Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data representations”

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 739 records · Page 41

Precession electron diffraction for SiC grain boundary characterization in unirradiated TRISO fuel

Precession electron diffraction (PED), a transmission electron microscopy-based technique, has been evaluated for the suitability for evaluating grain boundary character in the SiC layer of tristructural isotropic (TRISO) fuel. Although the ultimate goal is to determine the grain boundary characteristics of fission product containing grain boundaries of neutron irradiated SiC, our work reports the effect of transmission electron microscope (TEM) lamella thickness on quality of data and establishes a baseline comparison on grain boundary characteristics determined previously using a conventional EBSD scanning electron microscope (SEM) based technique. In general, it was determined that the lamella thickness produced using the standard FIB fabrication process, is sufficient to provide reliable PED measurements with thicker lamellae (~120 nm) produce higher quality orientation data. Analysis of grain boundary character from the TEM-based PED data showed a much lower fraction of low angle grain boundaries compared to SEM-based EBSD data from the SiC layer of the same TRISO-coated particle as well as a SiC layer deposited at a slightly lower temperature. The fractions of high angle and CSL-related grain boundaries determined by PED are similar to those found using SEM-based EBSD. Since the grain size of the SiC layer of TRSIO fuel can be as small as 250 nm [12], depending on the fabrication parameters, and grain boundary fission product precipitates can be nano-sized, the TEM-based PED orientation data collection method is preferred to determine an accurate representation of the relative fractions of low angle, high angle and CSL-related grain boundaries. It was concluded that although the resolution of the PED data is better by more than an order of magnitude, data acquisition times may be significantly longer or the number of areas analyzed significantly larger than the SEM-based method to obtain a statistically relevant distribution. Also, grain size could be accurately determined but significantly larger analysis areas than those used in this study would be required.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Making maps of cosmic microwave background polarization for B-mode studies: the POLARBEAR example

Analysis of cosmic microwave background (CMB) datasets typically requires some filtering of the raw time-ordered data. For instance, in the context of ground-based observations, filtering is frequently used to minimize the impact of low frequency noise, atmospheric contributions and/or scan synchronous signals on the resulting maps. In this paper, we have explicitly constructed a general filtering operator, which can unambiguously remove any set of unwanted modes in the data, and then amend the map-making procedure in order to incorporate and correct for it. We show that such an approach is mathematically equivalent to the solution of a problem in which the sky signal and unwanted modes are estimated simultaneously and the latter are marginalized over. We investigated the conditions under which this amended map-making procedure can render an unbiased estimate of the sky signal in realistic circumstances. We then discuss the potential implications of these observations on the choice of map-making and power spectrum estimation approaches in the context of B-mode polarization studies. Specifically, we have studied the effects of time-domain filtering on the noise correlation structure in the map domain, as well as impact it may haveon the performance of the popular pseudo-spectrum estimators. We conclude that although maps produced by the proposed estimators arguably provide the most faithful representation of the sky possible given the data, they may not straightforwardly lead to the best constraints on the power spectra of the underlying sky signal and special care may need to be taken to ensure this is the case. By contrast, simplified map-makers which do not explicitly correct for time-domain filtering, but leave it to subsequent steps in the data analysis, may perform equally well and be easier and faster to implement. We focused on polarization-sensitive measurements targeting the B-mode component of the CMB signal and apply the proposed methods to realistic simulations based on characteristics of an actual CMB polarization experiment, POLARBEAR. Finally, our analysis and conclusions are however more generally applicable.

