Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “classification 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 559 records · Page 31
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Contextualizing Air Traffic Management Conversations using Natural Language Understanding

Efficient management of air traffic and mitigation of delays depend on extracting actionable information from unstructured data, such as dialogues from the Federal Aviation Administration’s (FAA’s) Air Traffic Control System Command Center (ATCSCC) telecons. This study presents a pipeline utilizing Natural Language Processing (NLP) methods for Intent Classification (IC) and Slot Filling (SF) to identify and extract Traffic Management Initiatives (TMIs) from aviation-specific dialogues. We leveraged DeBERTa, a pre-trained transformer model, and fine-tuned it to the nuances of the aviation domain. Despite challenges posed by annotation complexities, the IC model achieved promising results with a weighted average F1-score of 0.81. Our results are close to those of human annotators, which demonstrates the model’s strong alignment with human-level performance. The SF model also showed strong performance, achieving a weighted F1-score of 0.97, which demonstrates its effectiveness in accurately predicting key slots. Our analysis revealed limitations in handling less frequent intents and slot labels due to data sparsity, motivating future efforts to adopt joint IC-SF modeling and data augmentation strategies. This research highlights the potential of domain-specific NLP to streamline decision-making in the aviation industry and improve the management of TMIs.

Air Traffic Control Management↗
NASA NTRS1993

Mapping and monitoring changes in vegetation communities of Jasper Ridge, CA, using spectral fractions derived from AVIRIS images

An important application of remote sensing is to map and monitor changes over large areas of the land surface. This is particularly significant with the current interest in monitoring vegetation communities. Most of traditional methods for mapping different types of plant communities are based upon statistical classification techniques (i.e., parallel piped, nearest-neighbor, etc.) applied to uncalibrated multispectral data. Classes from these techniques are typically difficult to interpret (particularly to a field ecologist/botanist). Also, classes derived for one image can be very different from those derived from another image of the same area, making interpretation of observed temporal changes nearly impossible. More recently, neural networks have been applied to classification. Neural network classification, based upon spectral matching, is weak in dealing with spectral mixtures (a condition prevalent in images of natural surfaces). Another approach to mapping vegetation communities is based on spectral mixture analysis, which can provide a consistent framework for image interpretation. Roberts et al. (1990) mapped vegetation using the band residuals from a simple mixing model (the same spectral endmembers applied to all image pixels). Sabol et al. (1992b) and Roberts et al. (1992) used different methods to apply the most appropriate spectral endmembers to each image pixel, thereby allowing mapping of vegetation based upon the the different endmember spectra. In this paper, we describe a new approach to classification of vegetation communities based upon the spectra fractions derived from spectral mixture analysis. This approach was applied to three 1992 AVIRIS images of Jasper Ridge, California to observe seasonal changes in surface composition.

Sabol, Donald E., Jr.↗
NASA NTRS1980

Composite model of a 3-D image

This paper presents a composite model of a moving (3-D) image especially useful for the sequential image processing and encoding. A non-linear predictor based on the composite model is described. The performance of this predictor is used as a measure of the validity of the model for a real image source. The minimization of a total mean square prediction error provides an inequality which determines a condition for the profitable use of the composite model and can serve as a decision device for the selection of the number of subsources within the model. The paper also describes statistical properties of the prediction error and contains results of computer simulation of two non-linear predictors in the case of perfect classification between subsources.

Dukhovich, I. J.↗
NASA NTRS1982

Comparison of Land Cover Information from LANDSAT MSS and Airborne TMS for Hydrological Applications: Preliminary Results

Land cover information for the Clinton River Basin (Michigan) derived from LANDSAT multispectral scanner (MSS) data was compared with that from airborne thematic mapper simulator (TMS) to investigate the probable capabilities of the thematic mapper (TM) launched aboard LANDSAT-4 in July 1982. The preliminary findings for one 7.5 minute topographic map, Mt. Clemens West, are reported. Significant improvements in land cover classification accuracy were obtained using TMS data as compared with MSS data. Overall mapping accuracy increased from 49 to 61 percent with an improvement from 71 to 84 percent in the residential category. A combination of four bands with one band in each major region of the spectrum (visible, near IR, middle IR and thermal IR) provided as good a discrimination of land cover as all seven TM bands. Based on the improved land cover classification accuracy of TM, TM data has the potential to provide more useful and effective input to US Army Corps of Engineers flood forecasting and flood damage prediction/assessment models.

