Search NASA⌕ Search

SEARCH · Search NASA

Results for “shape classification”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Dual X-ray computed tomography-aided classification of melt pool boundaries and flaws in crept additively manufactured parts

In metal additive manufacturing (AM), understanding the process-structure-performance relationships requires a combination of multi-scale characterization techniques that allows for the measurement of the melt pool shape and boundary and classifying various defects and flaws in the AM parts. Such approaches can be destructive, only 2D in nature, or have a small field of view and can be complex to co-register and analyze. Here, in this work, we present a non-destructive 3D inspection technique that employs dual-energy X-ray computed tomography (XCT) along with a model-based iterative reconstruction (MBIR) and a new segmentation algorithm. The proposed approach and algorithm are not only capable of classifying and quantifying flaws such as pores, cracks, and inclusions, but they also allow for the extraction of microstructural features such as melt pool boundaries (MPB) and melt pool regions (MPR), that can help understand process-structure-performance relationships for alloys under study. As an exemplar application, we employed the method for characterization of an additively manufactured aluminum alloy crept under tensile stress at 300 °C for 1064 h. Our results demonstrate high quality segmentation and classification of various flaws and MPB and MPR, for the first time, using 3D X-ray CT inspection. The delineated MPB and MPR in the crept samples reveal the preferential growth paths of cracks that formed during creep deformation. The technique was used for successfully quantifying the characteristics (number of defects, their density, volume fraction, etc.) of the manufacturing-induced pores and creep-induced cracks, which is necessary to better understand the creep failure mechanisms of the material.

36 MATERIALS SCIENCE↗
DOE OSTI2019

In Situ Quality Monitoring in AM Using Acoustic Emission: A Reinforcement Learning Approach

Additive manufacturing (AM) has attracted considerable attention in recent years. This technology overcomes the geometrical limits of workpieces produced with the traditional subtractive methods and so gives the opportunity to manufacture highly complex shapes. Unfortunately, the repeatability of the manufacturing process and the monitoring of quality are not reliable enough to be utilized in mass production. The quality monitoring of AM processes in commercial equipment has been largely based on temperature measurements of the process zone or high-resolution imaging of the layers. However, both techniques lack information about the physical phenomena taking place in the depth of the materials medium and this limits their reliability in real-life applications. To overcome those restrictions, we propose to combine acoustic emission and reinforcement learning. The former captures the information about the subsurface dynamics of the process. The latter is a branch of machine learning that allows interpreting the received data in terms of quality. The combination of both is an original method for in situ and real-time quality monitoring. Acoustic data were collected during a real process using a commercial AM machine. The process parameters were selected to achieve three levels of quality in terms of porosity concentration while manufacturing a stainless steel 316L cuboid shape. Using our method, we demonstrated that each level of quality produced unique acoustic signatures during the build that were recognized by the classifier. The classification accuracy reached in this work proves that the proposed method has high potential to be used as in situ and real-time monitoring of AM quality.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2018

A new analysis approach based on Haralick texture features for the characterization of microstructure on the example of low-alloy steels

Highlights: • Microstructures were characterized based on orientation-invariant image-texture features. • A new parameter called “amplitude”, was formulated and is based on image rotation and the Haralick parameters: texture contrast, correlation, homogeneity and energy. • The proposed method is insensitive to changing image resolution and image contrast/brightness settings. - Abstract: Microstructures were analyzed by an improved texture-based method using gray level co-occurrence matrices (GLCM). This method is based on a new parameter calculated from the stepwise rotation of images and thereby, calculating the values independent of the original texture orientation. The proposed method was applied on a database of etched and scanning electron microscopy (SEM)-imaged low-carbon steel microstructures that are currently extensively used for automated microstructure classification. The results on the microstructures consisting of pearlitic, lath martensitic and lower bainitic constituents revealed that the method allows a significant separation of various types of microstructures in the ideal case of square-shaped cutouts. For complete grains of the corresponding second phases, the results imply that the application of a classifier is advantageous to distinguish them with a sufficient accuracy. The robustness and workability of the method was further demonstrated by discussing the effect of varying the image resolution and contrast/brightness settings during image acquisition. It was shown that such user-dependent setting parameters do not impair the separability of the steel constituents by using the proposed method.

