Search NASA⌕ Search

SEARCH · Search NASA

Results for “tree network”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS1992

Scheduling of an aircraft fleet

Scheduling is the task of assigning resources to operations. When the resources are mobile vehicles, they describe routes through the served stations. To emphasize such aspect, this problem is usually referred to as the routing problem. In particular, if vehicles are aircraft and stations are airports, the problem is known as aircraft routing. This paper describes the solution to such a problem developed in OMAR (Operative Management of Aircraft Routing), a system implemented by Bull HN for Alitalia. In our approach, aircraft routing is viewed as a Constraint Satisfaction Problem. The solving strategy combines network consistency and tree search techniques.

Paltrinieri, Massimo↗
NASA NTRS2004

Support vector machines

Support Vector Machines (SVMs) are a type of supervised learning algorith,, other examples of which are Artificial Neural Networks (ANNs), Decision Trees, and Naive Bayesian Classifiers. Supervised learning algorithms are used to classify objects labled by a 'supervisor' - typically a human 'expert.'.

multiangle↗
NASA NTRS2004

NASA Tech Briefs, April 2004

Topics covered include: Analysis of SSEM Sensor Data Using BEAM; Hairlike Percutaneous Photochemical Sensors; Video Guidance Sensors Using Remotely Activated Targets; Simulating Remote Sensing Systems; EHW Approach to Temperature Compensation of Electronics; Polymorphic Electronic Circuits; Micro-Tubular Fuel Cells; Whispering-Gallery-Mode Tunable Narrow-Band-Pass Filter; PVM Wrapper; Simulation of Hyperspectral Images; Algorithm for Controlling a Centrifugal Compressor; Hybrid Inflatable Pressure Vessel; Double-Acting, Locking Carabiners; Position Sensor Integral with a Linear Actuator; Improved Electromagnetic Brake; Flow Straightener for a Rotating-Drum Liquid Separator; Sensory-Feedback Exoskeletal Arm Controller; Active Suppression of Instabilities in Engine Combustors; Fabrication of Robust, Flat, Thinned, UV-Imaging CCDs; Chemical Thinning Process for Fabricating UV-Imaging CCDs; Pseudoslit Spectrometer; Waste-Heat-Driven Cooling Using Complex Compound Sorbents; Improved Refractometer for Measuring Temperatures of Drops; Semiconductor Lasers Containing Quantum Wells in Junctions; Phytoplankton-Fluorescence-Lifetime Vertical Profiler; Hexagonal Pixels and Indexing Scheme for Binary Images; Finding Minimum-Power Broadcast Trees for Wireless Networks; and Automation of Design Engineering Processes.

Source record↗
NASA NTRS2020

Search Tree Pruning for Progressive Neural Architecture Search

Our neural architecture search algorithm progressively searches a tree of neural network architectures. Child nodes are created by inserting new layers determined by a transition graph into a parent network up to a maximum depth and pruned when performance is worse than its parent. This increases efficiency but makes the algorithm greedy. Simpler networks are successfully found before more complex ones that can achieve benchmark performance similar to other top-performing networks.

Deanna Flynn↗
NASA NTRSDate not supplied

QuantifyML: How Good is My Machine Learning Model?

We present QuantifyML, which applies model counting to assess the learn ability, safety, and robustness of machine learning models. Typically, the efficacy of machine learning models is determined by computing their accuracy statistically on test datasets. However, this may be misleading, if the test data is not representative of the problem that is being studied. With QuantifyML we aim to precisely quantify the extent to which machine learning models have learned and generalized from the given data. In QuantifyML, a trained model is translated into aC program, which is fed to the CBMC model checking tool to produce a formula in Conjunctive Normal Form (CNF), which in turn is analyzed with state-of-the-art model counters to efficiently obtain precise countsw.r.t different outputs. QuantifyML enables i) evaluating the learnability of models by comparing the counts for the outputs to ground truth, ex-pressed as logical predicates (if available), ii) comparing the performance of different models that may be built with different machine learning algorithms (e.g., decision-trees vs. neural networks), and iii) quantifying the safety and robustness of trained models.

