Search NASA⌕ Search

SEARCH · Search NASA

Results for “Selective 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 253 records · Page 14

Prediction of Cognitive States During Flight Simulation Using Multimodal Psychophysiological Sensing

The Commercial Aviation Safety Team found the majority of recent international commercial aviation accidents attributable to loss of control inflight involved flight crew loss of airplane state awareness (ASA), and distraction was involved in all of them. Research on attention-related human performance limiting states (AHPLS) such as channelized attention, diverted attention, startle/surprise, and confirmation bias, has been recommended in a Safety Enhancement (SE) entitled "Training for Attention Management." To accomplish the detection of such cognitive and psychophysiological states, a broad suite of sensors was implemented to simultaneously measure their physiological markers during a high fidelity flight simulation human subject study. Twenty-four pilot participants were asked to wear the sensors while they performed benchmark tasks and motion-based flight scenarios designed to induce AHPLS. Pattern classification was employed to predict the occurrence of AHPLS during flight simulation also designed to induce those states. Classifier training data were collected during performance of the benchmark tasks. Multimodal classification was performed, using pre-processed electroencephalography, galvanic skin response, electrocardiogram, and respiration signals as input features. A combination of one, some or all modalities were used. Extreme gradient boosting, random forest and two support vector machine classifiers were implemented. The best accuracy for each modality-classifier combination is reported. Results using a select set of features and using the full set of available features are presented. Further, results are presented for training one classifier with the combined features and for training multiple classifiers with features from each modality separately. Using the select set of features and combined training, multistate prediction accuracy averaged 0.64 +/- 0.14 across thirteen participants and was significantly higher than that for the separate training case. These results support the goal of demonstrating simultaneous real-time classification of multiple states using multiple sensing modalities in high fidelity flight simulators. This detection is intended to support and inform training methods under development to mitigate the loss of ASA and thus reduce accidents and incidents.

Harrivel, Angela R.↗

Data-Driven Surface Traversability Analysis for Mars 2020 Landing Site Selection

The objective of this paper is three-fold: 1) to describe the engineering challenges in the surface mobility of the Mars 2020 Rover mission that are considered in the landing site selection processs, 2) to introduce new automated traversability analysis capabilities, and 3) to present the preliminary analysis results for top candidate landing sites. The analysis capabilities presented in this paper include automated terrain classification, automated rock detection, digital elevation model (DEM) generation, and multi-ROI (region of interest) route planning. These analysis capabilities enable to fully utilize the vast volume of high-resolution orbiter imagery, quantitatively evaluate surface mobility requirements for each candidate site, and reject subjectivity in the comparison between sites in terms of engineering considerations. The analysis results supported the discussion in the Second Landing Site Workshop held in August 2015, which resulted in selecting eight candidate sites that will be considered in the third workshop.

Ono, Masahiro↗

Automatic photointerpretation for land use management in Minnesota

The author has identified the following significant results. The Minnesota Iron Range area was selected as one of the land use areas to be evaluated. Six classes were selected: (1) hardwood; (2) conifer; (3) water (including in mines); (4) mines, tailings and wet areas; (5) open area; and (6) urban. Initial classification results show a correct classification of 70.1 to 95.4% for the six classes. This is extremely good. It can be further improved since there were some incorrect classifications in the ground truth.

Swanlund, G. D.↗

Deep infrared galaxies

High signal-to-noise ratio optical spectra of 17 infrared-bright emission-line galaxies near the north ecliptic pole are presented. Reddening-corrected line ratios forbidden O III 5007/H-beta, N II 6583/H-alpha, S II (6716 + 6731)/H-alpha, and O I 6300/H-alpha are used to discriminate between candidate energy generation mechanisms in each galaxy. These criteria have frequently been applied to optically selected samples of galaxies in the past, but this is the first time they have been applied to a set of faint flux-limited infrared-selected objects. The analysis indicates the sample contains seven starburst galaxies and three (AGN). However, seven galaxies in the present sample elude the classification scheme based on these line ratios. It is concluded that a two-component (starburst plus AGN) model for energy generation is inadequate for infrared galaxies.

