Search NASA⌕ Search

SEARCH · Search NASA

Results for “Classifier”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
NASA NTRS2006

An Automated Classification Technique for Detecting Defects in Battery Cells

Battery cell defect classification is primarily done manually by a human conducting a visual inspection to determine if the battery cell is acceptable for a particular use or device. Human visual inspection is a time consuming task when compared to an inspection process conducted by a machine vision system. Human inspection is also subject to human error and fatigue over time. We present a machine vision technique that can be used to automatically identify defective sections of battery cells via a morphological feature-based classifier using an adaptive two-dimensional fast Fourier transformation technique. The initial area of interest is automatically classified as either an anode or cathode cell view as well as classified as an acceptable or a defective battery cell. Each battery cell is labeled and cataloged for comparison and analysis. The result is the implementation of an automated machine vision technique that provides a highly repeatable and reproducible method of identifying and quantifying defects in battery cells.

McDowell, Mark↗
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 NTRS2011

Category Learning Research in the Interactive Online Environment Second Life

The interactive online environment Second Life allows users to create novel three-dimensional stimuli that can be manipulated in a meaningful yet controlled environment. These features suggest Second Life's utility as a powerful tool for investigating how people learn concepts for unfamiliar objects. The first of two studies was designed to establish that cognitive processes elicited in this virtual world are comparable to those tapped in conventional settings by attempting to replicate the established finding that category learning systematically influences perceived similarity . From the perspective of an avatar, participants navigated a course of unfamiliar three-dimensional stimuli and were trained to classify them into two labeled categories based on two visual features. Participants then gave similarity ratings for pairs of stimuli and their responses were compared to those of control participants who did not learn the categories. Results indicated significant compression, whereby objects classified together were judged to be more similar by learning than control participants, thus supporting the validity of using Second Life as a laboratory for studying human cognition. A second study used Second Life to test the novel hypothesis that effects of learning on perceived similarity do not depend on the presence of verbal labels for categories. We presented the same stimuli but participants classified them by selecting between two complex visual patterns designed to be extremely difficult to label. While learning was more challenging in this condition , those who did learn without labels showed a compression effect identical to that found in the first study using verbal labels. Together these studies establish that at least some forms of human learning in Second Life parallel learning in the actual world and thus open the door to future studies that will make greater use of the enriched variety of objects and interactions possible in simulated environments compared to traditional experimental situations.

Andrews, Jan↗
NASA NTRS2006

PixelLearn

PixelLearn is an integrated user-interface computer program for classifying pixels in scientific images. Heretofore, training a machine-learning algorithm to classify pixels in images has been tedious and difficult. PixelLearn provides a graphical user interface that makes it faster and more intuitive, leading to more interactive exploration of image data sets. PixelLearn also provides image-enhancement controls to make it easier to see subtle details in images. PixelLearn opens images or sets of images in a variety of common scientific file formats and enables the user to interact with several supervised or unsupervised machine-learning pixel-classifying algorithms while the user continues to browse through the images. The machinelearning algorithms in PixelLearn use advanced clustering and classification methods that enable accuracy much higher than is achievable by most other software previously available for this purpose. PixelLearn is written in portable C++ and runs natively on computers running Linux, Windows, or Mac OS X.

Mazzoni, Dominic↗
NASA NTRS2012

Refinement of a Method for Identifying Probable Archaeological Sites from Remotely Sensed Data

To facilitate locating archaeological sites before they are compromised or destroyed, we are developing approaches for generating maps of probable archaeological sites, through detecting subtle anomalies in vegetative cover, soil chemistry, and soil moisture by analyzing remotely sensed data from multiple sources. We previously reported some success in this effort with a statistical analysis of slope, radar, and Ikonos data (including tasseled cap and NDVI transforms) with Student's t-test. We report here on new developments in our work, performing an analysis of 8-band multispectral Worldview-2 data. The Worldview-2 analysis begins by computing medians and median absolute deviations for the pixels in various annuli around each site of interest on the 28 band difference ratios. We then use principle components analysis followed by linear discriminant analysis to train a classifier which assigns a posterior probability that a location is an archaeological site. We tested the procedure using leave-one-out cross validation with a second leave-one-out step to choose parameters on a 9,859x23,000 subset of the WorldView-2 data over the western portion of Ft. Irwin, CA, USA. We used 100 known non-sites and trained one classifier for lithic sites (n=33) and one classifier for habitation sites (n=16). We then analyzed convex combinations of scores from the Archaeological Predictive Model (APM) and our scores. We found that that the combined scores had a higher area under the ROC curve than either individual method, indicating that including WorldView-2 data in analysis improved the predictive power of the provided APM.