79 ASTRONOMY AND ASTROPHYSICS↗

Cryo-STEM Tomography with Inpainting

Traditionally, microscopists have worked with the Nyquist-Shannon theory of sampling, which states that to be able to reconstruct the image fully it needs to be sampled at a rate of at least twice the highest spatial frequency in the image. This sampling rate assumes that the image is sampled at regular intervals and that every pixel contains information that is crucial for the image (it even assumes that noise is important). Images in general, and especially low dose S/TEM images, contain significantly less information than can be encoded by a grid of pixels (which is why image compression works). Mathematically speaking, the image data has a low dimensional or sparse representation. Through the application of compressive sensing methods [1,2,3] this representation can be found using pre-designed measurements that are usually random for implementation simplicity. These measurements and the compressive sensing reconstruction algorithms have the added benefit of reducing noise. This reconstruction approach can be extended into higher dimensions, whereby the random sampling in each 2-D image can be extended into: a sequence of tomographic projections (i.e. tilt images); a sequence of video frames (i.e. incorporating temporal resolution and dynamics); spectral resolution (i.e. energy filtering an image to see the distribution of elements); and ptychography (i.e. sampling a full diffraction image at each location in a 2-D grid across the sample). This approach has been employed experimentally for materials science samples requiring low-dose imaging [2], and can be readily applied to biological samples. Figure 1 shows the resolution possible in a complex biological system, mouse pancreatic islet beta cells [4], when tomogram slices are reconstructed using subsampling. Reducing the number of pixels (1/6 pix and 1/3*1/3) shows minimal degradation compared to the reconstructions using all pixels (all data and 1/3 tilt). Although subsampling 1/6 of the tilts (1/6 of overall dose) degrades the reconstruction to the point that the cellular structures cannot be identified. Using 1/3 of both the pixels and the tilts provides a high quality image at 1/9 the overall dose even for this most basic and rapid demonstration of the CS methods. Figure 2 demonstrates the theoretical tomogram reconstruction quality (vertical axis) as undersampling (horizontal axis) is increased; we examined subsampling pixels and tilt-angles individually and a combined approach in which both pixels and tilts are sub-sampled. Note that subsampling pixels maintains high quality reconstructions (solid lines). Using the inpainting algorithm to obtain tomograms can automatically reduce the dose applied to the system by an order of magnitude. Perhaps the best way to understand the impact is to consider that by using inpainting (and with minimal hardware changes), a sample that can normally withstand a dose of ~10 e/Å2 can potentially be imaged with an “equivalent quality” to a dose level of 103 e/Å2. To put this in perspective, this is approaching the dose level used for the most advanced images, in terms of spatial resolution, for inorganic systems. While there are issues for biological specimens beyond dose (structural complexity being the most important one), this sampling approach allows the methods that are traditionally used for materials science to be applied to biological systems [5]. References: [1] A Stevens, H Yang, L Carin et al. Microscopy 63(1), (2014), pp. 41. [2] L Kovarik, A Stevens, A Liyu et al. Appl. Phys. Lett. 109, 164102 (2016) [3] A Stevens, L Kovarik, P Abellan et al. Adv. Structural and Chemical Imaging 1(10), (2015), pp. 1. [4] MD Guay, W Czaja, MA Aronova et al. Scientific Reports 6, 27614 (2016) [5] Supported by the Chemical Imaging, Signature Discovery, and Analytics in Motion Initiatives at PNNL. PNNL is operated by Battelle Memorial Inst. for the US DOE; contract DE-AC05-76RL01830.

Stevens, Andrew↗

Comparison of Orientation Mapping in SEM and TEM

In this work, multiple experimental configurations for performing nanoscale orientation mapping are compared to determine their fidelity to the true 3D microstructure of a sample. Transmission Kikuchi Diffraction (TKD) experiments in an SEM and nanobeam diffraction (NBD) experiments in a TEM were performed on thin electrodeposited hard Au films with two different microstructures. The Au samples either have a grain size that is >50 nm or <20 nm. The same regions of the samples were measured with TKD apparatuses at 30 kV in an SEM with detectors in the horizontal and vertical configurations and in the TEM at 300 kV. Under the proper conditions, we demonstrate all three configurations can produce data of equivalent quality.Each method has strengths and challenges associated with its application and representation of the true microstructure. The conditions needed to obtain high-quality data for each acquisition method and the challenges associated with each will be discussed.