Gervin, J. C.↗
NASA NTRS1983

Remote-sensing technology applied to forest assessment in California

Remote-sensing technology has been thoroughly evaluated for the analysis of California forest policy. A statewide, 1.6-acre-resolution, digital land-cover data base of Landsat Multispectral Scanner (MSS) classification has been produced. Three major resource regions have been analyzed in detail and one of them geographically integrated with 12 other physical and socioeconomic data layers to model fire and reforestation problems, using a geographic information system (GIS). A study of GIS design criteria has been conducted and the California Department of Forestry, the cooperator in all of these studies, is presently evaluating the alternatives and implementing certain aspects of them.

Peterson, D. L.↗
NASA NTRS2002

Studying Turbulence Using Numerical Simulation Databases - IX: Proceedings of the 2002 Summer Program

The ninth Summer Program of the Center for Turbulence Research was held during the period July 29th - August 23rd, 2002. The increase in number of participants, noted in the Preface to the Proceedings of the 2000 Program, continues: this year there were 50 participants from ten countries, and 30 hosts from Stanford and NASA-Ames. This Proceedings volume contains 32 papers that span a wide range of topics and an enormous range of physical scales. The papers have been divided into seven groups: Acoustics, RANS modeling, Combustion, Large-eddy simulation (LES), LES Numerics, Stratified Flows, and Fundamentals, In several cases, a paper could have fitted in more than one group so the classification is somewhat arbitrary.

Bradshaw, Peter↗
NASA NTRS2011

Collaborative Clustering for Sensor Networks

Traditionally, nodes in a sensor network simply collect data and then pass it on to a centralized node that archives, distributes, and possibly analyzes the data. However, analysis at the individual nodes could enable faster detection of anomalies or other interesting events, as well as faster responses such as sending out alerts or increasing the data collection rate. There is an additional opportunity for increased performance if individual nodes can communicate directly with their neighbors. Previously, a method was developed by which machine learning classification algorithms could collaborate to achieve high performance autonomously (without requiring human intervention). This method worked for supervised learning algorithms, in which labeled data is used to train models. The learners collaborated by exchanging labels describing the data. The new advance enables clustering algorithms, which do not use labeled data, to also collaborate. This is achieved by defining a new language for collaboration that uses pair-wise constraints to encode useful information for other learners. These constraints specify that two items must, or cannot, be placed into the same cluster. Previous work has shown that clustering with these constraints (in isolation) already improves performance. In the problem formulation, each learner resides at a different node in the sensor network and makes observations (collects data) independently of the other learners. Each learner clusters its data and then selects a pair of items about which it is uncertain and uses them to query its neighbors. The resulting feedback (a must and cannot constraint from each neighbor) is combined by the learner into a consensus constraint, and it then reclusters its data while incorporating the new constraint. A strategy was also proposed for cleaning the resulting constraint sets, which may contain conflicting constraints; this improves performance significantly. This approach has been applied to collaborative clustering of seismic and infrasonic data collected by the Mount Erebus Volcano Observatory in Antarctica. Previous approaches to distributed clustering cannot readily be applied in a sensor network setting, because they assume that each node has the same view of the data set. A view is the set of features used to represent each object. When a single data set is partitioned across several computational nodes, distributed clustering works; all objects have the same view. But when the data is collected from different locations, using different sensors, a more flexible approach is needed. This approach instead operates in situations where the data collected at each node has a different view (e.g., seismic vs. infrasonic sensors), but they observe the same events. This enables them to exchange information about the likely cluster membership relations between objects, even if they do not use the same features to represent the objects.

Wagstaff. Loro :/↗
NASA NTRSDate not supplied

From Simulation to Reality With Random Noise

The challenging environment of autonomous vehicle (AV) navigation necessitates certain functions be performed by deep neural networks. Optimizing these models involves collecting vast quantities of domain-specific training data and ensuring that the dataset is representative of expected conditions. High-fidelity simulation plays a vital role in making this process feasible, allowing a wide range of scenarios to be explored at low cost. However, learning from simulation introduces subtle biases into models, which can degrade real-world performance in unpredictable ways. This effect can be mitigated with learning schemes specialized to bridge distributional shifts (transfer learning). Given the complex nature of these methods, the underlying models, and their environments, meaningfully evaluating performance is notstraight forward. Many unrelated factors can effect an improvement in generalization accuracy, but a full ablation analysis is often difficult. To tease out signal from noise, it is necessary to understand how transfer learning performance is affected by noise itself. The goals of this paper are (i) to establish a domain randomization baseline for a simple classification transfer learning task and (ii) to validate the RRAV testbed as a platform for further research in sim-to-real learning. We generate imagery from a simulation of NASA Ames Research Center and train a small convolutional neural network (ConvNet) to classify position relative to a centerline. Further models are trained with different types of noise progressively added to the data. The models are deployed aboard the on-site test vehicle to test real-world performance. In our experiments, we find that such naive domain randomization raises sim-to-real accuracy from 64% to 79%, while training directly on real data yields an 89% accuracy ceiling. These results suggest that the isolated mechanism of domain randomization can significantly improve generalization.

