Search NASA⌕ Search

SEARCH · Search NASA

Results for “classifier models”

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 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
NASA NTRS2018

Supervised Learning Applied to Air Traffic Trajectory Classification

Given the recent increase of interest in introducing new vehicle types and missions into the National Airspace System, a transition towards a more autonomous air traffic control system is required in order to enable and handle increased density and complexity. This paper presents an exploratory effort of the needed autonomous capabilities by exploring supervised learning techniques in the context of aircraft trajectories. In particular, it focuses on the application of machine learning algorithms and neural network models to a runway recognition trajectory-classification study. It investigates the applicability and effectiveness of various classifiers using datasets containing trajectory records for a month of air traffic. A feature importance and sensitivity analysis are conducted to challenge the chosen time-based datasets and the ten selected features. The study demonstrates that classification accuracy levels of 90% and above can be reached in less than 40 seconds of training for most machine learning classifiers when one track data point, described by the ten selected features at a particular time step, per trajectory is used as input. It also shows that neural network models can achieve similar accuracy levels but at higher training time costs.

Bosson, Christabelle S.↗
NASA NTRS2018

Supervised Learning Applied to Air Traffic Trajectory Classification

Given the recent increase of interest in introducing new vehicle types and missions into the National Airspace System, a transition towards a more autonomous air traffic control system is required in order to enable and handle increased density and complexity. This paper presents an exploratory effort of the needed autonomous capabilities by exploring supervised learning techniques in the context of aircraft trajectories. In particular, it focuses on the application of machine learning algorithms and neural network models to a runway recognition trajectory-classification study. It investigates the applicability and effectiveness of various classifiers using datasets containing trajectory records for a month of air traffic. A feature importance and sensitivity analysis are conducted to challenge the chosen time-based datasets and the ten selected features. The study demonstrates that classification accuracy levels of 90% and above can be reached in less than 40 seconds of training for most machine learning classifiers when one track data point, described by the ten selected features at a particular time step, per trajectory is used as input. It also shows that neural network models can achieve similar accuracy levels but at higher training time costs.

Bosson, Christabelle↗
NASA NTRS1987

IMF B(y) and day-night conductivity effects in the expanding polar cap convection model

During southward B(z) periods the open field line region in the ionosphere (polar cap) expands due to increased dayside merging. Ionospheric plasma flow patterns result which can be classified by the sign of the interplanetary magnetic field (IMF) B(y) component. In this paper, a time-dependent ionospheric convection model is constructed to simulate these flows. The model consists of a spiral boundary with a gap in it. The sign of the IMF B(y) component determines the geometry of the gap. A potential is applied across the gap and distributed around the boundary. A flow results which enters the polar cap through the gap and uniformly pushes the boundary outward. Results of the model show that B(y) effects are greatest near the gap and virtually unnoticeable on the nightside of the polar cap. Adding a day-night ionospheric conductivity gradient concentrates the polar cap electric field toward dawn. The resulting flow curvature gives a sunward component that is independent of B(y). These patterns are shown to be consistent with published observations.

Moses, J. J.↗
NASA NTRS1994

Shock-tunnel combustor testing for hypersonic vehicles

Proposed configurations for the next generation of transatmospheric vehicles will rely on air breathing propulsion systems during all or part of their mission. At flight Mach numbers greater than about 7 these engines will operate in the supersonic combustion ramjet mode (scramjet). Ground testing of these engine concepts above Mach 8 requires high pressure, high enthalpy facilities such as shock tunnels and expansion tubes. These impulse, or short duration facilities have test times on the order of a millisecond, requiring high speed instrumentation and data systems. One such facility ideally suited for scramjet testing is the NASA-Ames 16-Inch shock tunnel, which over the last two years has completed a series of tests for the NASP (National Aero-Space Plane) program at simulated flight Mach numbers ranging from 12-16. The focus of the experimental programs consisted of a series of classified tests involving a near-full scale hydrogen fueled scramjet combustor model in the semi-free jet method of engine testing whereby the compressed forebody flow ahead of the cowl inlet is reproduced (see appendix A). The AIMHYE-1 (Ames Integrated Modular Hypersonic Engine) test entry for the NASP program was completed in April 1993, while AIMHYE-2 was completed in May 1994. The test entries were regarded as successful, resulting in some of the first data of its kind on the performance of a near full scale scramjet engine at Mach 12-16. The data was distributed to NASP team members for use in design system verification and development. Due to the classified nature of the hardware and data, the data reports resulting from this work are classified and have been published as part of the NASP literature. However, an unclassified AIAA paper resulted from the work and has been included as appendix A. It contains an overview of the test program and a description of some of the important issues.