Deep Neural Networks↗
NASA NTRS2022

Hybrid data-driven and model-informed online tool wear detection in milling machines

Precision machining tool wear is responsible for low product throughput and quality. Monitoring the tool wear online is vital to prevent degradation in machining quality. However, direct real-time tool wear measurement is not practical. This paper presents residual-based anomaly detection models, combining a hybrid model comprised of a physics-based model and a data-driven model (a decision tree or a neural network) to predict signals of interest (e.g., power or forces) under nominal conditions, followed by Page’s cumulative sum test for detecting tool wear on-line using the computer numerical control machine measurements. The most informative features are ranked using dynamic programming and its approximation variants from real-time measurements and machine settings, such as the width of cut, depth of cut, feed rate and spindle speed, that serve as inputs to the predictive models. The baseline nominal model is incrementally updated with experimental data via a gradient boosted adaptation model to generate the residuals that account for discrepancies between the actual machine data under normal conditions and the baseline nominal model predictions. The hybrid model is validated against 20 Mazak milling machine experimental tests and one Haas run-to-failure experiment. The proposed anomaly detector is applied to synthetic data from simulations of the physics-based model at different operating conditions, measurement noise levels, and tool wear levels, and the methods were able to achieve an overall 92% accuracy in data with 1% noise. The anomaly detection methods based on hybrid model reduced the false alarms of either the data-driven or physical-based models alone, and are found to be capable of good online detection of tool wear.

Online anomaly detection↗
NASA NTRS2017

Very High Resolution Tree Cover Mapping for Continental United States using Deep Convolutional Neural Networks

Uncertainties in input land cover estimates contribute to a significant bias in modeled above ground biomass (AGB) and carbon estimates from satellite-derived data. The resolution of most currently used passive remote sensing products is not sufficient to capture tree canopy cover of less than ca. 10-20 percent, limiting their utility to estimate canopy cover and AGB for trees outside of forest land. In our study, we created a first of its kind Continental United States (CONUS) tree cover map at a spatial resolution of 1-m for the 2010-2012 epoch using the USDA NAIP imagery to address the present uncertainties in AGB estimates. The process involves different tasks including data acquisition ingestion to pre-processing and running a state-of-art encoder-decoder based deep convolutional neural network (CNN) algorithm for automatically generating a tree non-tree map for almost a quarter million scenes. The entire processing chain including generation of the largest open source existing aerial satellite image training database was performed at the NEX supercomputing and storage facility. We believe the resulting forest cover product will substantially contribute to filling the gaps in ongoing carbon and ecological monitoring research and help quantifying the errors and uncertainties in derived products.

High Resolution↗
NASA NTRS1992

Self-growing neural network architecture using crisp and fuzzy entropy

The paper briefly describes the self-growing neural network algorithm, CID2, which makes decision trees equivalent to hidden layers of a neural network. The algorithm generates a feedforward architecture using crisp and fuzzy entropy measures. The results of a real-life recognition problem of distinguishing defects in a glass ribbon and of a benchmark problem of differentiating two spirals are shown and discussed.

Cios, Krzysztof J.↗
NASA NTRS1992

Self-growing neural network architecture using crisp and fuzzy entropy

The paper briefly describes the self-growing neural network algorithm, CID3, which makes decision trees equivalent to hidden layers of a neural network. The algorithm generates a feedforward architecture using crisp and fuzzy entropy measures. The results for a real-life recognition problem of distinguishing defects in a glass ribbon, and for a benchmark problen of telling two spirals apart are shown and discussed.

Cios, Krzysztof J.↗
NASA NTRS1972

Computer generation of symbolic network functions - A new theory and implementation.

A new method is presented for obtaining network functions in which some, none, or all of the network elements are represented by symbolic parameters (i.e., symbolic network functions). Unlike the topological tree enumeration or signal flow graph methods generally used to derive symbolic network functions, the proposed procedure employs fast, efficient, numerical-type algorithms to determine the contribution of those network branches that are not represented by symbolic parameters. A computer program called NAPPE (for Network Analysis Program using Parameter Extractions) and incorporating all of the concepts discussed has been written. Several examples illustrating the usefulness and efficiency of NAPPE are presented.

