Search NASA⌕ Search

SEARCH · Search NASA

Results for “pattern classification”

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 649 records · Page 36

Use of feature extraction techniques for the texture and context information in ERTS imagery: Spectral and textural processing of ERTS imagery

The author has identified the following significant results. A procedure was developed to extract cross-band textural features from ERTS MSS imagery. Evolving from a single image texture extraction procedure which uses spatial dependence matrices to measure relative co-occurrence of nearest neighbor grey tones, the cross-band texture procedure uses the distribution of neighboring grey tone N-tuple differences to measure the spatial interrelationships, or co-occurrences, of the grey tone N-tuples present in a texture pattern. In both procedures, texture is characterized in such a way as to be invariant under linear grey tone transformations. However, the cross-band procedure complements the single image procedure by extracting texture information and spectral information contained in ERTS multi-images. Classification experiments show that when used alone, without spectral processing, the cross-band texture procedure extracts more information than the single image texture analysis. Results show an improvement in average correct classification from 86.2% to 88.8% for ERTS image no. 1021-16333 with the cross-band texture procedure. However, when used together with spectral features, the single image texture plus spectral features perform better than the cross-band texture plus spectral features, with an average correct classification of 93.8% and 91.6%, respectively.

Haralick, R. H.↗

System diagnostic builder

The System Diagnostic Builder (SDB) is an automated software verification and validation tool using state-of-the-art Artificial Intelligence (AI) technologies. The SDB is used extensively by project BURKE at NASA-JSC as one component of a software re-engineering toolkit. The SDB is applicable to any government or commercial organization which performs verification and validation tasks. The SDB has an X-window interface, which allows the user to 'train' a set of rules for use in a rule-based evaluator. The interface has a window that allows the user to plot up to five data parameters (attributes) at a time. Using these plots and a mouse, the user can identify and classify a particular behavior of the subject software. Once the user has identified the general behavior patterns of the software, he can train a set of rules to represent his knowledge of that behavior. The training process builds rules and fuzzy sets to use in the evaluator. The fuzzy sets classify those data points not clearly identified as a particular classification. Once an initial set of rules is trained, each additional data set given to the SDB will be used by a machine learning mechanism to refine the rules and fuzzy sets. This is a passive process and, therefore, it does not require any additional operator time. The evaluation component of the SDB can be used to validate a single software system using some number of different data sets, such as a simulator. Moreover, it can be used to validate software systems which have been re-engineered from one language and design methodology to a totally new implementation.

Nieten, Joseph L.↗

Evaluation of Decision Trees for Cloud Detection from AVHRR Data

Automated cloud detection and tracking is an important step in assessing changes in radiation budgets associated with global climate change via remote sensing. Data products based on satellite imagery are available to the scientific community for studying trends in the Earth's atmosphere. The data products include pixel-based cloud masks that assign cloud-cover classifications to pixels. Many cloud-mask algorithms have the form of decision trees. The decision trees employ sequential tests that scientists designed based on empirical astrophysics studies and simulations. Limitations of existing cloud masks restrict our ability to accurately track changes in cloud patterns over time. In a previous study we compared automatically learned decision trees to cloud masks included in Advanced Very High Resolution Radiometer (AVHRR) data products from the year 2000. In this paper we report the replication of the study for five-year data, and for a gold standard based on surface observations performed by scientists at weather stations in the British Islands. For our sample data, the accuracy of automatically learned decision trees was greater than the accuracy of the cloud masks p < 0.001.

AVHRR (ADVANCED VERY HIGH RESOLUTION RADIOMETER)↗

Mesoscale Cellular Convection Detection and Classification Using Convolutional Neural Networks: Insights From Long-Term Observations at ARM Eastern North Atlantic Site