Loomis, Mark P.↗
NASA NTRS2007

Interference Path Loss Prediction in A319/320 Airplanes Using Modulated Fuzzy Logic and Neural Networks

In this paper, neural network (NN) modeling is combined with fuzzy logic to estimate Interference Path Loss measurements on Airbus 319 and 320 airplanes. Interference patterns inside the aircraft are classified and predicted based on the locations of the doors, windows, aircraft structures and the communication/navigation system-of-concern. Modeled results are compared with measured data. Combining fuzzy logic and NN modeling is shown to improve estimates of measured data over estimates obtained with NN alone. A plan is proposed to enhance the modeling for better prediction of electromagnetic coupling problems inside aircraft.

Jafri, Madiha J.↗
NASA NTRSDate not supplied

Benchmark Models for Classification of Radiation Type Induced in Immune Cells

NASA Biological and Physical Sciences and the Science Mission Directorate have published a benchmark dataset of mouse immune cells subjected to radiation-induced DNA damage. The dataset comprises ML-ready microscopic imagery of said cells, including labels indicating radiation type and dose. The machine learning team at NASA Interagency Implementation and Advanced Concept Team (IMPACT) created multiple benchmark models. Initially, we conducted a preliminary analysis using thresholding. The algorithm used thresholds on average brightness of the available images to classify them into their respective radiation type. We also tested machine learning approaches. Convolutional Neural Networks (CNN) emerged as the best-performing model. This poster presents the benchmark scores obtained by the models.

Vishal Perekadan↗
NASA NTRS2024

Presound: UAV Diagnostic System Enabled by Vibration-Based Machine Learning

A low-weight, inexpensive small unmanned aerial system (sUAS) that takes off, performs a mission, lands, and safely stows and recharges itself has myriad future applications ranging from agricultural imaging to last-mile package delivery. Likewise, Urban Air Mobility (UAM) systems will enable people to take air taxis from point to point in cities, rapidly moving commuters long distances without concern for road traffic and congestion. Fully electric aviation systems will be cleaner and quieter than ground transport. Cities could eliminate cars and buses, and convert roads to higher capacity bike and pedestrian throughways. Yet, for sUAS as well as UAM, system reliability and assurance is a limiting factor to deploying affordable autonomous flight systems. For this bright future of aviation to be realized, aircraft must be able to autonomously and accurately self-diagnose health issues both before takeoff and during flight. The GreenSight PreSound system is designed to identify defects on aircraft through intelligent analysis of vibration. It accomplishes this by measuring structural vibrations induced by the vehicle’s own propellers, and analyzing that data using a machine learning model that determines whether a defect is present. The PreSound system is designed to require no human oversight, and to operate across a wide array of vehicles through re-training of the model for each target aircraft. PreSound has been developed and seen limited early success using data collected from the GreenSight Dreamer sUAS, a 5lb quadrotor vehicle designed for aerial imaging applications. The final detection model, trained on data with props spinning at 50% throttle, achieves excellent performance with over 99% average accuracy in detecting blade damage using a single FFT vector input. It demonstrates the ability to generalize to new types of blade damage, correctly classifying a different type of blade damage with 98% accuracy. Full test pulses were classified with 100% accuracy, and in live testing, all sets of data during blade movement were classified accurately with over 95% confidence. When trained on in-flight data, the same model achieves an average accuracy of 85% in distinguishing between undamaged and blade-damaged states in flight. The authors believe that these accuracies show significant potential of this approach to expand unmanned flight safety, with significant potential benefits in accelerating Advanced Aerial Mobility (AAM) and UAM aviation applications.