36 MATERIALS SCIENCE↗

On the Generalizability of Time-of-Flight Convolutional Neural Networks for Noninvasive Acoustic Measurements

Bulk wave acoustic time-of-flight (ToF) measurements in pipes and closed containers can be hindered by guided waves with similar arrival times propagating in the container wall, especially when a low excitation frequency is used to mitigate sound attenuation from the material. Convolutional neural networks (CNNs) have emerged as a new paradigm for obtaining accurate ToF in non-destructive evaluation (NDE) and have been demonstrated for such complicated conditions. However, the generalizability of ToF-CNNs has not been investigated. In this work, we analyze the generalizability of the ToF-CNN for broader applications, given limited training data. We first investigate the CNN performance with respect to training dataset size and different training data and test data parameters (container dimensions and material properties). Furthermore, we perform a series of tests to understand the distribution of data parameters that need to be incorporated in training for enhanced model generalizability. This is investigated by training the model on a set of small- and large-container datasets regardless of the test data. We observe that the quantity of data partitioned for training must be of a good representation of the entire sets and sufficient to span through the input space. The result of the network also shows that the learning model with the training data on small containers delivers a sufficiently stable result on different feature interactions compared to the learning model with the training data on large containers. To check the robustness of the model, we tested the trained model to predict the ToF of different sound speed mediums, which shows excellent accuracy. Furthermore, to mimic real experimental scenarios, data are augmented by adding noise. We envision that the proposed approach will extend the applications of CNNs for ToF prediction in a broader range.

47 OTHER INSTRUMENTATION↗

An open source knowledge graph ecosystem for the life sciences

Translational research requires data at multiple scales of biological organization. Advancements in sequencing and multi-omics technologies have increased the availability of these data, but researchers face significant integration challenges. Knowledge graphs (KGs) are used to model complex phenomena, and methods exist to construct them automatically. However, tackling complex biomedical integration problems requires flexibility in the way knowledge is modeled. Moreover, existing KG construction methods provide robust tooling at the cost of fixed or limited choices among knowledge representation models. PheKnowLator (Phenotype Knowledge Translator) is a semantic ecosystem for automating the FAIR (Findable, Accessible, Interoperable, and Reusable) construction of ontologically grounded KGs with fully customizable knowledge representation. The ecosystem includes KG construction resources (e.g., data preparation APIs), analysis tools (e.g., SPARQL endpoint resources and abstraction algorithms), and benchmarks (e.g., prebuilt KGs). We evaluated the ecosystem by systematically comparing it to existing open-source KG construction methods and by analyzing its computational performance when used to construct 12 different large-scale KGs. With flexible knowledge representation, PheKnowLator enables fully customizable KGs without compromising performance or usability.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Leveraging the checkpoint-restart technique for optimizing CPU efficiency of ATLAS production applications on opportunistic platforms

Data processing applications of the ATLAS experiment, such as event simulation and reconstruction, spend considerable amount of time in the initialization phase. This phase includes loading a large number of shared libraries, reading detector geometry and condition data from external databases, building a transient representation of the detector geometry and initializing various algorithms and services. In some cases the initialization step can take as long as 10-15 minutes. Such slow initialization has a significant negative impact on overall CPU efficiency of the production job, especially when the job is executed on opportunistic, often short-lived, resources such as commercial clouds or volunteer computing. In order to improve this situation, we can take advantage of the fact that ATLAS runs large numbers of production jobs with similar configuration parameters (e.g. jobs within the same production task). This allows us to checkpoint one job at the end of its configuration step and then use the generated checkpoint image for rapid startup of thousands of production jobs. By applying this technique we can bring the initialization time of a job from tens of minutes down to just a few seconds. In addition to that we can leverage container technology for restarting checkpointed applications on the variety of computing platforms, in particular of platforms different from the one on which the checkpoint image was created. We will describe the mechanism of creating checkpoint images of Geant4 simulation jobs with AthenaMP (the multi-process version of the ATLAS data simulation, reconstruction and analysis framework Athena) and the usage of these images for running ATLAS Simulation production jobs on volunteer computing resources (ATLAS@Home) and on Supercomputers.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Continous Representation Learning via User Feedback