Marine boundary layer clouds are crucial in Earth's climate system. They frequently manifest as closed or open cell mesoscale cellular convection (MCC). MCC clouds are challenging to represent accurately in current climate models, highlighting the need for detailed observational data sets and in-depth analyses. This study utilizes over 8 years of observations from the U.S. Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) User Facility Eastern North Atlantic (ENA) site at Graciosa Island, Azores, to investigate these clouds. We first apply a convolutional neural network with a U-Net architecture to classify open and closed cells, marking the first application of such an approach for automatically detecting MCC patterns from ground-based radar measurements. This method addresses some observational gaps in satellite data related to low temporal resolution, nighttime challenges, and limited vertical structure capture. The analysis of the MCC cases shows clear differences between closed and open MCCs: Closed MCC clouds are characterized by lower cloud tops and bases, shallower cloud geometrical depth, weaker horizontal wind speeds, stronger atmospheric stability, and a more homogeneous liquid water path than open MCCs. Finally, we demonstrate two potential applications of our radar-based MCC classifications: (a) facilitating the investigation of aerosol-cloud interactions and (b) exploring meteorological factors along with MCC's evolution by integrating satellite imagery and back-trajectory analysis. The identified MCC cases offer a valuable resource for the scientific community to study MCC processes further and improve climate model accuracy.

54 ENVIRONMENTAL SCIENCES↗

The Occlusion Spectrum for Volume Classification and Visualization

Despite the ever-growing improvements on graphics processing units and computational power, classifying 3D volume data remains a challenge. In this paper, we present a new method for classifying volume data based on the ambient occlusion of voxels. This information stems from the observation that most volumes of a certain type, e.g., CT, MRI or flow simulation, contain occlusion patterns that reveal the spatial structure of their materials or features. Furthermore, these patterns appear to emerge consistently for different data sets of the same type. We call this collection of patterns the \emph{occlusion spectrum} of a dataset. We show that using this occlusion spectrum leads to better two-dimensional transfer functions that can help classify complex data sets in terms of the spatial relationships among features. In general, the ambient occlusion of a voxel can be interpreted as a weighted average of the intensities in a spherical neighborhood around the voxel. Different weighting schemes determine the ability to separate structures of interest in the occlusion spectrum. We present a general methodology for finding such a weighting. We show results of our approach in 3D imaging for different applications, including brain and breast tumor detection and the visualization of turbulent flow.

42 ENGINEERING↗

ThunderSecure: deploying real-time intrusion detection for 100G research networks by leveraging stream-based features and one-class classification network

Nowadays, data generated by large-scale scientific experiments are on the scale of petabytes per month. These data are transferred through dedicated high-bandwidth networks (40/100G) across distributed sites for processing, storage, and analysis. Like general purpose networks, research networks experience intrusions. However, monitoring anomalies in such high-speed network traffics is challenging given current cyber-infrastructure. Moreover, traditional network intrusion detection systems (NIDS) are signature based. However, anomaly patterns are difficult to define and that rulesets are often not updated frequently enough to reflect the changes of attack behaviors. We present ThunderSecure, a high-throughput, unsupervised learning-based intrusions detection system for 100G research networks. ThunderSecure implements an efficient packet processing and detection pipeline using multi-cores and GPUs. It extracts statistical and temporal features from real-time network data streams and feeds them to a one-class anomaly detection network. A baseline of normal distribution will be created based on the training observation. Testing traffic deviated from the learned profile will be marked as anomalies. We trained ThunderSecure on hundreds of billions of science data packets mirrored from two 100G network connections at Fermi National Accelerator Laboratory. The detection performance was evaluated on traffic captured from the same research network days and weeks after the training with different types of attack flows injected. Results show that ThunderSecure can recognize science data traffic captured long after the training and made nearly certain detection on the segment of the streams where anomalous flows were injected.

100G research network↗

Minimum Bayes risk image correlation

In this paper, the problem of designing a matched filter for image correlation will be treated as a statistical pattern recognition problem. It is shown that, by minimizing a suitable criterion, a matched filter can be estimated which approximates the optimum Bayes discriminant function in a least-squares sense. It is well known that the use of the Bayes discriminant function in target classification minimizes the Bayes risk, which in turn directly minimizes the probability of a false fix. A fast Fourier implementation of the minimum Bayes risk correlation procedure is described.