UAS↗
NASA NTRS1989

Flow-field characteristics and normal-force correlations for delta wings from Mach 2.4 to 4.6

An experimental investigation has been conducted to determine the upper-surface flowfield types and the normal-force characteristics of a series of delta wing models at supersonic speeds. Flow-visualization data were used to classify the flowfields into seven primary types: shockless attached flow, separation bubble, classical vortex, vortex with shock, shock with no separation, shock-induced separation, and separation bubble with shock. The pressure distributions were integrated to obtain upper and lower surface normal-force loadings. A minimal effect of sweep was observed on the upper-surface normal force at constant Mach number and a minimal effect of Mach number was noted for the 75 deg delta wing lower-surface normal force. The normal-force coefficients for all test conditions were correlated, and a single empirical equation was formulated from which the normal-force coefficient could be calculated as a function of Mach number, angle of attack, and wing aspect ratio.

Covell, Peter F.↗
NASA NTRS2005

BEAM Technology Flight Demonstration

As technologies advance, their growing complexity makes them harder to maintain. Detection methods for isolating and identifying impending problems are needed to balance this complexity. Through comparison of signal pairs from onboard sensors, the Beacon-based Exception Analysis For Multimissions (BEAM) algorithm can identify and help classify deviations in system operation from a data-trained statistical model. The goal of this task is to mature BEAM and validate its performance on a flying test bed. A series of F-18 flight demonstrations with BEAM monitoring engine parameters in real time was used to demonstrate in-the-field readiness. Captured F-18 and simulated F-18 engine data were used in model creation and training. The algorithm was then ported to the embedded system with a data buffering, file writing, and data-time-stamp monitoring shell to reduce the impact of embedded system faults on BEAM'S ability to correctly identify engine faults. Embedded system testing identified hardware related restrictions and contributed to iterative improvements in the code's runtime performance. The system was flown with forced engine flameouts and other pilot induced faults to simulate operation out of the norm. Successful detection of these faults, confirmed through post-flight data analysis, helped BEAM achieve TRL6.

Wang, David↗
NASA NTRS2021

Bhutan Agriculture: Developing a Crop Mask for Rice and Creating a Data Collection Protocol Utilizing Remotely Sensed Data in Bhutan

Rice cultivation in Bhutan has been increasingly threatened by deteriorating soil health and outbreaks of diseases and pests associated with the global change in climate patterns. Field surveys, which the national government of Bhutan has relied on to monitor remote agricultural lands, are becoming increasingly overwhelmed by growing threats to agricultural health. To address these concerns, NASA DEVELOP partnered with the Department of Agriculture of Bhutan, the Bhutan Foundation, and the Ugyen Wangchuck Institute of Conservation and Environmental Research (UWICER) and worked to increase the government of Bhutan’s agricultural monitoring capacity. Utilizing Earth observations including Landsat 8 Operational Land Imager (OLI), Sentinel-1 C-band Synthetic Aperture Radar (C-SAR), Shuttle Radar Topography Mission (SRTM), and Planet imagery, the DEVELOP team worked with NASA SERVIR and created a sampling protocol to identify rice plantations and supplement field surveys for more efficient agriculture monitoring. The analysis focused on districts Paro, Punakha, Samtse, Sarpang, Trongsa, Zhemgang, Wangdue Phodrang, and Samdrup Jongkhar in the year 2020 during the period of transplantation (June) to harvesting of rice (November). The team provided the partners with a sampling protocol for integrating NASA Earth observations into their crop monitoring methods, as well as a crop mask for rice identification and to aid crop management. The crop mask for rice was developed using the Random Forest (RF) classifier for the eight districts of Bhutan. Visually, the random forest model has proved to be more accurate and precise than the classification and Regression Tree model. Statistically, the Random Forest model was 91.8% accurate in identifying rice in Bhutan.