Alderson, G. E.↗
NASA NTRS2011

Remote Asynchronous Message Service Gateway

The Remote Asynchronous Message Service (RAMS) gateway is a special-purpose AMS application node that enables exchange of AMS messages between nodes residing in different AMS "continua," notionally in different geographical locations. JPL s implementation of RAMS gateway functionality is integrated with the ION (Interplanetary Overlay Network) implementation of the DTN (Delay-Tolerant Networking) bundle protocol, and with JPL s implementation of AMS itself. RAMS protocol data units are encapsulated in ION bundles and are forwarded to the neighboring RAMS gateways identified in the source gateway s AMS management information base. Each RAMS gateway has interfaces in two communication environments: the AMS message space it serves, and the RAMS network - the grid or tree of mutually aware RAMS gateways - that enables AMS messages produced in one message space to be forwarded to other message spaces of the same venture. Each gateway opens persistent, private RAMS network communication channels to the RAMS gateways of other message spaces for the same venture, in other continua. The interconnected RAMS gateways use these communication channels to forward message petition assertions and cancellations among themselves. Each RAMS gateway subscribes locally to all subjects that are of interest in any of the linked message spaces. On receiving its copy of a message on any of these subjects, the RAMS gateway node uses the RAMS network to forward the message to every other RAMS gateway whose message space contains at least one node that has subscribed to messages on that subject. On receiving a message via the RAMS network from some other RAMS gateway, the RAMS gateway node forwards the message to all subscribers in its own message space.

Wang, Shin-Ywan↗
NASA NTRS2007

Revealing the ISO/IEC 9126-1 Clique Tree for COTS Software Evaluation

Previous research has shown that acyclic dependency models, if they exist, can be extracted from software quality standards and that these models can be used to assess software safety and product quality. In the case of commercial off-the-shelf (COTS) software, the extracted dependency model can be used in a probabilistic Bayesian network context for COTS software evaluation. Furthermore, while experts typically employ Bayesian networks to encode domain knowledge, secondary structures (clique trees) from Bayesian network graphs can be used to determine the probabilistic distribution of any software variable (attribute) using any clique that contains that variable. Secondary structures, therefore, provide insight into the fundamental nature of graphical networks. This paper will apply secondary structure calculations to reveal the clique tree of the acyclic dependency model extracted from the ISO/IEC 9126-1 software quality standard. Suggestions will be provided to describe how the clique tree may be exploited to aid efficient transformation of an evaluation model.

Morris, A. Terry↗
NASA NTRS1997

Unsupervised, Robust Estimation-based Clustering for Multispectral Images

To prepare for the challenge of handling the archiving and querying of terabyte-sized scientific spatial databases, the NASA Goddard Space Flight Center's Applied Information Sciences Branch (AISB, Code 935) developed a number of characterization algorithms that rely on supervised clustering techniques. The research reported upon here has been aimed at continuing the evolution of some of these supervised techniques, namely the neural network and decision tree-based classifiers, plus extending the approach to incorporating unsupervised clustering algorithms, such as those based on robust estimation (RE) techniques. The algorithms developed under this task should be suited for use by the Intelligent Information Fusion System (IIFS) metadata extraction modules, and as such these algorithms must be fast, robust, and anytime in nature. Finally, so that the planner/schedule module of the IlFS can oversee the use and execution of these algorithms, all information required by the planner/scheduler must be provided to the IIFS development team to ensure the timely integration of these algorithms into the overall system.

Netanyahu, Nathan S.↗
NASA NTRS2011

Improve Data Mining and Knowledge Discovery Through the Use of MatLab

Data mining is widely used to mine business, engineering, and scientific data. Data mining uses pattern based queries, searches, or other analyses of one or more electronic databases/datasets in order to discover or locate a predictive pattern or anomaly indicative of system failure, criminal or terrorist activity, etc. There are various algorithms, techniques and methods used to mine data; including neural networks, genetic algorithms, decision trees, nearest neighbor method, rule induction association analysis, slice and dice, segmentation, and clustering. These algorithms, techniques and methods used to detect patterns in a dataset, have been used in the development of numerous open source and commercially available products and technology for data mining. Data mining is best realized when latent information in a large quantity of data stored is discovered. No one technique solves all data mining problems; challenges are to select algorithms or methods appropriate to strengthen data/text mining and trending within given datasets. In recent years, throughout industry, academia and government agencies, thousands of data systems have been designed and tailored to serve specific engineering and business needs. Many of these systems use databases with relational algebra and structured query language to categorize and retrieve data. In these systems, data analyses are limited and require prior explicit knowledge of metadata and database relations; lacking exploratory data mining and discoveries of latent information. This presentation introduces MatLab(R) (MATrix LABoratory), an engineering and scientific data analyses tool to perform data mining. MatLab was originally intended to perform purely numerical calculations (a glorified calculator). Now, in addition to having hundreds of mathematical functions, it is a programming language with hundreds built in standard functions and numerous available toolboxes. MatLab's ease of data processing, visualization and its enormous availability of built in functionalities and toolboxes make it suitable to perform numerical computations and simulations as well as a data mining tool. Engineers and scientists can take advantage of the readily available functions/toolboxes to gain wider insight in their perspective data mining experiments.

