Search NASA⌕ Search

Engineering topics

Mazzoni, Dominic

Publications and source records attributed to Mazzoni, Dominic.

At least 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2010

JMISR INteractive eXplorer

MISR (Multi-angle Imaging SpectroRadiometer) INteractive eXplorer (MINX) is an interactive visualization program that allows a user to digitize smoke, dust, or volcanic plumes in MISR multiangle images, and automatically retrieve height and wind profiles associated with those plumes. This innovation can perform 9-camera animations of MISR level-1 radiance images to study the 3D relationships of clouds and plumes. MINX also enables archiving MISR aerosol properties and Moderate Resolution Imaging Spectroradiometer (MODIS) fire radiative power along with the heights and winds. It can correct geometric misregistration between cameras by correlating off-nadir camera scenes with corresponding nadir scenes and then warping the images to minimize the misregistration offsets. Plots of BRF (bidirectional reflectance factor) vs. camera angle for points clicked in an image can be displayed. Users get rapid access to map views of MISR path and orbit locations and overflight dates, and past or future orbits can be identified that pass over a specified location at a specified time. Single-camera, level-1 radiance data at 1,100- or 275- meter resolution can be quickly displayed in color using a browse option. This software determines the heights and motion vectors of features above the terrain with greater precision and coverage than previous methods, based on an algorithm that takes wind direction into consideration. Human interpreters can precisely identify plumes and their extent, and wind direction. Overposting of MODIS thermal anomaly data aids in the identification of smoke plumes. The software has been used to preserve graphical and textural versions of the digitized data in a Web-based database.

Nelson, David L.↗
NASA NTRS2009

Active Learning with Irrelevant Examples

An improved active learning method has been devised for training data classifiers. One example of a data classifier is the algorithm used by the United States Postal Service since the 1960s to recognize scans of handwritten digits for processing zip codes. Active learning algorithms enable rapid training with minimal investment of time on the part of human experts to provide training examples consisting of correctly classified (labeled) input data. They function by identifying which examples would be most profitable for a human expert to label. The goal is to maximize classifier accuracy while minimizing the number of examples the expert must label. Although there are several well-established methods for active learning, they may not operate well when irrelevant examples are present in the data set. That is, they may select an item for labeling that the expert simply cannot assign to any of the valid classes. In the context of classifying handwritten digits, the irrelevant items may include stray marks, smudges, and mis-scans. Querying the expert about these items results in wasted time or erroneous labels, if the expert is forced to assign the item to one of the valid classes. In contrast, the new algorithm provides a specific mechanism for avoiding querying the irrelevant items. This algorithm has two components: an active learner (which could be a conventional active learning algorithm) and a relevance classifier. The combination of these components yields a method, denoted Relevance Bias, that enables the active learner to avoid querying irrelevant data so as to increase its learning rate and efficiency when irrelevant items are present. The algorithm collects irrelevant data in a set of rejected examples, then trains the relevance classifier to distinguish between labeled (relevant) training examples and the rejected ones. The active learner combines its ranking of the items with the probability that they are relevant to yield a final decision about which item to present to the expert for labeling. Experiments on several data sets have demonstrated that the Relevance Bias approach significantly decreases the number of irrelevant items queried and also accelerates learning speed.

Wagstaff, Kiri↗
NASA NTRS2008

MISR Instrument Data Visualization

The MISR Interactive eXplorer (MINX) software functions both as a general-purpose tool to visualize Multiangle Imaging SpectroRadiometer (MISR) instrument data, and as a specialized tool to analyze properties of smoke, dust, and volcanic plumes. It includes high-level options to create map views of MISR orbit locations; scrollable, single-camera RGB (red-greenblue) images of MISR level 1B2 (L1B2) radiance data; and animations of the nine MISR camera images that provide a 3D perspective of the scenes that MISR has acquired. NASA Tech Briefs, September 2008 55 The plume height capability provides an accurate estimate of the injection height of plumes that is needed by air quality and climate modelers. MISR provides global high-quality stereo height information, and this program uses that information to perform detailed height retrievals of aerosol plumes. Users can interactively digitize smoke, dust, or volcanic plumes and automatically retrieve heights and winds, and can also archive MISR albedos and aerosol properties, as well as fire power and brightness temperatures associated with smoke plumes derived from Moderate Resolution Imaging Spectroradiometer (MODIS) data. Some of the specialized options in MINX enable the user to do other tasks. Users can display plots of top-of-atmosphere bidirectional reflectance factors (BRFs) versus camera-angle for selected pixels. Images and animations can be saved to disk in various formats. Also, users can apply a geometric registration correction to warp camera images when the standard processing correction is inadequate. It is possible to difference the images of two MISR orbits that share a path (identical ground track), as well as to construct pseudo-color images by assigning different combinations of MISR channels (angle or spectral band) to the RGB display channels. This software is an interactive application written in IDL and compiled into an IDL Virtual Machine (VM) ".sav" file.