Ashby, Matthew↗

Interpretable Machine Learning Models for Autonomous Characterization of Analogue Ocean World Seawater Chemistry and Biosignature Potential Using Isotope Ratio Data

Background: Future missions to ocean worlds, such as Enceladus and Europa, will attempt to characterize the subsurface seawater chemistry and assess the potential for life. Such missions will be equipped with capabilities to precisely measure volatile isotopes in plumes, atmospheres, and exospheres. Motivation: While large isotopic fractionations can indicate a biological source, there are signatures resulting from abiotic geochemical processes that mimic isotopic biosignatures. While machine learning (ML) has the potential to disentangle competing effects and biotic mimicry, high-dimensional isotope ratio mass spectrometry (IRMS) data is likely to contain noise/irrelevant features and involve complex statistical interactions that make human inference and interpretation difficult. Further, ML predictions with as far-reaching implications as an extraterrestrial biosignature on an ocean world requires the use of interpretable models (i.e., not “black box” models) with physically and mathematically meaningful feature spaces along with false positive diagnostics. Methods: We use volatile CO2 IRMS data of analogue ocean world seawaters to validate an ML approach to provide biogeochemical context for biosignature detection. We employ a feature selection method called nearest-neighbor projected distance regression (NPDR) that detects statistical interactions and helps elucidate the mechanisms of the Random Forest classification models. Results: We train and validate predictive ML models on volatile CO2 IRMS data of analogue ocean world seawaters to predict major salt components (e.g., MgSO4, NaHCO3), pH, ionic strength, and the presence of biosignatures. Features derived from IRMS measurements are augmented with extracted time-series features. Our results show high test accuracy and interpretability, which is increased by interaction network visualization, sample-wise variable importance scores, and single-sample class probability estimates. We demonstrate an ML mission software solution that triggers autonomous data transmission and biogeochemical sample prediction.

geochemistry↗

Consensus theoretic classification methods

Consensus theory is adopted as a means of classifying geographic data from multiple sources. The foundations and usefulness of different consensus theoretic methods are discussed in conjunction with pattern recognition. Weight selections for different data sources are considered and modeling of non-Gaussian data is investigated. The application of consensus theory in pattern recognition is tested on two data sets: 1) multisource remote sensing and geographic data and 2) very-high-dimensional remote sensing data. The results obtained using consensus theoretic methods are found to compare favorably with those obtained using well-known pattern recognition methods. The consensus theoretic methods can be applied in cases where the Gaussian maximum likelihood method cannot. Also, the consensus theoretic methods are computationally less demanding than the Gaussian maximum likelihood method and provide a means for weighting data sources differently.

Benediktsson, Jon A.↗

Pattern recognition principles

The present work gives an account of basic principles and available techniques for the analysis and design of pattern processing and recognition systems. Areas covered include decision functions, pattern classification by distance functions, pattern classification by likelihood functions, the perceptron and the potential function approaches to trainable pattern classifiers, statistical approach to trainable classifiers, pattern preprocessing and feature selection, and syntactic pattern recognition.

Tou, J. T.↗

LANDSAT imagery of the Venetian Lagoon: A multitemporal analysis

The use of LANDSAT multispectral scanner images from 1975 to 1979 to determine pollution dispersion in the central basin of the lagoon under varying tidal conditions is described. Images taken during the late spring and representing both short and long range tidal dynamics were processed for partial haze removal and removal of residual striping. Selected spectral bands were correlated to different types of turbid water. The multitemporal data was calibrated, classified considering sea truth data, and evaluated. The classification differentiated tide diffusion, algae belts, and industrial, agricultural, and urban turbidity distributions. Pollution concentration is derived during the short time interval between inflow and outflow and from the distance between the two lagoon inlets and the industrial zones. Increasing pollution of the lagoon is indicated.

Alberotanza, L.↗

NASA/BLM APT, phase 2. Volume 2: Technology demonstration

Techniques described include: (1) steps in the preprocessing of LANDSAT data; (2) the training of a classifier; (3) maximum likelihood classification and precision; (4) geometric correction; (5) class description; (6) digitizing; (7) digital terrain data; (8) an overview of sample design; (9) allocation and selection of primary sample units; (10) interpretation of secondary sample units; (11) data collection ground plots; (12) data reductions; (13) analysis for productivity estimation and map verification; (14) cost analysis; and (150) LANDSAT digital products. The evaluation of the pre-inventory planning for P.J. is included.