Shaykhian, Gholam Ali↗
NASA NTRS2011

Improve Data Mining and Knowledge Discovery through the use of MatLab

Data mining is widely used to mine business, engineering, and scientific data. Data mining uses pattern based queries, searches, or other analyses of one or more electronic databases/datasets in order to discover or locate a predictive pattern or anomaly indicative of system failure, criminal or terrorist activity, etc. There are various algorithms, techniques and methods used to mine data; including neural networks, genetic algorithms, decision trees, nearest neighbor method, rule induction association analysis, slice and dice, segmentation, and clustering. These algorithms, techniques and methods used to detect patterns in a dataset, have been used in the development of numerous open source and commercially available products and technology for data mining. Data mining is best realized when latent information in a large quantity of data stored is discovered. No one technique solves all data mining problems; challenges are to select algorithms or methods appropriate to strengthen data/text mining and trending within given datasets. In recent years, throughout industry, academia and government agencies, thousands of data systems have been designed and tailored to serve specific engineering and business needs. Many of these systems use databases with relational algebra and structured query language to categorize and retrieve data. In these systems, data analyses are limited and require prior explicit knowledge of metadata and database relations; lacking exploratory data mining and discoveries of latent information. This presentation introduces MatLab(TradeMark)(MATrix LABoratory), an engineering and scientific data analyses tool to perform data mining. MatLab was originally intended to perform purely numerical calculations (a glorified calculator). Now, in addition to having hundreds of mathematical functions, it is a programming language with hundreds built in standard functions and numerous available toolboxes. MatLab's ease of data processing, visualization and its enormous availability of built in functionalities and toolboxes make it suitable to perform numerical computations and simulations as well as a data mining tool. Engineers and scientists can take advantage of the readily available functions/toolboxes to gain wider insight in their perspective data mining experiments.

Shaykahian, Gholan Ali↗
NASA NTRS2020

The European Russia Drought Atlas (1400-2016 CE)

We present the European Russia Drought Atlas (ERDA) that covers the East European Plain to the Ural Mountains from 1400–2016 CE. Like the Old World Drought Atlas (OWDA) for the Euro-Mediterranean region, the ERDA is a one-half degree gridded reconstruction of summer Palmer Drought Severity Indices estimated from a network of annual tree-ring chronologies. Ensemble point-by-point regression is used to generate the ERDA with the identical protocols used for developing the OWDA. Split calibration/validation tests of the ERDA indicate that it has significant skill over most of its domain and is much more skillful than the OWDA where they overlap in the western part of ERDA domain. Comparisons to historical droughts over European Russia additionally support the ERDA’s overall validity. The ERDA has been spatially smoothed and infilled using a local regression method to yield a spatially complete drought atlas back to 1400 CE. EOF analysis indicates that there are three principal modes of hydroclimatic variability in the ERDA. After Varimax rotation, these modes correlate significantly with independent climate data sets extending back to the late nineteenth century in a physically interpretable way and relate to atmospheric circulation dynamics of droughts and heatwaves over European Russia based on more recent instrumental data.

Cook, Edward R.↗
NASA NTRS2014

Hindlimb Suspension as a Model to Study Ophthalmic Complications in Microgravity Status Report: Optimization of Rat Retina Flat Mounts Staining to Study Vascular Remodeling