36 MATERIALS SCIENCE↗
DOE OSTI2024

The Evaluation of Machine Learning Techniques for Isotope Identification Contextualized by Training and Testing Spectral Similarity

Precise gamma-ray spectral analysis is crucial in high-stakes applications, such as nuclear security. Research efforts toward implementing machine learning (ML) approaches for accurate analysis are limited by the resemblance of the training data to the testing scenarios. The underlying spectral shape of synthetic data may not perfectly reflect measured configurations, and measurement campaigns may be limited by resource constraints. Consequently, ML algorithms for isotope identification must maintain accurate classification performance under domain shifts between the training and testing data. To this end, four different classifiers (Ridge, Random Forest, Extreme Gradient Boosting, and Multilayer Perceptron) were trained on the same dataset and evaluated on twelve other datasets with varying standoff distances, shielding, and background configurations. A tailored statistical approach was introduced to quantify the similarity between the training and testing configurations, which was then related to the predictive performance. Wilcoxon signed-rank tests revealed that the OVR-wrapped XGB significantly outperformed the other algorithms, with confidence levels of 99.0% or above for the 133Ba, 60Co, 137Cs, and 152Eu sources. The findings from this work are significant as they outline techniques to promote the development of robust ML-based approaches for isotope identification.

domain adaptation↗
DOE OSTI2016

MO-DE-207A-02: A Feature-Preserving Image Reconstruction Method for Improved Pancreaticlesion Classification in Diagnostic CT Imaging

Purpose: To develop a feature-preserving model based image reconstruction (MBIR) method that improves performance in pancreatic lesion classification at equal or reduced radiation dose. Methods: A set of pancreatic lesion models was created with both benign and premalignant lesion types. These two classes of lesions are distinguished by their fine internal structures; their delineation is therefore crucial to the task of pancreatic lesion classification. To reduce image noise while preserving the features of the lesions, we developed a MBIR method with curvature-based regularization. The novel regularization encourages formation of smooth surfaces that model both the exterior shape and the internal features of pancreatic lesions. Given that the curvature depends on the unknown image, image reconstruction or denoising becomes a non-convex optimization problem; to address this issue an iterative-reweighting scheme was used to calculate and update the curvature using the image from the previous iteration. Evaluation was carried out with insertion of the lesion models into the pancreas of a patient CT image. Results: Visual inspection was used to compare conventional TV regularization with our curvature-based regularization. Several penalty-strengths were considered for TV regularization, all of which resulted in erasing portions of the septation (thin partition) in a premalignant lesion. At matched noise variance (50% noise reduction in the patient stomach region), the connectivity of the septation was well preserved using the proposed curvature-based method. Conclusion: The curvature-based regularization is able to reduce image noise while simultaneously preserving the lesion features. This method could potentially improve task performance for pancreatic lesion classification at equal or reduced radiation dose. The result is of high significance for longitudinal surveillance studies of patients with pancreatic cysts, which may develop into pancreatic cancer. The Senior Author receives financial support from Siemens GmbH Healthcare.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

NuSTAR SPECTROSCOPY OF MULTI-COMPONENT X-RAY REFLECTION FROM NGC 1068

We report on high-energy X-ray observations of the Compton-thick Seyfert 2 galaxy NGC 1068 with NuSTAR, which provide the best constraints to date on its >10 keV spectral shape. The NuSTAR data are consistent with those from past and current instruments to within cross-calibration uncertainties, and we find no strong continuum or line variability over the past two decades, which is in line with its X-ray classification as a reflection-dominated Compton-thick active galactic nucleus. The combined NuSTAR, Chandra, XMM-Newton, and Swift BAT spectral data set offers new insights into the complex secondary emission seen instead of the completely obscured transmitted nuclear continuum. The critical combination of the high signal-to-noise NuSTAR data and the decomposition of the nuclear and extranuclear emission with Chandra allow us to break several model degeneracies and greatly aid physical interpretation. When modeled as a monolithic (i.e., a single N{sub H}) reflector, none of the common Compton reflection models are able to match the neutral fluorescence lines and broad spectral shape of the Compton reflection hump without requiring unrealistic physical parameters (e.g., large Fe overabundances, inconsistent viewing angles, or poor fits to the spatially resolved spectra). A multi-component reflector with three distinct column densities (e.g., with best-fit values of N{sub H} of 1.4 × 10{sup 23}, 5.0 × 10{sup 24}, and 10{sup 25} cm{sup −2}) provides a more reasonable fit to the spectral lines and Compton hump, with near-solar Fe abundances. In this model, the higher N{sub H} component provides the bulk of the flux to the Compton hump, while the lower N{sub H} component produces much of the line emission, effectively decoupling two key features of Compton reflection. We find that ≈30% of the neutral Fe Kα line flux arises from >2″ (≈140 pc) and is clearly extended, implying that a significant fraction (and perhaps most) of the <10 keV reflected component arises from regions well outside a parsec-scale torus. These results likely have ramifications for the interpretation of Compton-thick spectra from observations with poorer signal-to-noise and/or more distant objects.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2016