Source record↗

Black Holes and Neutron Stars in Nearby Galaxies: Insights from NuSTAR

Nearby galaxy surveys have long classified X-ray binaries (XRBs) by the mass category of their donor stars (high-mass and low-mass). The NuSTAR (Nuclear Spectroscopic Telescope Array) observatory, which provides imaging data at E greater than 10 keV (kiloelectronvolts), has enabled the classification of extragalactic XRBs by their compact object type: neutron star (NS) or black hole (BH). We analyzed NuSTAR/Chandra/XMM-Newton observations from a NuSTAR-selected sample of 12 galaxies within 5 Mpc (megaparsecs) having stellar masses (M (sub asterisk)) 10 (sup 7-11) solar masses and star formation rates (SFRs) approximately 0.01-15 solar masses per year. We detected 128 NuSTAR sources to a sensitivity of 10 (sup 38) ergs per second. Using NuSTAR color-intensity and color-color diagrams we classified 43 of these sources as candidate NSs and 47 as candidate BHs. We further subdivide BHs by accretion states (soft, intermediate, and hard) and NSs by weak (Z/Atoll) and strong (accreting pulsar) magnetic field. Using eight normal (Milky Way-type) galaxies in the sample, we confirm the relation between the SFR and galaxy X-ray point source luminosity in the 4-25 and 12-25 keV energy bands. We also constrained galaxy X-ray point source luminosity using the relation L (sub X) equals M (sub asterisk) plus Beta SFR, finding agreement with previous work. The X-ray luminosity function (XLF) of all sources in the 4-25 and 12-25 keV energy bands matches the alpha = 1.6 slope for high-mass XRBs. We find that NS XLFs suggest a decline beginning at the Eddington limit for a 1.4 solar mass NS, whereas the BH fraction shows an approximate monotonic increase in the 4-25 and 12-25 keV energy bands. We calculate the overall ratio of BH to NS to be approximately 1 for 4-25 keV and approximately 2 for 12-25 keV.

Vulic, N.↗

Selecting reconnaissance strategies for floodplain surveys

Multispectral aircraft and satellite data over the West Branch of the Susquehanna River were analyzed to evaluate potential contributions of remote sensing to flood-plain surveys. Multispectral digital classifications of land cover features indicative of floodplain areas were used by interpreters to locate various floodprone area boundaries. The digital approach permitted LANDSAT results to be displayed at 1:24,000 scale and aircraft results at even larger scales. Results indicate that remote sensing techniques can delineate floodprone areas more easily in agricultural and limited development areas as opposed to areas covered by a heavy forest canopy. At this time it appears that the remote sensing data would be best used as a form of preliminary planning information or as an internal check on previous or ongoing floodplain studies. In addition, the remote sensing techniques can assist in effectively monitoring floodplain activities after a community enters into the National Flood Insurance Program.

Sollers, S. C.↗

Support Vector Machines for Hyperspectral Remote Sensing Classification

The Support Vector Machine provides a new way to design classification algorithms which learn from examples (supervised learning) and generalize when applied to new data. We demonstrate its success on a difficult classification problem from hyperspectral remote sensing, where we obtain performances of 96%, and 87% correct for a 4 class problem, and a 16 class problem respectively. These results are somewhat better than other recent results on the same data. A key feature of this classifier is its ability to use high-dimensional data without the usual recourse to a feature selection step to reduce the dimensionality of the data. For this application, this is important, as hyperspectral data consists of several hundred contiguous spectral channels for each exemplar. We provide an introduction to this new approach, and demonstrate its application to classification of an agriculture scene.

Gualtieri, J. Anthony↗

Statistical Emulator for Expensive Classification Simulators

Expensive simulators prevent any kind of meaningful analysis to be performed on the phenomena they model. To get around this problem the concept of using a statistical emulator as a surrogate representation of the simulator was introduced in the 1980's. Presently, simulators have become more and more complex and as a result running a single example on these simulators is very expensive and can take days to weeks or even months. Many new techniques have been introduced, termed criteria, which sequentially select the next best (most informative to the emulator) point that should be run on the simulator. These criteria methods allow for the creation of an emulator with only a small number of simulator runs. We follow and extend this framework to expensive classification simulators.

Ross, Jerret↗

Exploring Applications of Machine Learning for Wildfire Monitoring and Detection using Unmanned Aerial Vehicles

Wildfires are increasing in frequency and severity around the world, including the United States. The losses caused by wildfires could be mitigated if high-risk areas, hotspots, and flare-ups could be monitored continuously, such as through the use of Unmanned Aerial Vehicles (UAVs). This paper documents exploratory efforts using machine learning to determine efficient flight paths for UAVs and to detect wildfires using image classification. On path planning, three machine learning techniques—Genetic Algorithm, Simulated Annealing, and Dynamic Programming—were explored. Genetic Algorithm was found to be an effective approach for path planning for wildfire monitoring and surveillance by UAVs. For a scenario of 25 locations in a circular arrangement, the algorithm was able to return the optimal path. The accuracy and execution time was found to be sensitive to the algorithm hyperparameters selected, which was especially evident in scenarios with hundreds or thousands of locations. Simulated Annealing was also found to be an effective approach for UAV path planning, with a major benefit of avoiding getting trapped in local minima and being straightforward to implement. Like Genetic Algorithm, the performance of Simulated Annealing was also found to be sensitive to the algorithm hyperparameters selected. By comparison, Dynamic Programming guarantees optimality for any number of locations, but it was found to be less practical in terms of execution time for scenarios with more than about a couple dozen locations. On wildfire detection, image classification using deep learning with a convolutional neural network was explored. Transfer learning was found to be a useful technique to efficiently train deep learning models. Also, it was determined that GPU processing can increase training speed by an order of magnitude, which enables significantly faster development. For a validation test set of 500 images, there were only two false negatives and zero false positives. These results demonstrate that detecting wildfires in static cameras using machine learning is feasible and establish a baseline for using images captured by UAVs in flight for wildfire detection.