Tilton, James C.↗
NASA NTRS2014

Application of Machine Learning Algorithms to the Study of Noise Artifacts in Gravitational-Wave Data

The sensitivity of searches for astrophysical transients in data from the Laser Interferometer Gravitationalwave Observatory (LIGO) is generally limited by the presence of transient, non-Gaussian noise artifacts, which occur at a high-enough rate such that accidental coincidence across multiple detectors is non-negligible. Furthermore, non-Gaussian noise artifacts typically dominate over the background contributed from stationary noise. These "glitches" can easily be confused for transient gravitational-wave signals, and their robust identification and removal will help any search for astrophysical gravitational-waves. We apply Machine Learning Algorithms (MLAs) to the problem, using data from auxiliary channels within the LIGO detectors that monitor degrees of freedom unaffected by astrophysical signals. Terrestrial noise sources may manifest characteristic disturbances in these auxiliary channels, inducing non-trivial correlations with glitches in the gravitational-wave data. The number of auxiliary-channel parameters describing these disturbances may also be extremely large; high dimensionality is an area where MLAs are particularly well-suited. We demonstrate the feasibility and applicability of three very different MLAs: Artificial Neural Networks, Support Vector Machines, and Random Forests. These classifiers identify and remove a substantial fraction of the glitches present in two very different data sets: four weeks of LIGO's fourth science run and one week of LIGO's sixth science run. We observe that all three algorithms agree on which events are glitches to within 10% for the sixth science run data, and support this by showing that the different optimization criteria used by each classifier generate the same decision surface, based on a likelihood-ratio statistic. Furthermore, we find that all classifiers obtain similar limiting performance, suggesting that most of the useful information currently contained in the auxiliary channel parameters we extract is already being used. Future performance gains are thus likely to involve additional sources of information, rather than improvements in the MLAs themselves.

gravitational-wave data↗
NASA NTRS2013

Selection of Hyperspectral Narrowbands (HNBs) and Composition of Hyperspectral Twoband Vegetation Indices (HVIs) for Biophysical Characterization and Discrimination of Crop Types Using Field Reflectance and Hyperion-EO-1 Data

The overarching goal of this study was to establish optimal hyperspectral vegetation indices (HVIs) and hyperspectral narrowbands (HNBs) that best characterize, classify, model, and map the world's main agricultural crops. The primary objectives were: (1) crop biophysical modeling through HNBs and HVIs, (2) accuracy assessment of crop type discrimination using Wilks' Lambda through a discriminant model, and (3) meta-analysis to select optimal HNBs and HVIs for applications related to agriculture. The study was conducted using two Earth Observing One (EO-1) Hyperion scenes and other surface hyperspectral data for the eight leading worldwide crops (wheat, corn, rice, barley, soybeans, pulses, cotton, and alfalfa) that occupy approx. 70% of all cropland areas globally. This study integrated data collected from multiple study areas in various agroecosystems of Africa, the Middle East, Central Asia, and India. Data were collected for the eight crop types in six distinct growth stages. These included (a) field spectroradiometer measurements (350-2500 nm) sampled at 1-nm discrete bandwidths, and (b) field biophysical variables (e.g., biomass, leaf area index) acquired to correspond with spectroradiometer measurements. The eight crops were described and classified using approx. 20 HNBs. The accuracy of classifying these 8 crops using HNBs was around 95%, which was approx. 25% better than the multi-spectral results possible from Landsat-7's Enhanced Thematic Mapper+ or EO-1's Advanced Land Imager. Further, based on this research and meta-analysis involving over 100 papers, the study established 33 optimal HNBs and an equal number of specific two-band normalized difference HVIs to best model and study specific biophysical and biochemical quantities of major agricultural crops of the world. Redundant bands identified in this study will help overcome the Hughes Phenomenon (or "the curse of high dimensionality") in hyperspectral data for a particular application (e.g., biophysical characterization of crops). The findings of this study will make a significant contribution to future hyperspectral missions such as NASA's HyspIRI. Index Terms-Hyperion, field reflectance, imaging spectroscopy, HyspIRI, biophysical parameters, hyperspectral vegetation indices, hyperspectral narrowbands, broadbands.