Nelson, David↗
NASA NTRS2007

Automated Knowledge Discovery From Simulators

A computational method, SimLearn, has been devised to facilitate efficient knowledge discovery from simulators. Simulators are complex computer programs used in science and engineering to model diverse phenomena such as fluid flow, gravitational interactions, coupled mechanical systems, and nuclear, chemical, and biological processes. SimLearn uses active-learning techniques to efficiently address the "landscape characterization problem." In particular, SimLearn tries to determine which regions in "input space" lead to a given output from the simulator, where "input space" refers to an abstraction of all the variables going into the simulator, e.g., initial conditions, parameters, and interaction equations. Landscape characterization can be viewed as an attempt to invert the forward mapping of the simulator and recover the inputs that produce a particular output. Given that a single simulation run can take days or weeks to complete even on a large computing cluster, SimLearn attempts to reduce costs by reducing the number of simulations needed to effect discoveries. Unlike conventional data-mining methods that are applied to static predefined datasets, SimLearn involves an iterative process in which a most informative dataset is constructed dynamically by using the simulator as an oracle. On each iteration, the algorithm models the knowledge it has gained through previous simulation trials and then chooses which simulation trials to run next. Running these trials through the simulator produces new data in the form of input-output pairs. The overall process is embodied in an algorithm that combines support vector machines (SVMs) with active learning. SVMs use learning from examples (the examples are the input-output pairs generated by running the simulator) and a principle called maximum margin to derive predictors that generalize well to new inputs. In SimLearn, the SVM plays the role of modeling the knowledge that has been gained through previous simulation trials. Active learning is used to determine which new input points would be most informative if their output were known. The selected input points are run through the simulator to generate new information that can be used to refine the SVM. The process is then repeated. SimLearn carefully balances exploration (semi-randomly searching around the input space) versus exploitation (using the current state of knowledge to conduct a tightly focused search). During each iteration, SimLearn uses not one, but an ensemble of SVMs. Each SVM in the ensemble is characterized by different hyper-parameters that control various aspects of the learned predictor - for example, whether the predictor is constrained to be very smooth (nearby points in input space lead to similar output predictions) or whether the predictor is allowed to be "bumpy." The various SVMs will have different preferences about which input points they would like to run through the simulator next. SimLearn includes a formal mechanism for balancing the ensemble SVM preferences so that a single choice can be made for the next set of trials.

Burl, Michael↗
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 NTRS2006

Active Learning with Irrelevant Examples

Active learning algorithms attempt to accelerate the learning process by requesting labels for the most informative items first. In real-world problems, however, there may exist unlabeled items that are irrelevant to the user's classification goals. Queries about these points slow down learning because they provide no information about the problem of interest. We have observed that when irrelevant items are present, active learning can perform worse than random selection, requiring more time (queries) to achieve the same level of accuracy. Therefore, we propose a novel approach, Relevance Bias, in which the active learner combines its default selection heuristic with the output of a simultaneously trained relevance classifier to favor items that are likely to be both informative and relevant. In our experiments on a real-world problem and two benchmark datasets, the Relevance Bias approach significantly improved the learning rate of three different active learning approaches.

machine learning↗
NASA NTRS2006

Onboard Classifiers for Science Event Detection on a Remote Sensing Spacecraft

Typically, data collected by a spacecraft is downlinked to Earth and pre-processed before any analysis is performed. We have developed classifiers that can be used onboard a spacecraft to identify high priority data for downlink to Earth, providing a method for maximizing the use of a potentially bandwidth limited downlink channel. Onboard analysis can also enable rapid reaction to dynamic events, such as flooding, volcanic eruptions or sea ice break-up. Four classifiers were developed to identify cryosphere events using hyperspectral images. These classifiers include a manually constructed classifier, a Support Vector Machine (SVM), a Decision Tree and a classifier derived by searching over combinations of thresholded band ratios. Each of the classifiers was designed to run in the computationally constrained operating environment of the spacecraft. A set of scenes was hand-labeled to provide training and testing data. Performance results on the test data indicate that the SVM and manual classifiers outperformed the Decision Tree and band-ratio classifiers with the SVM yielding slightly better classifications than the manual classifier.

classification↗
NASA NTRS2006

Multiclass Reduced-Set Support Vector Machines

There are well-established methods for reducing the number of support vectors in a trained binary support vector machine, often with minimal impact on accuracy. We show how reduced-set methods can be applied to multiclass SVMs made up of several binary SVMs, with significantly better results than reducing each binary SVM independently. Our approach is based on Burges' approach that constructs each reduced-set vector as the pre-image of a vector in kernel space, but we extend this by recomputing the SVM weights and bias optimally using the original SVM objective function. This leads to greater accuracy for a binary reduced-set SVM, and also allows vectors to be 'shared' between multiple binary SVMs for greater multiclass accuracy with fewer reduced-set vectors. We also propose computing pre-images using differential evolution, which we have found to be more robust than gradient descent alone. We show experimental results on a variety of problems and find that this new approach is consistently better than previous multiclass reduced-set methods, sometimes with a dramatic difference.