Minter, T. C., Jr.↗

Evaluating Changes in Freshwater Health in the Tonlé Sap Basin using Remotely Sensed Data

The Tonlé Sap lake and river basin provide freshwater resources to about 4.5 million people in central Cambodia. Accelerating dam construction, intensifying agriculture, deforestation, and changing climate patterns threaten the health of the lake and the food security of nearby communities. NASA DEVELOP collaborated with Conservation International to calculate multiple components of the ecosystem vitality indicator of the Freshwater Health Index for Tonlé Sap lake from 2000 – 2020 using remote sensing. Landcover classifications, lake level altimetry, groundwater storage and nutrient flows were derived from multiple satellites including Landsat 5, Landsat 7, Landsat 8, Sentinel-2, the Global Precipitation Measurement (GPM)mission, and the Gravity Recovery and Climate Experiment (GRACE). Additionally, the Soil and Water Assessment Tool (SWAT) was used to analyze nutrient flow and water quality in the basin. A breakdown in the volume and regularity of annual lake levels from 2000-2020 was observed, reflecting increased pressure on water supply and agricultural productivity. A decrease in landcover naturalness was also observed and at least 8% of forested areas in the basin were lost while rice harvest intensity increased throughout the study period. Additionally, an initial water quality analysis was demonstrated using SWAT. Continued collaboration with Conservation International and local representatives will guide the remaining water quality analyses and allow them to make informed decisions regarding freshwater management and resource allocation in the Tonlé Sap lake and river basin.

Adriana Le Compte↗

Modeling Spatial Dependencies and Semantic Concepts in Data Mining

Data mining is the process of discovering new patterns and relationships in large datasets. However, several studies have shown that general data mining techniques often fail to extract meaningful patterns and relationships from the spatial data owing to the violation of fundamental geospatial principles. In this tutorial, we introduce basic principles behind explicit modeling of spatial and semantic concepts in data mining. In particular, we focus on modeling these concepts in the widely used classification, clustering, and prediction algorithms. Classification is the process of learning a structure or model (from user given inputs) and applying the known model to the new data. Clustering is the process of discovering groups and structures in the data that are ``similar,'' without applying any known structures in the data. Prediction is the process of finding a function that models (explains) the data with least error. One common assumption among all these methods is that the data is independent and identically distributed. Such assumptions do not hold well in spatial data, where spatial dependency and spatial heterogeneity are a norm. In addition, spatial semantics are often ignored by the data mining algorithms. In this tutorial we cover recent advances in explicitly modeling of spatial dependencies and semantic concepts in data mining.

99 GENERAL AND MISCELLANEOUS↗

Existence of different intermediate Hamiltonians in type A N-fold supersymmetry II

We continue the previous study on the existence of different intermediate Hamiltonians in type A N-fold supersymmetric systems and carry out an exhaustive investigation on the N = 3 case. In contrast with the N = 2 case, we find various patterns in the existence of intermediate Hamiltonians due to the presence of two different intermediate positions in a factorized type A 3-fold supercharge. In addition, all the N = 3 models are strictly restricted to at most elliptic type, which enables us to make the complete classification of the systems which admit intermediate Hamiltonians. Finally, we show realizations of third-order parasupersymmetry and variant generalized 3-fold superalgebras by such systems.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Rapid classification of biological components

A method is disclosed for analyzing a biological sample by antibody profiling for identifying forensic samples or for detecting the presence of an analyte. In an illustrative embodiment of the invention, the analyte is a drug, such as marijuana, Cocaine (crystalline tropane alkaloid), methamphetamine, methyltestosterone, or mesterolone. The method involves attaching antigens of the surface of a solid support in a preselected pattern to form an array wherein the locations of the antigens are known; contacting the array with the biological sample such that a portion of antibodies in the sample reacts with and binds to antigens in the array, thereby forming immune complexes; washing away antibodies that do not form immune complexes; and detecting the immune complexes, thereby forming an antibody profile. Forensic samples are identified by comparing a sample from an unknown source with a sample from a known source. Further, an assay, such as a test for illegal drug use, can be coupled to a test for identity such that the results of the assay can be positively correlated to a subject's identity.

Thompson, Vicki S↗

Rapid classification of biological components

A method is disclosed for analyzing a biological sample by antibody profiling for identifying forensic samples or for detecting the presence of an analyte. In an illustrative embodiment of the invention, the analyte is a drug, such as marijuana, cocaine (crystalline tropane alkaloid), methamphetamine, methyltestosterone, or mesterolone. The method involves attaching antigens to a surface of a solid support in a preselected pattern to form an array wherein the locations of the antigens are known; contacting the array with the biological sample such that a portion of antibodies in the sample reacts with and binds to antigens in the array, thereby forming immune complexes; washing away antibodies that do not form immune complexes; and detecting the immune complexes, thereby forming an antibody profile. Forensic samples are identified by comparing a sample from an unknown source with a sample from a known source. Further, an assay, such as a test for illegal drug use, can be coupled to a test for identity such that the results of the assay can be positively correlated to a subject's identity.