Vegetation↗
NASA NTRS2011

Optimization of Adaboost Algorithm for Sonar Target Detection in a Multi-Stage ATR System

JPL has developed a multi-stage Automated Target Recognition (ATR) system to locate objects in images. First, input images are preprocessed and sent to a Grayscale Optical Correlator (GOC) filter to identify possible regions-of-interest (ROIs). Second, feature extraction operations are performed using Texton filters and Principal Component Analysis (PCA). Finally, the features are fed to a classifier, to identify ROIs that contain the targets. Previous work used the Feed-forward Back-propagation Neural Network for classification. In this project we investigate a version of Adaboost as a classifier for comparison. The version we used is known as GentleBoost. We used the boosted decision tree as the weak classifier. We have tested our ATR system against real-world sonar images using the Adaboost approach. Results indicate an improvement in performance over a single Neural Network design.

Adaboost↗
NASA NTRS2014

The Rise and Fall of the Type Ib Supernova iPTF13bvn Not a Massive Wolf-Rayet Star

Context. We investigate iPTF13bvn, a core-collapse (CC) supernova (SN) in the nearby spiral galaxy NGC 5806. This object was discovered by the intermediate Palomar Transient Factory (iPTF) very close to the estimated explosion date and was classified as a stripped-envelope CC SN, likely of Type Ib. Furthermore, a possible progenitor detection in pre-explosion Hubble Space Telescope (HST) images was reported, making this the only SN Ib with such an identification. Based on the luminosity and color of the progenitor candidate, as well as on early-time spectra and photometry of the SN, it was argued that the progenitor candidate is consistent with a single, massive Wolf-Rayet (WR) star. Aims. We aim to confirm the progenitor detection, to robustly classify the SN using additional spectroscopy, and to investigate if our follow-up photometric and spectroscopic data on iPTF13bvn are consistent with a single-star WR progenitor scenario. Methods. We present a large set of observational data, consisting of multi-band light curves (UBVRI, g′r′i′z′) and optical spectra. We perform standard spectral line analysis to track the evolution of the SN ejecta. We also construct a bolometric light curve and perform hydrodynamical calculations to model this light curve to constrain the synthesized radioactive nickel mass and the total ejecta mass of the SN. Late-time photometry is analyzed to constrain the amount of oxygen. Furthermore, image registration of pre- and post-explosion HST images is performed. Results. Our HST astrometry confirms the location of the progenitor candidate of iPTF13bvn, and follow-up spectra securely classify this as a SN Ib. We use our hydrodynamical model to fit the observed bolometric light curve, estimating the total ejecta mass to be 1.9 solar mass and the radioactive nickel mass to be 0.05 solar mass. The model fit requires the nickel synthesized in the explosion to be highly mixed out in the ejecta. We also find that the late-time nebular r′-band luminosity is not consistent with predictions based on the expected oxygen nucleosynthesis in very massive stars. Conclusions. We find that our bolometric light curve of iPTF13bvn is not consistent with the previously proposed single massive WR-star progenitor scenario. The total ejecta mass and, in particular, the late-time oxygen emission are both significantly lower than what would be expected from a single WR progenitor with a main-sequence mass of at least 30 solar mass.

massive↗
NASA NTRS2016

Using Multimodal Input for Autonomous Decision Making for Unmanned Systems

Autonomous decision making in the presence of uncertainly is a deeply studied problem space particularly in the area of autonomous systems operations for land, air, sea, and space vehicles. Various techniques ranging from single algorithm solutions to complex ensemble classifier systems have been utilized in a research context in solving mission critical flight decisions. Realized systems on actual autonomous hardware, however, is a difficult systems integration problem, constituting a majority of applied robotics development timelines. The ability to reliably and repeatedly classify objects during a vehicles mission execution is vital for the vehicle to mitigate both static and dynamic environmental concerns such that the mission may be completed successfully and have the vehicle operate and return safely. In this paper, the Autonomy Incubator proposes and discusses an ensemble learning and recognition system planned for our autonomous framework, AEON, in selected domains, which fuse decision criteria, using prior experience on both the individual classifier layer and the ensemble layer to mitigate environmental uncertainty during operation.