Representation learning is a deep-learning based technique for extracting features from data for the purpose of machine learning. This requires a large amount of data, on order tens of thousands to millions of samples, to properly teach the deep neural network. This a system for continuous representation learning, where the system may be improved with a small number of additional samples (order 10-100). The unique characteristics of this invention include a human-computer feedback component, where assess the quality of the current representation and then provides a better representation to the system. The system then mixes the new data with old training examples to avoid overfitting and improve overall performance of the system. The model can be exported and shared with other users, and it may be applied to additional images the system hasn't seen before.

Source record↗

Fitting coupled potential energy surfaces for large systems: Method and construction of a 3-state representation for phenol photodissociation in the full 33 internal degrees of freedom using multireference configuration interaction determined data

A recently reported algorithm for representing adiabatic states coupled by conical intersections using a quasi-diabatic state Hamiltonian in four and five atom systems is extended to treat nonadiabatic processes in considerably larger molecules. The method treats all internal degrees of freedom and uses electronic structure data from ab initio multireference configuration interaction wave functions with nuclear configuration selection based on quasi-classical surface hopping trajectories. The method is shown here to be able to treat ∼30 internal degrees of freedom including dissociative and large amplitude internal motion. Two procedures are introduced which are essential to the algorithm, a null space projector which removes basis functions from the fitting process until they are needed and a partial diagonalization technique which allows for automated, but accurate, treatment of the vicinity of extended seams of conical intersections of two or more states. These procedures are described in detail. The method is illustrated using the photodissociaton of phenol, C{sub 6}H{sub 5}OH(X{sup ~1}A{sup ′}) + hv → C{sub 6}H{sub 5}OH(A{sup ~1}A{sup ′}, B{sup ~1}A{sup ′′}) → C{sub 6}H{sub 5}O(X{sup ~2}B{sub 1}, A{sup ~2}B{sub 2}) + H as a test case. Ab initio electronic structure data for the 1,2,3{sup 1}A states of phenol, which are coupled by conical intersections, are obtained from multireference first order configuration interaction wave functions. The design of bases to simultaneously treat large amplitude motion and dissociation is described, as is the ability of the fitting procedure to smooth the irregularities in the electronic energies attributable to the orbital changes that are inherent to nonadiabatic processes.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

A RESTful API for accessing microbial community data for MG-RAST

Metagenomic sequencing has produced significant amounts of data in recent years. For example, as of summer 2013, MGRAST has been used to annotate over 110,000 data sets totaling over 43 Terabases. With metagenomic sequencing finding even wider adoption in the scientific community, the existing web-based analysis tools and infrastructure in MG-RAST provide limited capability for data retrieval and analysis, such as comparative analysis between multiple data sets. Moreover, although the system provides many analysis tools, it is not comprehensive. By opening MG-RAST up via a web services API (application programmers interface) we have greatly expanded access to MG-RAST data, as well as provided a mechanism for the use of third-party analysis tools with MG-RAST data. This RESTful API makes all data and data objects created by the MG-RAST pipeline accessible as JSON objects. As part of the DOE Systems Biology Knowledgebase project (KBase, http:// kbase.us) we have implemented a web services API for MG-RAST. This API complements the existing MG-RAST web interface and constitutes the basis of KBase’s microbial community capabilities. In addition, the API exposes a comprehensive collection of data to programmers. This API, which uses a RESTful (Representational State Transfer) implementation, is compatible with most programming environments and should be easy to use for end users and third parties. It provides comprehensive access to sequence data, quality control results, annotations, and many other data types. Where feasible, we have used standards to expose data and metadata. Code examples are provided in a number of languages both to show the versatility of the API and to provide a starting point for users. We present an API that exposes the data in MG-RAST for consumption by our users, greatly enhancing the utility of the MG-RAST service.