Thompson, Vicki S↗

Rapid classification of biological components

A method is disclosed for analyzing a biological sample by antibody profiling for identifying forensic samples or for detecting the presence of an analyte. In an illustrative embodiment of the invention, the analyte is a drug, such as marijuana, cocaine (crystalline tropane alkaloid), methamphetamine, methyltestosterone, or mesterolone. The method involves attaching antigens to a surface of a solid support in a preselected pattern to form an array wherein the locations of the antigens are known; contacting the array with the biological sample such that a portion of antibodies in the sample reacts with and binds to antigens in the array, thereby forming immune complexes; washing away antibodies that do not form immune complexes; and detecting the immune complexes, thereby forming an antibody profile. Forensic samples are identified by comparing a sample from an unknown source with a sample from a known source. Further, an assay, such as a test for illegal drug use, can be coupled to a test for identity such that the results of the assay can be positively correlated to a subject's identity.

59 BASIC BIOLOGICAL SCIENCES↗

An algorithm for optimal single linear feature extraction from several Gaussian pattern classes

A computational algorithm is presented for the extraction of an optimal single linear feature from several Gaussian pattern classes. The algorithm minimizes the increase in the probability of misclassification in the transformed (feature) space. Numerical results on the application of this procedure to the remotely sensed data from the Purdue Cl flight line as well as LANDSAT data are presented. It was found that classification using the optimal single linear feature yielded a value for the probability of misclassification on the order of 30% less than that obtained by using the best single untransformed feature. Also, the optimal single linear feature gave performance results comparable to those obtained by using the two features which maximized the average divergence.

Starks, S. A.↗

Spaceborne microwave remote sensing of seasonal freeze-thaw processes in theterrestrial high l atitudes : relationships with land-atmosphere CO2 exchange

Landscape transitions between seasonally frozen and thawed conditions occur each year over roughly 50 million square kilometers of Earth's Northern Hemisphere. These relatively abrupt transitions represent the closest analog to a biospheric and hydrologic on/off switch existing in nature, affecting surface meteorological conditions, ecological trace gas dynamics, energy exchange and hydrologic activity profoundly. We utilize time series satellite-borne microwave remote sensing measurements from the Special Sensor Microwave Imager (SSM/I) to examine spatial and temporal variability in seasonal freeze/thaw cycles for the pan-Arctic basin and Alaska. Regional measurements of spring thaw timing are derived using daily brightness temperature measurements from the 19 GHz, horizontally polarized channel, separately for overpasses with 6 AM and 6 PM equatorial crossing times. Spatial and temporal patterns in regional freeze/thaw dynamics show distinct differences between North America and Eurasia, and boreal forest and Arctic tundra biomes. Annual anomalies in the timing of thawing in spring also correspond closely to seasonal atmospheric CO2 concentration anomalies derived from NOAA CMDL arctic and subarctic monitoring stations. Classification differences between AM and PM overpass data average approximately 5 days for the region, though both appear to be effective surrogates for monitoring annual growing seasons at high latitudes.

Sensor Microwave Imager (SSM/I)carbon cycle↗

Spaceborne Microwave Remote Sensing of Seasonal Freeze-Thaw Processes in the Terrestrial High Latitudes: Relationships with Land-Atmosphere CO2 exchange

Landscape transitions between seasonally frozen and thawed conditions occur each year over roughly 50 million square kilometers of Earth's Northern Hemisphere. These relatively abrupt transitions represent the closest analog to a biospheric and hydrologic on/off switch existing in nature, affecting surface meteorological conditions, ecological trace gas dynamics, energy exchange and hydrologic activity profoundly. We utilize time series satellite-borne microwave remote sensing measurements from the Special Sensor Microwave Imager (SSM/I) to examine spatial and temporal variability in seasonal freeze/thaw cycles for the pan-Arctic basin and Alaska. Regional measurements of spring thaw timing are derived using daily brightness temperature measurements from the 19 GHz, horizontally polarized channel, separately for overpasses with 6 AM and 6 PM equatorial crossing times. Spatial and temporal patterns in regional freeze/thaw dynamics show distinct differences between North America and Eurasia, and boreal forest and Arctic tundra biomes. Annual anomalies in the timing of thawing in spring also correspond closely to seasonal atmospheric CO2 concentration anomalies derived from NOAA CMDL arctic and subarctic monitoring stations. Classification differences between AM and PM overpass data average approximately 5 days for the region, though both appear to be effective surrogates for monitoring annual growing seasons at high latitudes.