reduced set methods↗
NASA NTRS2006

Recent HARVIST Results: Classifying Crops from Remote Sensing Data

In this paper, we report on recent results from the Heterogeneous Agricultural Research Via Interactive, Scalable Technology (HARVIST) project. HARVIST seeks to provide the tools and scalability required to enable practicioners to analyze large, diverse data sets that may come from different data sources. We have focused on agricultural applications, and our current results demonstrate the ability of the system to train a crop type classifier that operates on orbital remote sensing images. We find that this classifier can label crops with an accuracy of 82%, comparable to other published results.

support vector machines↗
NASA NTRS2005

Combining MISR and MODIS data to automatically catalogue smoke plumes in North America

We are in the early stages of work on EPA task to investigate the effects of fires on air quality in North America, led by Jennifer Logan of Harvard University. JPL's contribution to this study is to find thousands of smoke plumes in satellite images of North America, and derive statistics about their geographic distribution, extent, orientation, and injection height.

smoke plume↗
NASA NTRS2005

The application of support vector machines to analysis of global satellite data sets from MlSR

The Multi-angle Imaging Spectro Radiometer (MISR) is one of a suite of five instruments onboard NASA's Terra EOS satellite, launched in December 1999. Typical satellite imagers view the earth from a single direction, but MISR's cameras image the earth simultaneously from nine different directions in four spectral bands. In this way, MISR provides unique multiangle information about solar radiation scattered from clouds, aerosols and other terrestrial surfaces. One of the primary goals of the MISR mission is to improve our understanding of how clouds and aerosols affect the earth's global energy balance.

support vector machines↗
NASA NTRS2004

Fast Query-Optimized Kernel-Machine Classification

A recently developed algorithm performs kernel-machine classification via incremental approximate nearest support vectors. The algorithm implements support-vector machines (SVMs) at speeds 10 to 100 times those attainable by use of conventional SVM algorithms. The algorithm offers potential benefits for classification of images, recognition of speech, recognition of handwriting, and diverse other applications in which there are requirements to discern patterns in large sets of data. SVMs constitute a subset of kernel machines (KMs), which have become popular as models for machine learning and, more specifically, for automated classification of input data on the basis of labeled training data. While similar in many ways to k-nearest-neighbors (k-NN) models and artificial neural networks (ANNs), SVMs tend to be more accurate. Using representations that scale only linearly in the numbers of training examples, while exploring nonlinear (kernelized) feature spaces that are exponentially larger than the original input dimensionality, KMs elegantly and practically overcome the classic curse of dimensionality. However, the price that one must pay for the power of KMs is that query-time complexity scales linearly with the number of training examples, making KMs often orders of magnitude more computationally expensive than are ANNs, decision trees, and other popular machine learning alternatives. The present algorithm treats an SVM classifier as a special form of a k-NN. The algorithm is based partly on an empirical observation that one can often achieve the same classification as that of an exact KM by using only small fraction of the nearest support vectors (SVs) of a query. The exact KM output is a weighted sum over the kernel values between the query and the SVs. In this algorithm, the KM output is approximated with a k-NN classifier, the output of which is a weighted sum only over the kernel values involving k selected SVs. Before query time, there are gathered statistics about how misleading the output of the k-NN model can be, relative to the outputs of the exact KM for a representative set of examples, for each possible k from 1 to the total number of SVs. From these statistics, there are derived upper and lower thresholds for each step k. These thresholds identify output levels for which the particular variant of the k-NN model already leans so strongly positively or negatively that a reversal in sign is unlikely, given the weaker SV neighbors still remaining. At query time, the partial output of each query is incrementally updated, stopping as soon as it exceeds the predetermined statistical thresholds of the current step. For an easy query, stopping can occur as early as step k = 1. For more difficult queries, stopping might not occur until nearly all SVs are touched. A key empirical observation is that this approach can tolerate very approximate nearest-neighbor orderings. In experiments, SVs and queries were projected to a subspace comprising the top few principal- component dimensions and neighbor orderings were computed in that subspace. This approach ensured that the overhead of the nearest-neighbor computations was insignificant, relative to that of the exact KM computation.

Mazzoni, Dominic↗
NASA NTRS2004

Active learning in the presence of unlabelable examples

We propose a new active learning framework where the expert labeler is allowed to decline to label any example. This may be necessary because the true label is unknown or because the example belongs to a class that is not part of the real training problem. We show that within this framework, popular active learning algorithms (such as Simple) may perform worse than random selection because they make so many queries to the unlabelable class. We present a method by which any active learning algorithm can be modified to avoid unlabelable examples by training a second classifier to distinguish between the labelable and unlabelable classes. We also demonstrate the effectiveness of the method on two benchmark data sets and a real-world problem.

active learning↗