59 BASIC BIOLOGICAL SCIENCES↗

QUALITATIVE INTERPRETATION OF GALAXY SPECTRA

We describe a simple step-by-step guide to qualitative interpretation of galaxy spectra. Rather than an alternative to existing automated tools, it is put forward as an instrument for quick-look analysis and for gaining physical insight when interpreting the outputs provided by automated tools. Though the recipe is for general application, it was developed for understanding the nature of the Automatic Spectroscopic K-means-based (ASK) template spectra. They resulted from the classification of all the galaxy spectra in the Sloan Digital Sky Survey data release 7, thus being a comprehensive representation of the galaxy spectra in the local universe. Using the recipe, we give a description of the properties of the gas and the stars that characterize the ASK classes, from those corresponding to passively evolving galaxies, to H II galaxies undergoing a galaxy-wide starburst. The qualitative analysis is found to be in excellent agreement with quantitative analyses of the same spectra. We compare the mean ages of the stellar populations with those inferred using the code STARLIGHT. We also examine the estimated gas-phase metallicity with the metallicities obtained using electron-temperature-based methods. A number of byproducts follow from the analysis. There is a tight correlation between the age of the stellar population and the metallicity of the gas, which is stronger than the correlations between galaxy mass and stellar age, and galaxy mass and gas metallicity. The galaxy spectra are known to follow a one-dimensional sequence, and we identify the luminosity-weighted mean stellar age as the affine parameter that describes the sequence. All ASK classes happen to have a significant fraction of old stars, although spectrum-wise they are outshined by the youngest populations. Old stars are metal-rich or metal-poor depending on whether they reside in passive galaxies or in star-forming galaxies.

79 ASTRONOMY AND ASTROPHYSICS↗

A common path forward for the immersive visualization community

Immersive visualization makes use of the medium of virtual reality (VR) - it is a subset of virtual reality focused on the application of VR technologies to scientific and information visualization. As the name implies, there is a particular focus on the physically immersive aspect of VR that more fully engages the perceptual and kinesthetic capabilities of the scientist with the goal of producing greater insight. The immersive visualization community is uniquely positioned to address the analysis needs of the wide spectrum of domain scientists who are becoming increasingly overwhelmed by data. The outputs of computational science simulations and high-resolution sensors are creating a data deluge. Data is coming in faster than it can be analyzed, and there are countless opportunities for discovery that are missed as the data speeds by. By more fully utilizing the scientists visual and other sensory systems, and by offering a more natural user interface with which to interact with computer-generated representations, immersive visualization offers great promise in taming this data torrent. However, increasing the adoption of immersive visualization in scientific research communities can only happen by simultaneously lowering the engagement threshold while raising the measurable benefits of adoption. Scientists time spent immersed with their data will thus be rewarded with higher productivity, deeper insight, and improved creativity. Immersive visualization ties together technologies and methodologies from a variety of related but frequently disjoint areas, including hardware, software and human-computer interaction (HCI) disciplines. In many ways, hardware is a solved problem. There are well established technologies including large walk-in systems such as the CAVE{trademark} and head-based systems such as the Wide-5{trademark}. The advent of new consumer-level technologies now enable an entirely new generation of immersive displays, with smaller footprints and costs, widening the potential consumer base. While one would be hard-pressed to call software a solved problem, we now understand considerably more about best practices for designing and developing sustainable, scalable software systems, and we have useful software examples that illuminate the way to even better implementations. As with any research endeavour, HCI will always be exploring new topics in interface design, but we now have a sizable knowledge base of the strengths and weaknesses of the human perceptual systems and we know how to design effective interfaces for immersive systems. So, in a research landscape with a clear need for better visualization and analysis tools, a methodology in immersive visualization that has been shown to effectively address some of those needs, and vastly improved supporting technologies and knowledge of hardware, software, and HCI, why hasn't immersive visualization 'caught on' more with scientists? What can we do as a community of immersive visualization researchers and practitioners to facilitate greater adoption by scientific communities so as to make the transition from 'the promise of virtual reality' to 'the reality of virtual reality'.