net primary products↗

Classification of Meteorological Influences Surrounding Extreme Precipitation Events in the United States using the MERRA-2 Reanalysis

Extreme precipitation events can have a large impact on society through flooding that can result in property destruction, crop losses, economic losses, the spread of water-borne diseases, and fatalities. Observations indicate there has been a statistically significant increase in extreme precipitation events over the past 15 years in the Northeastern United States and other localized regions of the country have become crippled with record flooding events, for example, the flooding that occurred in the Southeast United States associated with Hurricane Matthew in October 2016. Extreme precipitation events in the United States can be caused by various meteorological influences such as extratropical cyclones, tropical cyclones, mesoscale convective complexes, general air mass thunderstorms, upslope flow, fronts, and the North American Monsoon. Reanalyses, such as the Modern Era Retrospective Analysis for Research and Applications, version 2 (MERRA-2), have become a pivotal tool to study the meteorology surrounding extreme precipitation events. Using days classified as an extreme precipitation events based on a combination of observational gauge and radar data, two techniques for the classification of these events are used to gather additional information that can be used to determine how events have changed over time using atmospheric data from MERRA-2. The first is self organizing maps, which is an artificial neural network that uses unsupervised learning to cluster like patterns and the second is an automated detection technique that searches for characteristics in the atmosphere that define a meteorological phenomena. For example, the automated detection for tropical cycles searches for a defined area of suppressed sea level pressure, alongside thickness anomalies aloft, indicating the presence of a warm core. These techniques are employed for extreme precipitation events in preselected regions that were chosen based an analysis of the climatology of precipitation.

Monsoon↗

SU-F-R-17: Advancing Glioblastoma Multiforme (GBM) Recurrence Detection with MRI Image Texture Feature Extraction and Machine Learning

Purpose: To test the potential of early Glioblastoma Multiforme (GBM) recurrence detection utilizing image texture pattern analysis in serial MR images post primary treatment intervention. Methods: MR image-sets of six time points prior to the confirmed recurrence diagnosis of a GBM patient were included in this study, with each time point containing T1 pre-contrast, T1 post-contrast, T2-Flair, and T2-TSE images. Eight Gray-level co-occurrence matrix (GLCM) texture features including Contrast, Correlation, Dissimilarity, Energy, Entropy, Homogeneity, Sum-Average, and Variance were calculated from all images, resulting in a total of 32 features at each time point. A confirmed recurrent volume was contoured, along with an adjacent non-recurrent region-of-interest (ROI) and both volumes were propagated to all prior time points via deformable image registration. A support vector machine (SVM) with radial-basis-function kernels was trained on the latest time point prior to the confirmed recurrence to construct a model for recurrence classification. The SVM model was then applied to all prior time points and the volumes classified as recurrence were obtained. Results: An increase in classified volume was observed over time as expected. The size of classified recurrence maintained at a stable level of approximately 0.1 cm{sup 3} up to 272 days prior to confirmation. Noticeable volume increase to 0.44 cm{sup 3} was demonstrated at 96 days prior, followed by significant increase to 1.57 cm{sup 3} at 42 days prior. Visualization of the classified volume shows the merging of recurrence-susceptible region as the volume change became noticeable. Conclusion: Image texture pattern analysis in serial MR images appears to be sensitive to detecting the recurrent GBM a long time before the recurrence is confirmed by a radiologist. The early detection may improve the efficacy of targeted intervention including radiosurgery. More patient cases will be included to create a generalizable classification model applicable to a larger patient cohort. NIH R43CA183390 and R01CA188300.NSF Graduate Research Fellowship DGE-1144087.

60 APPLIED LIFE SCIENCES↗