Preliminary data from a prior tissue‐sharing experiment has suggested that early growth response protein‐1 (Egr1), a transcription factor involved in various stress responses in the vasculature, is induced in the rat retina after 14 days of hindlimb suspension (HS) and may be evidence that mechanical stress is occurring secondary to the cephalad fluid shift. This mechanical stress could cause changes in oxygenation of the retina, and the subsequent ischemia‐ or inflammation‐driven hypoxia may lead to microvascular remodeling. This microvascular remodeling process can be studied using image analysis of retinal vessels and can be then be quantified by the VESsel GENeration Analysis (VESGEN) software, a computational tool that quantifies remodeling patterns of branching vascular trees and capillary or vasculogenic networks. Our project investigates whether rodent HS is a valid model to study the effects of simulated‐weightlessness on ocular structures and their relationship with intracranial pressure (ICP). One of the hypotheses to be tested is that HS‐induced cephalad fluid shift is accompanied by vascular engorgement that produces changes in retinal oxygenation, leading to oxidative stress, hypoxia, microvascular remodeling, and cellular degeneration. We have optimized the procedure to obtain flat mounts of rat retina, staining of the endothelial lining in vasculature and acquisition of high quality images suitable for VESGEN analysis. Briefly, eyes were fixed in 4% paraformaldehyde for 24 hours and retinas were detached and then mounted flat on microscope slides. The microvascular staining was done with endothelial cell‐specific isolectin binding, coupled to Alexa‐488 fluorophore. Image acquisition at low magnification and high resolution was performed using a new Leica SP8 confocal microscope in a tile pattern across the X,Y plane and multiple sections along the Z‐axis. This new confocal microscope has the added capability of dye separation using the Linear Unmixing method and allows us to remove the autofluorescence originating from the photoreceptor layer. In summary, we have an improved method for studying the retinal microvasculature that will provide an increase in the quality of images captured and will be applied throughout the various animal cohorts of the recentlyinitiated study that will evaluate rodent HS as a model to study ophthalmic complications in microgravity.

Theriot, Corey A.↗
NASA NTRS2016

The Mexican Drought Atlas: Tree-Ring Reconstructions of the Soil Moisture Balance During the Late Pre-Hispanic, Colonial, and Modern Eras

Mexico has suffered a long history and prehistory of severe sustained drought. Drought over Mexico is modulated by ocean-atmospheric variability in the Atlantic and Pacific, raising the possibility for long-range seasonal climate forecasting, which could help mediate the economic and social impacts of future dry spells. The instrumental record of Mexican climate is very limited before 1920, but tree-ring chronologies developed from old-growth forests in Mexico can provide an excellent proxy representation of the spatial pattern and intensity of past moisture regimes useful for the analysis of climate dynamics and climate impacts. The Mexican Drought Atlas (MXDA) has been developed from an extensive network of 252 climate sensitive tree-ring chronologies in and near Mexico. The MXDA reconstructions extend from 1400 CE-2012 and were calibrated with the instrumental summer (JJA) self-calibrating Palmer Drought Severity Index (scPDSI) on a 0.5deg latitude/longitude grid extending over land areas from 14 to 34degN and 75-120degW using Ensemble Point-by-Point Regression (EPPR) for the 1944-1984 period. The grid point reconstructions were validated for the period 1920-1943 against instrumental gridded scPDSI values based on the fewer weather station observations available during that interval. The MXDA provides a new spatial perspective on the historical impacts of moisture extremes over Mexico during the past 600-years, including the Aztec Drought of One Rabbit in 1454, the drought of El Ano de Hambre in 1785-1786, and the drought that preceded the Mexican Revolution of 1909-1910. The El Nino/Southern Oscillation (ENSO) is the most important ocean-atmospheric forcing of moisture variability detected with the MXDA. In fact, the reconstructions suggest that the strongest central equatorial Pacific sea surface temperature (SST) teleconnection to the soil moisture balance over North America may reside in northern Mexico. This ENSO signal has stronger and more time-stable correlations than computed for either the Atlantic Multidecadal Oscillation or Pacific Decadal Oscillation. The extended Multivariate ENSO Index is most highly correlated with reconstructed scPDSI over northern Mexico, where warm events favor moist conditions during the winter, spring, and early summer. This ENSO teleconnection to northern Mexico has been strong over the past 150 years, but it has been comparatively weak and non-stationary in the MXDA over central and southern Mexico where eastern tropical Pacific and Caribbean/tropical Atlantic SSTs seem to be more important. The ENSO teleconnection to northern Mexico is weaker in the available instrumental PDSI, but analyses based on the millennium climate simulations with the Community Earth System Model suggest that the moisture balance during the winter, spring, and early summer over northern Mexico may indeed be particularly sensitive to ENSO forcing. Nationwide drought is predicted to become more common with anthropogenic climate change, but the MXDA reconstructions indicate that intense "All Mexico" droughts have been rare over the past 600 years and their frequency does not appear to have increased substantially in recent decades.

El Nino↗