Wildfire management↗

A Machine Learning-Based Cloud Detection and Thermodynamic Phase Classification Algorithm using Passive Spectral Observations

We trained two Random Forest (RF) machine-learning models for cloud mask and cloud thermodynamic phase detection using spectral observations from VIIRS on Suomi NPP (SNPP). Observations from CALIOP were carefully selected to provide reference labels. The two RF models were trained for all-day and daytime-only conditions using a 4-year collocated VIIRS/CALIOP dataset from 2013 to 2016. Due to the orbit difference, the collocated CALIOP and SNPP VIIRS training samples cover a broad viewing zenith angle range, which is a great benefit to overall model performance. The all-day model uses 3 VIIRS infrared (IR) bands (8.6,11, and 12 μm) and the daytime model uses 5 Near-IR (NIR) and Shortwave-IR (SWIR) bands (0.86, 1.24, 1.38, 1.64 and 2.25 μm) together with the 3 IR bands to detect clear, liquid water, and ice cloud pixels. Up to 7 surface types, namely, ocean/water, forest, cropland, grassland, snow/ice, barren/desert, and shrubland, were considered separately to enhance performance for both models. Detection of cloudy pixels and thermodynamic phase with the two RF models were compared against collocated CALIOP products from 2017. It is shown that, with a conservative screening process that excludes the most challenging cloudy pixels for passive remote sensing, the two RF models have high accuracy rates in comparison with the CALIOP reference for both cloud detection and thermodynamic phase. Other existing SNPP VIIRS and Aqua MODIS cloud mask and phase products are also evaluated, with results showing that the two RF models and the MODIS MYD06 optical property phase product are the top 3 algorithms with respect to lidar observations during the daytime. During the nighttime, the RF all-day model works best for both cloud detection and phase, in particular for pixels over snow/ice surfaces. The present RF models can be extended to other similar passive instruments if training samples can be collected from CALIOP or other lidars. However, the quality of reference labels and potential sampling issues that may impact model performance would need further attention.

cloud detection↗

Fuzzy sets, rough sets, and modeling evidence: Theory and Application. A Dempster-Shafer based approach to compromise decision making with multiattributes applied to product selection

The Dempster-Shafer theory of evidence is applied to a multiattribute decision making problem whereby the decision maker (DM) must compromise with available alternatives, none of which exactly satisfies his ideal. The decision mechanism is constrained by the uncertainty inherent in the determination of the relative importance of each attribute element and the classification of existing alternatives. The classification of alternatives is addressed through expert evaluation of the degree to which each element is contained in each available alternative. The relative importance of each attribute element is determined through pairwise comparisons of the elements by the decision maker and implementation of a ratio scale quantification method. Then the 'belief' and 'plausibility' that an alternative will satisfy the decision maker's ideal are calculated and combined to rank order the available alternatives. Application to the problem of selecting computer software is given.

Dekorvin, Andre↗

Seasat over-land scatterometer data. II - Selection of extended area land-target sites for the calibration of spaceborne scatterometers

The post-launch performance verification for future scatterometers can use extended area land targets to calibrate antenna gain patterns and to verify and monitor deployment configurations. For the Ku-band Seasat scatterometer, a region of tropical rain forest in the Amazon basin was used as a homogeneous extended-area land target. As this region is continuously being deforested, other regions are investigated for calibrating scatterometers. The global backscatter coefficients (sigma0) are compared to classifications of natural vegetation and cultivation intensity and the variability with time during the three-month mission is studied. The statistical variability of sigma0 is compared with prior estimates resulting from the known variability of the instrument parameters and communication noise. Data from selected forested regions with relatively homogeneous sigma0 and little time-dependence are presented.

Kennett, Rosemary G.↗

An Iterative Approach to the Feature Selection Problem

The problem dealt with concerns feature selection or reducing the dimension of the data to be processed from n to k. By reducing the dimension of the data from n to k, classification time is generally reduced. Yet the dimension reduction should not be so great that classification accuracy is impaired. Thus, the general problem is considered of classifying an n-dimensional observation vector x into one of m-distinct classes where each class is normally distributed with mean and covariance. It is shown that the probability of misclassification is minimized if a maximum likelihood classification procedure is used to classify the data. The dimension of each observation vector to be processed is conveniently reduced by performing the transformation y = Bx, where B is a K by n matrix of rank k. Thus, the n-dimensional classification problem transforms into a k-dimensional classification problem.

Decell, H. P., Jr.↗