Neilan, James H.↗
NASA NTRS2016

Psychophysiological Sensing and State Classification for Attention Management in Commercial Aviation

Attention-related human performance limiting states (AHPLS) can cause pilots to lose airplane state awareness (ASA), and their detection is important to improving commercial aviation safety. The Commercial Aviation Safety Team found that the majority of recent international commercial aviation accidents attributable to loss of control inflight involved flight crew loss of airplane state awareness, and that distraction of various forms was involved in all of them. Research on AHPLS, including 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 has been implemented to simultaneously measure their physiological markers during high fidelity flight simulation human subject studies. Pilot participants were asked to perform benchmark tasks and experimental flight scenarios designed to induce AHPLS. Pattern classification was employed to distinguish the AHPLS induced by the benchmark tasks. Unimodal classification using pre-processed electroencephalography (EEG) signals as input features to extreme gradient boosting, random forest and deep neural network multiclass classifiers was implemented. Multi-modal classification using galvanic skin response (GSR) in addition to the same EEG signals and using the same types of classifiers produced increased accuracy with respect to the unimodal case (90 percent vs. 86 percent), although only via the deep neural network classifier. These initial results are a first step toward 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.↗
NASA NTRS2016

The IPAC Image Subtraction and Discovery Pipeline for the Intermediate Palomar Transient Factory

We describe the near real-time transient-source discovery engine for the intermediate Palomar Transient Factory (iPTF), currently in operations at the Infrared Processing and Analysis Center (IPAC), Caltech. We coin this system the IPAC/iPTF Discovery Engine (or IDE). We review the algorithms used for PSF-matching, image subtraction, detection, photometry, and machine-learned (ML) vetting of extracted transient candidates. We also review the performance of our ML classifier. For a limiting signal-to-noise ratio of 4 in relatively unconfused regions, bogus candidates from processing artifacts and imperfect image subtractions outnumber real transients by approximately equal to 10:1. This can be considerably higher for image data with inaccurate astrometric and/or PSF-matching solutions. Despite this occasionally high contamination rate, the ML classifier is able to identify real transients with an efficiency (or completeness) of approximately equal to 97% for a maximum tolerable false-positive rate of 1% when classifying raw candidates. All subtraction-image metrics, source features, ML probability-based real-bogus scores, contextual metadata from other surveys, and possible associations with known Solar System objects are stored in a relational database for retrieval by the various science working groups. We review our efforts in mitigating false-positives and our experience in optimizing the overall system in response to the multitude of science projects underway with iPTF.

methods: analytical – methods: data analysis –↗
NASA NTRS2017

Scientific Yield of Meteorites Recovered from the Dominion Range, Transantarctic Mountains

The US Antarctic Meteorite Program has visited the Dominion Range in the Transantarctic Mountains during several different seasons, including the 1985, 2003, 2008, 2010, and 2014 seasons. Total recovered meteorites from this region is over 2000. The 1985 (11 samples), 2003 (141 samples), 2008 (521) and 2010 (901 samples) seasons have been fully classified, and the 2014 samples (562) are in the process of being classified and characterized. Given that close to 1500 samples have been classified so far, it seems like a good opportunity to summarize the state of the collection. Here we describe the significant samples documented from this area, as well as a large meteorite shower that dominates the statistics of the region.