97 MATHEMATICS AND COMPUTING↗

Gradient-based Optimization for Regression in the Functional Tensor-Train Format

We consider the task of low-multilinear-rank functional regression, i.e., learning a low-rank parametric representation of functions from scattered real-valued data. Our first contribution is the development and analysis of gradient-based optimization procedures, including stochastic gradient descent and quasi-Newton methods, for learning the parameters of a functional tensor-train (FT) that yields improved accuracy over standard alternating least squares methods. The functional tensor-train uses the tensor-train (TT) representation of low-rank arrays as an ansatz for a class of low-multilinear-rank functions. The FT is represented by a set of matrix-valued functions that contain a set of univariate functions, and the regression task is to learn the parameters of these univariate functions. Our second contribution demonstrates that using nonlinearly parameterized univariate functions, e.g., symmetric kernels with moving centers, within each core can outperform the standard approach of using a linear expansion of basis functions. Our final contributions are new rank adaptation and group-sparsity regularization procedures to minimize overfitting. We use several benchmark problems to demonstrate at least an order of magnitude lower accuracy with gradient-based optimization methods than ALS in the low-sample number regime. We also demonstrate an order of magnitude reduction in accuracy on a test problem resulting from nonlinear parameterizations over linear parameterizations. Finally we compare regression performance with 22 other nonparametric and parametric regression methods on 10 real-world data sets. We achieve top-five accuracy for seven of the data sets and best accuracy for two of the data sets. These rankings are the best amongst parametric models and competetive with the best non-parametric methods.

97 MATHEMATICS AND COMPUTING↗

Uranium Oxide Synthetic Pathway Discernment through Unsupervised Morphological Analysis

We present a novel unsupervised machine learning method for quantitative representation of scanning electron micrographs and its applications and performance for nuclear forensic analysis of uranium ore concentrates. The method uses a vector quantizing variational autoencoder followed by a histogram operation to encode a micrograph into a single dimensional representation, called the latent vector. The method requires no extant labeling of the data and can be applied over large datasets of micrographs with minimal human interaction. The representations generated are broadly descriptive of each micrograph and the microstructure of the material imaged. In the case of uranium ore concentrate analysis, the representations were amenable to processing reagent and ore concentrate species classification with accuracy of 81:8%, which is competitive with state-of-the-art supervised networks. The representations were also used to classify previously unseen processing routes, were able to classify imaging parameters such as magnification (to 76:0% accuracy), were able to classify fine grained process parameters such as calcining temperature (to 74:4% accuracy), and their informatic properties indicate that they are generally descriptive of the image represented. This method can be applied across microstructure analysis fields to perform quantitative analysis without the need for labor intensive and possibly biased human analysis.

Scanning Electron Microscopy, Vector Quantizing Va↗

Artificial generation of representative single Li-ion electrode particle architectures from microscopy data

Accurately capturing the architecture of single lithium-ion electrode particles is necessary for understanding their performance limitations and degradation mechanisms through multi-physics modeling. Information is drawn from multimodal microscopy techniques to artificially generate LiNi 0.5 Mn 0.3 Co 0.2 O 2 particles with full sub-particle grain detail. Statistical representations of particle architectures are derived from X-ray nano-computed tomography data supporting an ‘outer shell’ model, and sub-particle grain representations are derived from focused-ion beam electron backscatter diffraction data supporting a ‘grain’ model. A random field model used to characterize and generate the outer shells, and a random tessellation model used to characterize and generate grain architectures, are combined to form a multi-scale model for the generation of virtual electrode particles with full-grain detail. This work demonstrates the possibility of generating representative single electrode particle architectures for modeling and characterization that can guide synthesis approaches of particle architectures with enhanced performance.