SN REFSDAL: CLASSIFICATION AS A LUMINOUS AND BLUE SN 1987A-LIKE TYPE II SUPERNOVA

We have acquired Hubble Space Telescope (HST) and Very Large Telescope near-infrared spectra and images of supernova (SN) Refsdal after its discovery as an Einstein cross in fall 2014. The HST light curve of SN Refsdal has a shape consistent with the distinctive, slowly rising light curves of SN 1987A-like SNe, and we find strong evidence for a broad H α P-Cygni profile and Na I D absorption in the HST grism spectrum at the redshift ( z = 1.49) of the spiral host galaxy. SNe IIn, largely powered by circumstellar interaction, could provide a good match to the light curve of SN Refsdal, but the spectrum of a SN IIn would not show broad and strong H α and Na I D absorption. From the grism spectrum, we measure an H α expansion velocity consistent with those of SN 1987A-like SNe at a similar phase. The luminosity, evolution, and Gaussian profile of the H α emission of the WFC3 and X-shooter spectra, separated by ∼2.5 months in the rest frame, provide additional evidence that supports the SN 1987A-like classification. In comparison with other examples of SN 1987A-like SNe, photometry of SN Refsdal favors bluer B - V and V - R colors and one of the largest luminosities for the assumed range of potential magnifications. The evolution of the light curve at late times will provide additional evidence about the potential existence of any substantial circumstellar material. Using MOSFIRE and X-shooter spectra, we estimate a subsolar host-galaxy metallicity (8.3 ± 0.1 dex and <8.4 dex, respectively) near the explosion site.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2018

Artificial neural network algorithms for pulse shape discrimination and recovery of piled-up pulses in organic scintillators

We developed two neural-network (NN)-based algorithms (fully-connected neural network (Fc-NN) and recurrent neural network (RNN)) to perform pulse shape discrimination (PSD) and identification of piled-up pulses produced by organic scintillators, upon interaction with neutrons and gamma rays. We tested the algorithms on measured and verification sets of data and compared their classification performances to standard approaches. At a high acquisition count rate (100,000 counts per second, cps), in the presence of a gamma-to-neutron ratio of approximately 400–1, the proposed NN-based algorithm achieves a fraction of misclassified neutron, gamma, and piled-up pulses of approximately 1%, 1.8%, and 0.6%, respectively. Compared to the traditional approach, it exhibits 3×, 14×, and 11× improved (lower) miscalculation rates for neutron, gamma, and piled-up pulses, respectively. Here, we also demonstrate the capability of NN-based algorithms of successfully recovering and identifying neutron and gamma ray compositions from piled-up pulses in challenging, high pulse count rate conditions.

42 ENGINEERING↗
DOE OSTI2015

Application of Bayes' theorem for pulse shape discrimination

A Bayesian approach is proposed for pulse shape discrimination of photons and neutrons in liquid organic scinitillators. Instead of drawing a decision boundary, each pulse is assigned a photon or neutron confidence probability. In addition, this allows for photon and neutron classification on an event-by-event basis. The sum of those confidence probabilities is used to estimate the number of photon and neutron instances in the data. An iterative scheme, similar to an expectation-maximization algorithm for Gaussian mixtures, is used to infer the ratio of photons-to-neutrons in each measurement. Therefore, the probability space adapts to data with varying photon-to-neutron ratios. A time-correlated measurement of Am–Be and separate measurements of 137 Cs, 60 Co and 232 Th photon sources were used to construct libraries of neutrons and photons. These libraries were then used to produce synthetic data sets with varying ratios of photons-to-neutrons. Probability weighted method that we implemented was found to maintain neutron acceptance rate of up to 90% up to photon-to-neutron ratio of 2000, and performed 9% better than the decision boundary approach. Furthermore, the iterative approach appropriately changed the probability space with an increasing number of photons which kept the neutron population estimate from unrealistically increasing.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Decarbonizing via disparities: Problematizing the relationship between social identity and solar energy transitions in the United States

As solar adoption across the United States continues to grow, so do the gaps between rural and urban communities in how they choose to embrace these technologies, leading to serious questions of social justice and equity by researchers and policymakers alike. While recent studies have examined the racial and social justice elements of solar adoption alongside institutions' role in shaping pro-solar policies, codes, and code enforcement, an opportunity exists to discuss how the place and composition of the body politic in terms of race/ethnicity and rurality exists. This paper establishes a methodology for examining location and body politic composition concerning adopting all types of solar (residential, non-residential, utility-scale), utilizing the State of Georgia as a case study. Results indicate that the approach yields useful and informative findings; namely, there is a significant difference in adopting non-residential and utility-scale solar between rural and urban counties. We conclude by discussing further opportunities to expand on this analysis and the impact of assessing solar adoption in terms of value alignment between a body politic and the policies that shape the adoption of sustainable energy technologies. Finally, combining solar adoption information for the State of Georgia with Census data, this study compares solar adoption trends across counties--grouped by urban/rural classification and racial and ethnic majority.