Righter, K.↗
NASA NTRS2017

40 Years of Collecting Martian Meteorites

This year marks the 40th anniversary of the first Martian meteorite found in Antarctica by ANSMET, ALH 77005. Since then, an additional 14 Martian meteorites have been found by the ANSMET team making for a total of 15 Martian meteorites in the Antarctic collection at Johnson Space Center. Of the 15 meteorites, some have been paired so the 15 meteorites actually represent a total of approximately 9 separate meteorites. The first Martian meteorite found by ANSMET was ALH 77005 (482.500 g), a lherzolitic shergottite. When collected, this meteorite was split as a part of the joint expedition with the National Institute of Polar Research (NIPR) Japan. Originally classified as an "achondrite-unique", it was re-classified as a Martian lherzolitic shergottites in 1982 [1]. This meteorite has been allocated to ~125 scientists for research and there are 181.964 g remaining at Johnson Space Center (JSC). Two years later, one of the most significant Martian meteorites of the collection at JSC was found at Elephant Moraine, EET 79001 (7942.000 g), a shergottite. This meteorite is the largest in the Martian collection at JSC and was the largest stony meteorite sample collected during the 1979 season. In addition to its size, this meteorite is of particular interest because it contains a linear contact separating two different igneous lithologies, basaltic and olivine-phyric. EET 79001 has glass inclusions that contain chemical compositions that are proportionally identical to the Martian atmosphere, as measured by the Viking spacecraft [2]. This discovery helped scientists to identify where the "SNC" meteorite suite had originated, and that we actually possessed Martian samples. This meteorite has been allocated to ~195 scientists for research and there are 5304.770 g of sample is available. Five years later, ANSMET found ALH 84001 (1930.900 g), the only Martian orthopyroxenite. This meteorite was initially classified as a diogenite but was reclassified as being a Martian meteorite in 1993 [3,4]. ALH 84001 is known as the "Life on Mars" meteorite, sparked debate about whether it contained evidence of Martian life [5] and significantly influenced the field of astrobiol-ogy. This sample has been allocated to 173 scientists for research and has 1426.694 g remaining at JSC. In 1988, another lherzolitic shergottite was found, LEW 88516, (13.203 g). This meteorite wasn't recognized in the field as an achondrite until it was broken during processing 2 years later. LEW 88516 has been allocated to 43 scientists for research and 5.351 g of this meteorite remains at JSC. Six years later a basaltic shergottite was found in the Queen Alexandra Range, QUE 94201 (12.020 g). This meteorite was believed to be of terrestrial origin until maskelynite was seen in a thin section. QUE 94201 has been allocated to 57 scientists for research and there are 3.629 g of this meteorite left at JSC. In 2003, the NASA Mars Exploration Program joined the ANSMET team with the hopes of finding another Martian mete-orite. During this expedition, MIL 03346 (715.200 g) was found. This meteorite is a nakhlite. MIL 03346 has been allocated to 98 scientists for research and there are 579.046 g of this sample remaining at JSC. Six years later, 3 more meteorites that have been paired with MIL 03346 were found, MIL 090030 (452.630 g), 090032 (532.190 g ) and 090136 (170.980 g). MIL 090030 has been allocated to 21 scientists for research and has 434.420 g remaining at JSC, MIL 090032 has been allocated to 21 scientists for re-search and has 508.710 g remaining at JSC and MIL 090136 has been allocated to 14 scientists for research and has 156.790 g remaining at JSC. During the 2004 expedition, 2 identical meteorites where found together on the ice, RBT 04261 (78.763 g) and RBT 04262 (204.600 g). These paired meteorites are olivine-phyric shergottites. RBT 04261 has been allocated to 33 scientists for research and has 32.335 g remaining at JSC. RBT 04262 has been allocated to 46 scientists for research and has 171.886 g remaining. In 2006, another olivine-phyric shergottite was found, LAR 06319 (78.572 g). This meteorite has 61.414 g remaining at JSC and has been allocated to 39 scientists for research. During the 2012 season, 3 more olivine-phyric shergottites were found at Larkman Nunatak, LAR 12011 (701.170 g), LAR 12095 (133.132 g) and LAR 12240 (57.596 g). LAR 12011 is paired with LAR 06319 and LAR 12095 and LAR 12240 are paired with each other. LAR 12011 has been allocated to 43 scientists for research and there are 685.778 g of LAR 12011 remaining at JSC. LAR 12095 has been allocated to 18 scientists for research and has 119.744 g remaining at JSC. LAR 12240 has been allocated to 10 scientists for research and has 52.231 g remaining at JSC. Martian meteorites are the only samples available from Mars because no mission has returned samples from there to date. All Martian meteorites are crustal rocks with most of them being crystallized magmas, so they are an important source for under-standing Martian geological history and volcanism. The ANSMET program has greatly contributed to the scientific community by collecting these meteorites

Funk, R. C.↗
NASA NTRS2017

Kepler Planet Detection Metrics: Robovetter Completeness and Effectiveness for Data Release 25