36 MATERIALS SCIENCE↗

Bridging 20 Years of Soil Organic Matter Frameworks: Empirical Support, Model Representation, and Next Steps

Abstract In the past few decades, there has been an evolution in our understanding of soil organic matter (SOM) dynamics from one of inherent biochemical recalcitrance to one deriving from plant‐microbe‐mineral interactions. This shift in understanding has been driven, in part, by influential conceptual frameworks which put forth hypotheses about SOM dynamics. Here, we summarize several focal conceptual frameworks and derive from them six controls related to SOM formation, (de)stabilization, and loss. These include: (a) physical inaccessibility; (b) organo‐mineral and ‐metal stabilization; (c) biodegradability of plant inputs; (d) abiotic environmental factors; (e) biochemical reactivity and diversity; and (f) microbial physiology and morphology. We then review the empirical evidence for these controls, their model representation, and outstanding knowledge gaps. We find relatively strong empirical support and model representation of abiotic environmental factors but disparities between data and models for biochemical reactivity and diversity, organo‐mineral and ‐metal stabilization, and biodegradability of plant inputs, particularly with respect to SOM destabilization for the latter two controls. More empirical research on physical inaccessibility and microbial physiology and morphology is needed to deepen our understanding of these critical SOM controls and improve their model representation. The SOM controls are highly interactive and also present some inconsistencies which may be reconciled by considering methodological limitations or temporal and spatial variation. Future conceptual frameworks must simultaneously refine our understanding of these six SOM controls at various spatial and temporal scales and within a hierarchical structure, while incorporating emerging insights. This will advance our ability to accurately predict SOM dynamics.

54 ENVIRONMENTAL SCIENCES↗

Extraction of Tumor Site from Cancer Pathology Reports using Deep Filters

Purpose: Pathology reports are the primary source of information concerning the millions of cancer cases across the United States. Cancer registries manually process the pathology reports to extract the pertinent information including primary tumor site, behavior, histology, laterality, and grade. Processing a large volume of the pathology reports in a timely manner is a continuing challenge for cancer registries. The purpose of this study is to develop an information extraction pipeline to reliably and efficiently extract reportable information. Method: We have developed a novel inverse-regression (IR) based information extraction pipeline. The inverse-regression based supervised filter has been successfully applied to many application domains. However, its application to the information extraction from unstructured text is hindered primarily by the extreme high-dimensionality of n-gram representations of text. In this study, we attempt to overcome the obstacles by a novel bootstrapping strategy. First, we use an information-theoretic mutual information based filter to discard the excessive and redundant n-gram features. This step reduces the size and improves the condition number of the sample covariance matrix, thus reducing the computational cost and improving the numerical stability of the subsequent inverse-regression step. Then we use localized sliced inverse-regression (LSIR) to learn a low-dimensional discriminatory subspace for information inference. In particular, we use the k-nearest neighbors of an unlabeled pathology report in the learned representation to infer the desired information from the labeled data in a supervised manner. Results: The experiments were conducted on a set of de-identified pathology reports with human expert labels as the ground truth. Our pipeline consistently performed better than or comparable to the best performing state-of-the-art methods while reducing the training and inference times substantially. Conclusion: Our results demonstrate the potential of inverse-regression based information extraction pipeline for reliable and efficient information extraction from unstructured text. The information extracted from the pathology reports can be used along with clinical information, medical imaging, and genomic information to instigate discoveries in cancer research.

Dubey, Abhishek↗

Experimental investigation and thermodynamic modeling of the binary Pt–Sn system

Here, the thermodynamics of the Pt–Sn system is revisited with attention to phase equilibria involving PtSn 4 , a topological quantum material with interesting physical properties. The phase relationship in the Sn-rich region of the Pt–Sn binary system was investigated by a combination of differential scanning calorimetry and equilibration experiments. Based on the present experiments and a critical evaluation of the available thermodynamic and phase diagram data reported in the literature, thermodynamic assessments of the entire Pt–Sn system were performed using the CALPHAD approach. Two sets of thermodynamic parameters were optimized, where the liquid phase was described using the Bragg-Williams random mixing model and the associate solution model, respectively. The modeling results are compared with the reliable experimental data and are shown to provide good representations of the phase equilibria and thermodynamic properties in this system.

36 MATERIALS SCIENCE↗