14 SOLAR ENERGY↗
DOE OSTI2025

SIDDA: SInkhorn Dynamic Domain Adaptation for image classification with equivariant neural networks

Modern neural networks (NNs) often do not generalize well in the presence of a ‘covariate shift’; that is, in situations where the training and test data distributions differ, but the conditional distribution of classification labels given the data remains unchanged. In such cases, NN generalization can be reduced to a problem of learning more robust, domain-invariant features. Domain adaptation (DA) methods include a broad range of techniques aimed at achieving this; however, these methods have struggled with the need for extensive hyperparameter tuning, which then incurs significant computational costs. In this work, we introduce SInkhorn Dynamic Domain Adaptation (SIDDA), an out-of-the-box DA training algorithm built upon the Sinkhorn divergence, that can achieve effective domain alignment with minimal hyperparameter tuning and computational overhead. We demonstrate the efficacy of our method on multiple simulated and real datasets of varying complexity, including simple shapes, handwritten digits, real astronomical observations, and remote sensing data. These datasets exhibit covariate shifts due to noise, blurring, differences between telescopes, and variations in imaging wavelengths. SIDDA is compatible with a variety of NN architectures, and it works particularly well in improving classification accuracy and model calibration when paired with symmetry-aware equivariant NNs (ENNs). We find that SIDDA consistently enhances the generalization capabilities of NNs, achieving up to a ${\approx}40\%$ improvement in classification accuracy on unlabeled target data, while also providing a more modest performance gain of $\lesssim 1\%$ on labeled source data. We also study the efficacy of DA on ENNs with respect to the varying group orders of the dihedral group DN, and find that the model performance improves as the degree of equivariance increases. Finally, if SIDDA achieves proper domain alignment, it also enhances model calibration on both source and target data, with the most significant gains in the unlabeled target domain—achieving over an order of magnitude improvement in the expected calibration error and Brier score. SIDDA’s versatility across various NN models and datasets, combined with its automated approach to domain alignment, has the potential to significantly advance multi-dataset studies by enabling the development of highly generalizable models.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2019

Event-Shape Engineering for the D-meson elliptic flow in mid-central Pb-Pb collisions at $\sqrt{s_{\mathrm{NN}}}=5.02$ TeV

The production yield of prompt D mesons and their elliptic flow coefficient $\nu$ 2 were measured with the Event-Shape Engineering (ESE) technique applied to mid-central (10–30% and 30–50% centrality classes) Pb-Pb collisions at the centre-of-mass energy per nucleon pair $\sqrt{s_{\mathrm{NN}}}=5.02$ TeV, with the ALICE detector at the LHC. The ESE technique allows the classification of events, belonging to the same centrality, according to the azimuthal anisotropy of soft particle production in the collision. The reported measurements give the opportunity to investigate the dynamics of charm quarks in the Quark-Gluon Plasma and provide information on their participation in the collective expansion of the medium. D mesons were reconstructed via their hadronic decays at mid-rapidity, | η | < 0.8, in the transverse momentum interval 1 < p T < 24 GeV/ c . The $\nu$ 2 coefficient is found to be sensitive to the event-shape selection confirming a correlation between the D-meson azimuthal anisotropy and the collective expansion of the bulk matter, while the per-event D-meson yields do not show any significant modification within the current uncertainties.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2015

SU-E-J-248: Contributions of Tumor and Stroma Phenotyping in Computer-Aided Diagnosis

