Franklin County for two adjacent days of 1975 and one day of 1973, and the extents of these errors were quantified by comparison with a ground-checked set of aerial-photograph interpretations. The open-space and agricultural categories are found to be the most consistently classified, while the more urban areas were classified correctly only from about 43 to 8% of the time. It is thus recommended that the direct application of Landsat data to land-use planning must await improvements in classification techniques and accuracy.

Gordon, S. I.↗
NASA NTRS1980

Spectral reflectance and discrimination of plutonic rocks in the 0.45- to 2.45-micron region

Visible and near-infrared field spectral reflectance measurements of plutonic rocks were acquired in the 0.45- to 2.45-micron region with a portable field reflectance spectrometer. These spectra were used to determine spectral signatures for the various rock types and to evaluate the separability of these rocks based on their spectral characteristics. A total of 135 samples were divided into 11 groups based on their mineralogy. These 11 groups approximately correspond to traditional rock classifications and include five granitic groups, three gabbroic groups, and three ultramafic groups. The positions, intensity, and presence of iron, CO3(-2), and Al-OH and Mg-OH absorption bands varied among the 11 groups. Each rock group also had a range of albedos characteristic of the group. Stepwise linear discriminant analysis was performed on the spectral data to determine the separability of the 11 groups. Classification accuracy for 30 equally spaced wavelength bands between 0.45 and 2.45 microns was 78% with 10% serious misclassifications. The same analysis was repeated, limiting the spectral data to the wavelength regions corresponding to the proposed Landsat D thematic mapper scanner.

Blom, R. G.↗
NASA NTRS1981

A comparison of unsupervised classification procedures on LANDSAT MSS data for an area of complex surface conditions in Basilicata, Southern Italy

Two unsupervised classification procedures were applied to ratioed and unratioed LANDSAT multispectral scanner data of an area of spatially complex vegetation and terrain. An objective accuracy assessment was undertaken on each classification and comparison was made of the classification accuracies. The two unsupervised procedures use the same clustering algorithm. By on procedure the entire area is clustered and by the other a representative sample of the area is clustered and the resulting statistics are extrapolated to the remaining area using a maximum likelihood classifier. Explanation is given of the major steps in the classification procedures including image preprocessing; classification; interpretation of cluster classes; and accuracy assessment. Of the four classifications undertaken, the monocluster block approach on the unratioed data gave the highest accuracy of 80% for five coarse cover classes. This accuracy was increased to 84% by applying a 3 x 3 contextual filter to the classified image. A detailed description and partial explanation is provided for the major misclassification. The classification of the unratioed data produced higher percentage accuracies than for the ratioed data and the monocluster block approach gave higher accuracies than clustering the entire area. The moncluster block approach was additionally the most economical in terms of computing time.

Justice, C.↗
NASA NTRS1982

Ultraviolet photometry of A-type stars at high galactic latitudes

Ultraviolet photometry on the International Ultraviolet Explorer (IUE) was used to study four stars located in one target of an earlier diffuse background sounding-rocket experiment. The resulting stellar correction is much smaller than that previously estimated, giving a higher diffuse background at this target. Visible photometry appears to be a better indicator of ultraviolet flux than spectral type. The discrepancy between previous predictions and the present observations is explained in terms of: (1) misclassification of two stars; (2) use of a spectral type/effective temperature calibration hotter than more recent determinations; and (3) inadequacy of the Kurucz models, in the far ultraviolet, for A-type stars.

Landsman, W. B.↗
NASA NTRS1983

Spline Classification Methods

The use of spline functions in the development of classification algorithms is discussed. A method is formulated for producing spline approximations to univariate density functions when each density function is described by a histogram of measurements. The resulting approximations are then incorporated into a Bayesian classification procedure for which the probability of misclassification can be readily computed. Some preliminary numerical results are presented to illustrate the method.

Guseman, L. F., Jr.↗
NASA NTRS1983

Discrimination Relative to Measures of Non-Normality

The robustness of discriminant functions to nonnormality is investigated. The performance of procedures relative to measures of the difference between the actual distribution of the observations and the usual assumption of normal densities is assessed. For example, the two population, mixed distributions problem with equal costs of misclassification are considered. The parameters are estimated by maximum likelihood and recently proposed robust methods.