Yeshey Seldon↗
NASA NTRSDate not supplied

SafeAeroBERT: Towards a Safety-Informed Aerospace-Specific Language Model

As aviation systems continue to operate with high traffic, large amounts of documents containing safety-relevant data continue to be generated via reporting systems such as the Aviation Safety Reporting System (ASRS). Advanced natural language processing techniques, specifically pre-trained language models, have shown great success in domain-specific applications; however, the text in aviation safety reports is inundated with jargon and thus not fully utilized by general pre-trained models. In this research, we work towards developing a safety-informed aerospace-specific language model by pre-training a Bidirectional Encoder Representations from Transformer (BERT) model on reports from the Aviation Safety Reporting System and the National Transportation Safety Board. The resulting model, called SafeAeroBERT, is fine-tuned for the specific task of document classification, and can be further tuned for named-entity recognition, relation detection, information retrieval, and summarization. Results from the classification task are compared between SafeAeroBERT, the base BERT, and SciBERT models and show SafeAeroBERT outperforms the general BERT and SciBERT on classifying reports about weather and procedure. SafeAeroBERT can be used on custom tasks, not limited to document classification, and is intended to aid an intelligent knowledge manager for safety report repositories.

Aviation↗
NASA NTRS2023

SafeAeroBERT: Towards a Safety-Informed Aerospace-Specific Language Model

As aviation systems continue to operate with high traffic, large amounts of documents containing safety-relevant data continue to be generated via reporting systems such as the ASRS. Advanced natural language processing techniques, specifically pre-trained language models, have shown great success in domain-specific applications; however, the text in aviation safety reports is inundated with jargon and thus not fully utilized by general pre-trained models. In this research, we work towards developing a safety-informed aerospace-specific language model by pre-training a Bidirectional Encoder Representations from Transformer (BERT) model on reports from the Aviation Safety Reporting System and the National Transportation Safety Board. The resulting model, called SafeAeroBERT, is fine-tuned for the specific task of document classification, and can be further tuned for named-entity recognition, relation detection, information retrieval, and summarization. Results from the classification task are compared between SafeAeroBERT, the base BERT, and SciBERT models and show SafeAeroBERT outperforms the general BERT and SciBERT on classifying reports about human factors, aircraft, and procedure. SafeAeroBERT can be used on custom tasks, not limited to document classification, and is intended to aid an intelligent knowledge manager for safety report repositories.

Aviation↗
NASA NTRS1998

Characteristics of Forests in Western Sayani Mountains, Siberia from SAR Data

This paper investigated the possibility of using spaceborne radar data to map forest types and logging in the mountainous Western Sayani area in Siberia. L and C band HH, HV, and VV polarized images from the Shuttle Imaging Radar-C instrument were used in the study. Techniques to reduce topographic effects in the radar images were investigated. These included radiometric correction using illumination angle inferred from a digital elevation model, and reducing apparent effects of topography through band ratios. Forest classification was performed after terrain correction utilizing typical supervised techniques and principal component analyses. An ancillary data set of local elevations was also used to improve the forest classification. Map accuracy for each technique was estimated for training sites based on Russian forestry maps, satellite imagery and field measurements. The results indicate that it is necessary to correct for topography when attempting to classify forests in mountainous terrain. Radiometric correction based on a DEM (Digital Elevation Model) improved classification results but required reducing the SAR (Synthetic Aperture Radar) resolution to match the DEM. Using ratios of SAR channels that include cross-polarization improved classification and

Ranson, K. Jon↗
NASA NTRS1994

Learning time series for intelligent monitoring

We address the problem of classifying time series according to their morphological features in the time domain. In a supervised machine-learning framework, we induce a classification procedure from a set of preclassified examples. For each class, we infer a model that captures its morphological features using Bayesian model induction and the minimum message length approach to assign priors. In the performance task, we classify a time series in one of the learned classes when there is enough evidence to support that decision. Time series with sufficiently novel features, belonging to classes not present in the training set, are recognized as such. We report results from experiments in a monitoring domain of interest to NASA.