In general, the Kepler pipeline identifies a list of Threshold Crossing Events (TCEs), which are periodic flux decrements meeting certain criteria (Jenkins, 2017). These TCEs are reviewed and those that appear consistent with astrophysically transiting or eclipsing systems are classified as Kepler Objects of Interest (KOIs). Further review is given to KOIs, which are then dispositioned as Planet Candidates (PCs) or False Positive (FPs). FPs are further denoted by four major flags that indicate if the signal is Not Transit-Like (NTL), due to a Stellar Eclipse (SS; previously referred to as Significant Secondary), and/or due to contamination from a source other than the target as evidenced by a Centroid Offset (CO) oran Ephemeris Match (EM) with another object. This entire TCE review process is known as dispositioning or vetting.In the first five Kepler mission planet candidate catalogs (Borucki et al., 2011a,b; Batalha et al., 2013; Burke et al., 2014; Rowe et al., 2015), TCEs were manually examined on an individual basis and dispositioned using various plots and quantitative diagnostic tests (see e.g., Coughlin, 2017). In the sixth catalog, Mullally et al. (2015a) employed partial automation via simple parameter cuts to automatically disposition a large fraction of TCEs as not transit-like. Mullally et al. (2015a) also used an automated technique known as the centroid Robovetter (Mullally, 2017) to automatically identify some FP KOIs due to centroid offsets - a telltale signature of light contamination from another target. The remaining targets were manually dispositioned. In the seventh catalog, Coughlin et al. (2016) automated theentire dispositioning process using what is collectively known simply as the Robovetter.In the eighth and final mission catalog, Thompson et al. (2017) use a revised Robovetter to automate the dispositioning of all TCEs with an emphasis on creating a catalog suitable for accurately determining planet occurrence rates. In order to calculate accurate occurrence rates, the completeness and effectiveness of the Robovetter must be characterized. We define these terms as applied to the Robovetter, following Thompson et al. (2017), as:1. Completeness: The fraction of transiting planets detected by the pipeline that are classified as planet candidates by the Robovetter.2. Effectiveness: The fraction of false positives detected by the pipeline that are classified as false positives by the Robovetter.The remainder of this document describes products that can be used to quantitatively assess Robovetter completeness and effectiveness for an arbitrary set of Kepler stars.

Robovetter↗
NASA NTRS2017

Ask-the-expert: Active Learning Based Knowledge Discovery Using the Expert

Often the manual review of large data sets, either for purposes of labeling unlabeled instances or for classifying meaningful results from uninteresting (but statistically significant) ones is extremely resource intensive, especially in terms of subject matter expert (SME) time. Use of active learning has been shown to diminish this review time significantly. However, since active learning is an iterative process of learning a classifier based on a small number of SME-provided labels at each iteration, the lack of an enabling tool can hinder the process of adoption of these technologies in real-life, in spite of their labor-saving potential. In this demo we present ASK-the-Expert, an interactive tool that allows SMEs to review instances from a data set and provide labels within a single framework. ASK-the-Expert is powered by an active learning algorithm for training a classifier in the backend. We demonstrate this system in the context of an aviation safety application, but the tool can be adopted to work as a simple review and labeling tool as well, without the use of active learning.

software↗
NASA NTRS2017

Ask-the-Expert: Active Learning Based Knowledge Discovery Using the Expert

Often the manual review of large data sets, either for purposes of labeling unlabeled instances or for classifying meaningful results from uninteresting (but statistically significant) ones is extremely resource intensive, especially in terms of subject matter expert (SME) time. Use of active learning has been shown to diminish this review time significantly. However, since active learning is an iterative process of learning a classifier based on a small number of SME-provided labels at each iteration, the lack of an enabling tool can hinder the process of adoption of these technologies in real-life, in spite of their labor-saving potential. In this demo we present ASK-the-Expert, an interactive tool that allows SMEs to review instances from a data set and provide labels within a single framework. ASK-the-Expert is powered by an active learning algorithm for training a classifier in the back end. We demonstrate this system in the context of an aviation safety application, but the tool can be adopted to work as a simple review and labeling tool as well, without the use of active learning.

GUI↗
NASA NTRS2018

Update on Automated Classification of Interplanetary Dust Particles

Every year, the Earth accretes about 40,000 tons of extraterrestrial material less than 1 mm in size on its surface. These dust particles originate from active comets, from impacts between asteroids and may also be coming from interstellar space for the very small particles. Since 1981, NASA Jonhson Space Center (JSC) has been systematically collecting the dust from Earth's strastosphere by airborne collectors and gathered them into "Cosmic Dust Catalogs". In those catalogs, a preliminary analysis of the dust particles based on SEM images, some geological characteristics and X-ray energy-dispersive spectrometry (EDS) composition is compiled. Based on those properties, the IDPs are classified into four main groups: C (Cosmic), TCN (Natural Terrestrial Contaminant), TCA (Artificial Terrestrial Contaminant) and AOS (Aluminium Oxide Sphere). Nevertheless, 20% of those particles remain ambiguously classified. Lasue et al. presented a methodology to help automatically classify the particles published in the catalog 15 based on their EDS spectra and nonlinear multivariate projections (as shown in Fig. 1). This work allowed to relabel 155 particles out of the 467 particles in catalog 15 and reclassify some contaminants as potential cosmic dusts. Further analyses of three such particles indicated their probable cosmic origin. The current work aims to bring complementary information to the automatic classification of IDPs to improve identification criteria.

Maroger, I.↗