simulation↗
NASA NTRS2004

A Comparison of Local Variance, Fractal Dimension, and Moran's I as Aids to Multispectral Image Classification

The accuracy of traditional multispectral maximum-likelihood image classification is limited by the skewed statistical distributions of reflectances from the complex heterogenous mixture of land cover types in urban areas. This work examines the utility of local variance, fractal dimension and Moran's I index of spatial autocorrelation in segmenting multispectral satellite imagery. Tools available in the Image Characterization and Modeling System (ICAMS) were used to analyze Landsat 7 imagery of Atlanta, Georgia. Although segmentation of panchromatic images is possible using indicators of spatial complexity, different land covers often yield similar values of these indices. Better results are obtained when a surface of local fractal dimension or spatial autocorrelation is combined as an additional layer in a supervised maximum-likelihood multispectral classification. The addition of fractal dimension measures is particularly effective at resolving land cover classes within urbanized areas, as compared to per-pixel spectral classification techniques.

Emerson, Charles W.↗
NASA NTRSDate not supplied

Transcribing Air Traffic Control System Command Center Planning Telecons Using Cloud-Based Automatic Speech Recognition

This paper addresses the challenge of using Automatic Speech Recognition (ASR) technology to transcribe regular teleconferences that happen between FAA Air Traffic Control System Command Center (ATCSCC) planners, stakeholders and air users. These planning teleconferences (aka telecons or planning webinars) are an integral part of managing air traffic in the U.S. National Airspace System (NAS). In particular, the meetings facilitate the creation and modification of various traffic management initiatives (TMIs), that are used to regulate the flow of air traffic. This is typically a human intensive process, requiring specialists to listen to the entire meeting audio (10-20 minutes duration) and inferring the state of the NAS (e.g., weather phenomenon) that was discussed. It would be advantageous to have digital transcripts of the audio and have useful information (e.g., related to TMIs) automatically extracted from the transcripts. In this regard, we are exploring the adoption of state-of-the-art speech to text and Natural Language Processing (NLP) tools that will achieve our objective of digitizing the webinar audio. Unfortunately, the highly technical phraseology present in the audio and limited data availability for model building make ASR difficult. To overcome this challenge, we have taken the critical first step in creating a human transcription dataset from ~20 hours of speech in the ATCSCC audio with the help of subject matter experts. A novelty of our work is the creation of a ground truth transcription dataset for ATCSCC teleconference webinars, which is particularly important for Aviation domain-specific NLP tasks. Using Microsoft Speech Studio, a cloud-based ASR platform, we have fine-tuned the English pre-trained ASR models (available in speech studio) and achieved an average word error rate (WER) of 6.81%. The baseline ASR also provides a digital version of each planning webinar, making it accessible and text-searchable for future references. Additionally, the transcriptions can serve as a bridge between raw audio data and a range of text-based NLP tasks, such as named entity recognition (NER) and intent classification, potentially enhancing the digital footprint of the webinars and other connected data sources. Our work has several potential applications. Firstly, the transcriptions can be analyzed to understand the complex decision process of creating, implementing and modifying TMIs and may also contribute to TMI prediction services. Secondly, our dataset and model can be used to develop more accurate ASR systems for aviation-specific language, which can bring about digital communication in the aviation industry (and aid current “voice only” communications, which are inherently error-prone). Lastly, the transcriptions themselves can be used as a valuable resource for training other NLP models.

Stephen S. B. Clarke↗
NASA NTRS2016

Automated Segmentation and Classification of Coral using Fluid Lensing from Unmanned Airborne Platforms

In recent years, there has been a growing interest among biologists in monitoring the short and long term health of the world's coral reefs. The environmental impact of climate change poses a growing threat to these biologically diverse and fragile ecosystems, prompting scientists to use remote sensing platforms and computer vision algorithms to analyze shallow marine systems. In this study, we present a novel method for performing coral segmentation and classification from aerial data collected from small unmanned aerial vehicles (sUAV). Our method uses Fluid Lensing algorithms to remove and exploit strong optical distortions created along the air-fluid boundary to produce cm-scale resolution imagery of the ocean floor at depths up to 5 meters. A 3D model of the reef is reconstructed using structure from motion (SFM) algorithms, and the associated depth information is combined with multidimensional maximum a posteriori (MAP) estimation to separate organic from inorganic material and classify coral morphologies in the Fluid-Lensed transects. In this study, MAP estimation is performed using a set of manually classified 100 x 100 pixel training images to determine the most probable coral classification within an interrogated region of interest. Aerial footage of a coral reef was captured off the coast of American Samoa and used to test our proposed method. 90 x 20 meter transects of the Samoan coastline undergo automated classification and are manually segmented by a marine biologist for comparison, leading to success rates as high as 85%. This method has broad applications for coastal remote sensing, and will provide marine biologists access to large swaths of high resolution, segmented coral imagery.