Manganaris, Stefanos↗
NASA NTRS2008

CALIPSO Satellite Lidar Identification Of Elevated Dust Over Australia Compared With Air Quality Model PM60 Forecasts

Global measurements of the vertical distribution of clouds and aerosols have been recorded by the lidar on board the CALIPSO (Cloud Aerosol Lidar Infrared Pathfinder Satellite Observations) satellite since June 2006. Such extensive, height-resolved measurements provide a rare and valuable opportunity for developing, testing and validating various atmospheric models, including global climate, numerical weather prediction, chemical transport and air quality models. Here we report on the initial results of an investigation into the performance of the Australian Air Quality Forecast System (AAQFS) model in forecasting the distribution of elevated dust over the Australian region. The model forecasts of PM60 dust distribution are compared with the CALIPSO lidar Vertical Feature Mask (VFM) data product. The VFM classifies contiguous atmospheric regions of enhanced backscatter as either cloud or aerosols. Aerosols are further classified into six subtypes. By comparing forecast PM60 concentration profiles to the spatial distribution of dust reported in the CALIPSO VFM, we can assess the model s ability to predict the occurrence and the vertical and horizontal extents of dust events within the study area.

Young, Stuart A.↗
NASA NTRS2006

Test Capability Enhancements to the NASA Langley 8-Foot High Temperature Tunnel

The NASA Langley 8-Foot High Temperature Tunnel produces true enthalpy environments simulating flight from Mach 4 to Mach 7, primarily for airbreathing propulsion and aerothermal/thermo-structural testing. Flow conditions are achieved through a methane-air heater and nozzles producing aerodynamic Mach numbers of 4, 5 or 7 and have exit diameters of 8 feet or 4.5 feet. The 12-ft long free-jet test section, housed inside a 26-ft vacuum sphere, accommodates large test articles. Recently, the facility underwent significant upgrades to support hydrocarbon fueled scramjet engine testing and to expand flight simulation capability. The upgrades were required to meet engine system development and flight clearance verification requirements originally defined by the joint NASA-Air Force X-43C Hypersonic Flight Demonstrator Project and now the Air Force X-51A Program. Enhancements to the 8-Ft. HTT were made in four areas: 1) hydrocarbon fuel delivery; 2) flight simulation capability; 3) controls and communication; and 4) data acquisition/processing. The upgrades include the addition of systems to supply ethylene and liquid JP-7 to test articles; a Mach 5 nozzle with dynamic pressure simulation capability up to 3200 psf, the addition of a real-time model angle-of-attack system; a new programmable logic controller sub-system to improve process controls and communication with model controls; the addition of MIL-STD-1553B and high speed data acquisition systems and a classified data processing environment. These additions represent a significant increase to the already unique test capability and flexibility of the facility, and complement the existing array of test support hardware such as a model injection system, radiant heaters, six-component force measurement system, and optical flow field visualization hardware. The new systems support complex test programs that require sophisticated test sequences and precise management of process fluids. Furthermore, the new systems, such as the real-time angle of attack system and the new programmable logic controller enhance the test efficiency of the facility. The motivation for the upgrades and the expanded capabilities is described here.