Smith, W. B.↗
NASA NTRS1984

Evaluation of entropy and JM-distance criterions as features selection methods using spectral and spatial features derived from LANDSAT images

A study area near Ribeirao Preto in Sao Paulo state was selected, with predominance in sugar cane. Eight features were extracted from the 4 original bands of LANDSAT image, using low-pass and high-pass filtering to obtain spatial features. There were 5 training sites in order to acquire the necessary parameters. Two groups of four channels were selected from 12 channels using JM-distance and entropy criterions. The number of selected channels was defined by physical restrictions of the image analyzer and computacional costs. The evaluation was performed by extracting the confusion matrix for training and tests areas, with a maximum likelihood classifier, and by defining performance indexes based on those matrixes for each group of channels. Results show that in spatial features and supervised classification, the entropy criterion is better in the sense that allows a more accurate and generalized definition of class signature. On the other hand, JM-distance criterion strongly reduces the misclassification within training areas.

Parada, N. D. J.↗
NASA NTRS1983

An exploitation of coregistered SIR-A, Seasat and Landsat images

Multispectral registration and classification of SIR-A, Seasat SAR, and Landsat MSS data is presented over two playas located in the northeastern Algerian Sahara. A supervised classification was made over six classes: salt, palm trees, dunes, limestones, gypsum and sand. The best classification is obtained by using all of the data. The images using radar only misclassify trees and salt, limestone and dunes, gypsum and dunes. Landsat only gives a good map but lacks the roughness information contained in the radar data. The Landsat/SIR-A combination gives a better classification than the Landsat/Seasat combination. Density number histograms computed within several classes on the Seasat and SIR-A data show the misclassification is mainly due to the Seasat data.

Rebillard, P.↗
NASA NTRS1984

Multivariate spline methods in surface fitting

The use of spline functions in the development of classification algorithms is examined. In particular, a method is formulated for producing spline approximations to bivariate density functions where the density function is decribed by a histogram of measurements. The resulting approximations are then incorporated into a Bayesiaan classification procedure for which the Bayes decision regions and the probability of misclassification is readily computed. Some preliminary numerical results are presented to illustrate the method.

Guseman, L. F., Jr.↗
NASA NTRS1984

Improved classification of small-scale urban watersheds using thematic mapper simulator data

The utility of Landsat MSS classification methods in the case of small, highly urbanized hydrological basins containing complex land-use patterns is limited, and is plagued by misclassifications due to the spectral response similarity of many dissimilar surfaces. Landsat MSS data for the Conley Creek basin near Atlanta, Georgia, have been compared to thematic mapper simulator (TMS) data obtained on the same day by aircraft. The TMS data were able to alleviate many of the recurring patterns associated with MSS data, through bandwidth optimization, an increase of the number of spectral bands to seven, and an improvement of ground resolution to 30 m. The TMS is thereby able to detect small water bodies, powerline rights-of-way, and even individual buildings.

Owe, M.↗
NASA NTRS1985

Star formation in grand design and flocculent spiral galaxies

An examination is conducted of the colors and neutral hydrogen contents of spiral galaxies which have been classified in the Elmegreen and Elmegreen arm morphology system. Using these data, possible differences between the star formation activity in spiral galaxies with and without classic spiral arms are delineated. At the same revised Hubble type, spiral galaxies with regular global arm patterns (the grand design spirals) are bluer than spiral galaxies lacking such patterns (the flocculent spirals) by a small, but statistically significant amount (approximately 0.05 in B-V and approximately 0.15 in U-V). The neutral hydrogen contents of the two groups are roughly similar, implying the star formation rate averaged over a Hubble time has been approximately the same in grand design and flocculent systems. The color differences can be explained either by using an initial mass function in the flocculent spiral galaxies which is deficient in massive stars by a factor of 2 compared with the grand design systems, or by a decrease of 30 percent in the ratio of recent to past star formation rates in flocculent galaxies. The possibility is discussed that systematic Hubble type misclassifications significantly affect these conclusions.

Romanishin, W.↗