algorithms segments classifications↗
NASA NTRS2015

Automated Segmentation and Classification of Coral Using Fluid Lensing from Unmanned Airborne Platforms

In recent years, there has been a growing interest among biologists in monitoring the short and long term health of the worlds coral reefs. The environmental impact of climate change poses a growing threat to these biologically diverse and fragile ecosystems, prompting scientists to use remote sensing platforms and computer vision algorithms to analyze shallow marine systems. In this study, we present a novel method for performing coral segmentation and classification from aerial data collected from small unmanned aerial vehicles (sUAV). Our method uses Fluid Lensing algorithms to remove and exploit strong optical distortions created along the air-fluid boundary to produce cm-scale resolution imagery of the ocean floor at depths up to 5 meters. A 3D model of the reef is reconstructed using structure from motion (SFM) algorithms, and the associated depth information is combined with multidimensional maximum a posteriori (MAP) estimation to separate organic from inorganic material and classify coral morphologies in the Fluid-Lensed transects. In this study, MAP estimation is performed using a set of manually classified 100 x 100 pixel training images to determine the most probable coral classification within an interrogated region of interest. Aerial footage of a coral reef was captured off the coast of American Samoa and used to test our proposed method. 90 x 20 meter transects of the Samoan coastline undergo automated classification and are manually segmented by a marine biologist for comparison, leading to success rates as high as 85. This method has broad applications for coastal remote sensing, and will provide marine biologists access to large swaths of high resolution, segmented coral imagery.

algorithms segments classifications↗
NASA NTRS1992

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.↗
NASA NTRS2014

The Unusual Multiwavelength Properties of the Gamma-Ray Source PMN J1603-4904

Context. We investigate the nature and classification of PMNJ1603-4904, a bright radio source close to the Galactic plane, which is associated with one of the brightest hard-spectrum gamma-ray sources detected by Fermi/LAT. It has previously been classified as a low peaked BL Lac object based on its broadband emission and the absence of optical emission lines. Optical measurements, however, suffer strongly from extinction and the absence of pronounced short-time gamma-ray variability over years of monitoring is unusual for a blazar. Aims. In this paper, we are combining new and archival multi-wavelength data of PMNJ1603-4904 in order to reconsider the classification and nature of this unusual gamma-ray source. Methods. For the first time, we study the radio morphology of PMNJ1603-4904 at 8.4GHz and 22.3GHz, and its spectral properties on milliarcsecond scales, based on VLBI observations from the TANAMI program. We combine the resulting images with multi-wavelength data in the radio, IR, optical/UV, X-ray, and gamma-ray regimes. Results. PMNJ1603-4904 shows a symmetric brightness distribution at 8.4 GHz on milliarcsecond scales, with the brightest, and most compact component in the center of the emission region. The morphology is reminiscent of a compact symmetric object (CSO). Such objects, thought to be young radio galaxies, have been predicted to produce gamma-ray emission but have not been detected as a class by the Fermi gamma-ray telescope so far. Sparse (u, v)-coverage at 22.3GHz prevents an unambiguous modeling of the source morphology at this higher frequency. Moreover, infrared measurements reveal an excess in the spectral energy distribution (SED), which can be modeled with a blackbody with a temperature of about 1600 K, and which is usually not present in blazar SEDs. Conclusions. The TANAMI VLBI data and the shape of the broadband SED challenge the current blazar classification of one of the brightest gamma-ray sources in the sky. PMNJ1603-4904 seems to be either a highly peculiar BL Lac object or a misaligned jet source. In the latter case, the intriguing VLBI structure opens room for a possible classification of PMNJ1603-4904 as a gamma-ray bright CSO.