Harvin, S. F.↗
NASA NTRS2007

Initial Verification of GEOS-4 Aerosols Using CALIPSO and MODIS: Scene Classification

A-train sensors such as MODIS and MISR provide column aerosol properties, and in the process a means of estimating aerosol type (e.g. smoke vs. dust). Correct classification of aerosol type is important because retrievals are often dependent upon selection of the right aerosol model. In addition, aerosol scene classification helps place the retrieved products in context for comparisons and analysis with aerosol transport models. The recent addition of CALIPSO to the A-train now provides a means of classifying aerosol distribution with altitude. CALIPSO level 1 products include profiles of attenuated backscatter at 532 and 1064 nm, and depolarization at 532 nm. Backscatter intensity, wavelength ratio, and depolarization provide information on the vertical profile of aerosol concentration, size, and shape. Thus similar estimates of aerosol type using MODIS or MISR are possible with CALIPSO, and the combination of data from all sensors provides a means of 3D aerosol scene classification. The NASA Goddard Earth Observing System general circulation model and data assimilation system (GEOS-4) provides global 3D aerosol mass for sulfate, sea salt, dust, and black and organic carbon. A GEOS-4 aerosol scene classification algorithm has been developed to provide estimates of aerosol mixtures along the flight track for NASA's Geoscience Laser Altimeter System (GLAS) satellite lidar. GLAS launched in 2003 and did not have the benefit of depolarization measurements or other sensors from the A-train. Aerosol typing from GLAS data alone was not possible, and the GEOS-4 aerosol classifier has been used to identify aerosol type and improve the retrieval of GLAS products. Here we compare 3D aerosol scene classification using CALIPSO and MODIS with the GEOS-4 aerosol classifier. Dust, smoke, and pollution examples will be discussed in the context of providing an initial verification of the 3D GEOS-4 aerosol products. Prior model verification has only been attempted with surface mass comparisons and column optical depth from AERONET and MODIS.

Welton, Ellsworth J.↗
NASA NTRSDate not supplied

Virtual Fit Assessment: Validation using Historical Spacesuit Fit Data

Virtual fit tests using 3D body scans have provided a cost-effective means to predictively assess spacesuit fit for the current and future astronaut population. However, fit is a complex issue influenced by physical interferences, subjective preference, and many other factors. Fit can substantially differ between the type of hardware, environmental conditions, and tasks being performed. Namely, fit changes across different contexts, such as 3D printed mockup evaluations, pressurized one-g suited test events, neutral buoyancy and other training events, and flight extravehicular activities (EVA). These challenges make it difficult to validate virtual fit frameworks to physical suit sizing. This study proposes a new method of validation using the wealth of historically archived suit fit data. Physically Assessed Fit (PAF) data was assessed from astronauts and test volunteers who wore the legacy Extravehicular Mobility Unit (EMU). The data was collected during the past decades at NASA and considered to be most reliable and dependable. Each participant was 3D scanned for body shape and spacesuit-critical dimensions were measured per NASA guidelines. The participants’ size preference for hard upper torso (HUT) assembly was retrieved from their pressurized suit fit check records. Fit assessments were also updated after one-g EVA training, neutral buoyancy training, and EVA flights. Virtually Assessed Fit (VAF) was done by overlaying the CAD model of a HUT with the 3D body scans of the PAF participants. Each body scan was iteratively adjusted for the position inside the HUT to minimize the suit-to-body contact interference while satisfying a set of prescribed requirements. Then the residual contact area, depth, and volume were quantified as VAF metrics. This process was repeated for the different HUT sizes, including medium, large, and extra-large. Statistical modeling is currently in progress and will be presented at the conference. A statistical classifier will be developed to predict a fit probability for different HUT sizes as a function of the corresponding person’s VAF metrics. The HUT size with the highest fit probability will constitute the most likely size selection for the person, and the prediction will be compared against the corresponding PAF data. The participant data will be randomly pre-grouped into either a model development or validation subset. While the model development subset will be used to build the probability model, the validation subset will be used to assess the model accuracy. Also, the locations and magnitudes of suit-body-contacts will be estimated from VAF. This information can identify the critical suit geometry and body shape features that influence suit fit. The variations found in PAF size selections by subjects with similar VAF metrics will allow for investigations into subjective preferences, for example, tight versus loose fit. Overall, this study is expected to provide a structured validation of a virtual suit fit framework, which has not been possible in the past. The outcome can also provide useful insights and potential limitations for interpreting virtual fit tests for future spacesuit designs and population accommodation.

Han Kim↗