Multiwavelength↗
NASA NTRS1975

Mapping of the wildland fuel characteristics of the Santa Monica mountains of Southern California

LANDSAT digital data was successfully used to map and evaluate the wildland fuels of the Santa Monica Mountains in Southern California. A mixed classification scheme was used where training areas of known vegetation types were entered and the maximum likelihood classifier run, followed by an evaluation of the results and an unsupervised retraining of the classifier using an image of the probability of misclassification. Estimation of maturity class and crown closure percents of the major cover types were assigned to each computer class by associating the photointerpretation of 159 large scale photo samples with the resultant computer classes using analysis of variance and analysis of categorized data. The result of the computer classification and statistical analysis were then transformed from the LANDSAT Coordinate California State Plane Coordinate system for use in a digital format in the FIRESCOPE data retrieval and fire modeling system.

Nichols, J. D.↗
NASA NTRS1990

Mesoscale monitoring of the soil freeze/thaw boundary from orbital microwave radiometry

A technique was developed for mapping the spatial extent of frozen soils from the spectral characteristics of the 10.7 to 37 GHz radiobrightness. Through computational models for the spectral radiobrightness of diurnally heated freesing soils, a distinctive radiobrightness signature was identified for frozen soils, and the signature was cast as a discriminant for unsupervised classification. In addition to large area images, local area spatial averages of radiobrightness were calculated for each radiobrightness channel at 7 meteorologic sites within the test region. Local area averages at the meteorologic sites were used to define the preliminary boundaries in the Freeze Indicator discriminate. Freeze Indicator images based upon Nimbus 7, Scanning Multichannel Microwave Radiometer (SMMR) data effectively map temporal variations in the freeze/thaw pattern for the northern Great Plains at the time scale of days. Diurnal thermal gradients have a small but measurable effect upon the SMMR spectral gradient. Scale-space filtering can be used to improve the spatial resolution of a freeze/thaw classified image.

Dobson, Craig↗
NASA NTRS2001

Analysis of the Westland Data Set

The "Westland" set of empirical accelerometer helicopter data with seeded and labeled faults is analyzed with the aim of condition monitoring. The autoregressive (AR) coefficients from a simple linear model encapsulate a great deal of information in a relatively few measurements; and it has also been found that augmentation of these by harmonic and other parameters call improve classification significantly. Several techniques have been explored, among these restricted Coulomb energy (RCE) networks, learning vector quantization (LVQ), Gaussian mixture classifiers and decision trees. A problem with these approaches, and in common with many classification paradigms, is that augmentation of the feature dimension can degrade classification ability. Thus, we also introduce the Bayesian data reduction algorithm (BDRA), which imposes a Dirichlet prior oil training data and is thus able to quantify probability of error in all exact manner, such that features may be discarded or coarsened appropriately.

Wen, Fang↗
NASA NTRS2004

Optical Calibration Process Developed for Neural-Network-Based Optical Nondestructive Evaluation Method

A completely optical calibration process has been developed at Glenn for calibrating a neural-network-based nondestructive evaluation (NDE) method. The NDE method itself detects very small changes in the characteristic patterns or vibration mode shapes of vibrating structures as discussed in many references. The mode shapes or characteristic patterns are recorded using television or electronic holography and change when a structure experiences, for example, cracking, debonds, or variations in fastener properties. An artificial neural network can be trained to be very sensitive to changes in the mode shapes, but quantifying or calibrating that sensitivity in a consistent, meaningful, and deliverable manner has been challenging. The standard calibration approach has been difficult to implement, where the response to damage of the trained neural network is compared with the responses of vibration-measurement sensors. In particular, the vibration-measurement sensors are intrusive, insufficiently sensitive, and not numerous enough. In response to these difficulties, a completely optical alternative to the standard calibration approach was proposed and tested successfully. Specifically, the vibration mode to be monitored for structural damage was intentionally contaminated with known amounts of another mode, and the response of the trained neural network was measured as a function of the peak-to-peak amplitude of the contaminating mode. The neural network calibration technique essentially uses the vibration mode shapes of the undamaged structure as standards against which the changed mode shapes are compared. The published response of the network can be made nearly independent of the contaminating mode, if enough vibration modes are used to train the net. The sensitivity of the neural network can be adjusted for the environment in which the test is to be conducted. The response of a neural network trained with measured vibration patterns for use on a vibration isolation table in the presence of various sources of laboratory noise is shown. The output of the neural network is called the degradable classification index. The curve was generated by a simultaneous comparison of means, and it shows a peak-to-peak sensitivity of about 100 nm. The following graph uses model generated data from a compressor blade to show that much higher sensitivities are possible when the environment can be controlled better. The peak-to-peak sensitivity here is about 20 nm. The training procedure was modified for the second graph, and the data were subjected to an intensity-dependent transformation called folding. All the measurements for this approach to calibration were optical. The peak-to-peak amplitudes of the vibration modes were measured using heterodyne interferometry, and the modes themselves were recorded using television (electronic) holography.

Decker, Arthur J.↗