Purpose: To gain insight into the role of parenchyma stroma in the characterization of breast tumors by incorporating computerized mammographic parenchyma assessment into breast CADx in the task of distinguishing between malignant and benign lesions. Methods: This study was performed on 182 biopsy-proven breast mass lesions, including 76 benign and 106 malignant lesions. For each full-field digital mammogram (FFDM) case, our quantitative imaging analysis was performed on both the tumor and a region-of-interest (ROI) from the normal contralateral breast. The lesion characterization includes automatic lesion segmentation and feature extraction. Radiographic texture analysis (RTA) was applied on the normal ROIs to assess the mammographic parenchymal patterns of these contralateral normal breasts. Classification performance of both individual computer extracted features and the output from a Bayesian artificial neural network (BANN) were evaluated with a leave-one-lesion-out method using receiver operating characteristic (ROC) analysis with area under the curve (AUC) as the figure of merit. Results: Lesion characterization included computer-extracted phenotypes of spiculation, size, shape, and margin. For parenchymal pattern characterization, five texture features were selected, including power law beta, contrast, and edge gradient. Merging of these computer-selected features using BANN classifiers yielded AUC values of 0.79 (SE=0.03) and 0.67 (SE=0.04) in the task of distinguishing between malignant and benign lesions using only tumor phenotypes and texture features from the contralateral breasts, respectively. Incorporation of tumor phenotypes with parenchyma texture features into the BANN yielded improved classification performance with an AUC value of 0.83 (SE=0.03) in the task of differentiating malignant from benign lesions. Conclusion: Combining computerized tumor and parenchyma phenotyping was found to significantly improve breast cancer diagnostic accuracy highlighting the need to consider both tumor and stroma in decision making. Funding: University of Chicago Dean Bridge Fund, NCI U24-CA143848-05, P50-CA58223 Breast SPORE program, and Breast Cancer Research Foundation. COI: MLG is a stockholder in R2 technology/Hologic and receives royalties from Hologic, GE Medical Systems, MEDIAN Technologies, Riverain Medical, Mitsubishi, and Toshiba. MLG is a cofounder and stockholder in Quantitative Insights.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2017

Volume changes upon heating of aerosol particles from biomass burning using transmission electron microscopy

The responses of aerosol particles to heating are important for measurements of their chemical, physical, and optical properties, classification, and determination of origin. However, the thermal behavior of organic aerosol particles is largely unknown. We provide a method to analyze such thermal behavior through heating from room temperature to >600°C by using a heating holder within a transmission electron microscope (TEM). Here we describe in-situ shape and size changes and variations in the compositions of individual particles before and after heating. We use ambient samples from wildland and agricultural biomass fires in North America collected during the 2013 Biomass Burn Observation Project (BBOP). The results indicate that individual tar balls (TB; spherical organic material) from biomass burning retained, on average, up to 30% of their volume when heated to 600°C. Chemical analysis reveals that K and Na remain in the residues, whereas S and O were lost. In contrast to bulk sample measurements of carbonaceous particles using thermal/optical carbon analyzers, our single-particle results imply that many individual organic particles consist of multiple types of organic matter having different thermal stabilities. Beyond TBs, our results suggest that because of their thermal stability some organic particles may not be detectable by using aerosol mass spectrometry or thermal/optical carbon analyzers. This result can lead to an underestimate of the abundance of TBs and other organic particles, and therefore biomass burning may have more influence than currently recognized in regional and global climate models.

Adachi, Kouji↗
DOE OSTI2016

Mediastinal lymph node detection and station mapping on chest CT using spatial priors and random forest

Purpose: To develop an automated system for mediastinal lymph node detection and station mapping for chest CT. Methods: The contextual organs, trachea, lungs, and spine are first automatically identified to locate the region of interest (ROI) (mediastinum). The authors employ shape features derived from Hessian analysis, local object scale, and circular transformation that are computed per voxel in the ROI. Eight more anatomical structures are simultaneously segmented by multiatlas label fusion. Spatial priors are defined as the relative multidimensional distance vectors corresponding to each structure. Intensity, shape, and spatial prior features are integrated and parsed by a random forest classifier for lymph node detection. The detected candidates are then segmented by the following curve evolution process. Texture features are computed on the segmented lymph nodes and a support vector machine committee is used for final classification. For lymph node station labeling, based on the segmentation results of the above anatomical structures, the textual definitions of mediastinal lymph node map according to the International Association for the Study of Lung Cancer are converted into patient-specific color-coded CT image, where the lymph node station can be automatically assigned for each detected node. Results: The chest CT volumes from 70 patients with 316 enlarged mediastinal lymph nodes are used for validation. For lymph node detection, their system achieves 88% sensitivity at eight false positives per patient. For lymph node station labeling, 84.5% of lymph nodes are correctly assigned to their stations. Conclusions: Multiple-channel shape, intensity, and spatial prior features aggregated by a random forest classifier improve mediastinal lymph node detection on chest CT. Using the location information of segmented anatomic structures from the multiatlas formulation enables accurate identification of lymph node stations.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Protein Conformational States—A First Principles Bayesian Method

Automated identification of protein conformational states from simulation of an ensemble of structures is a hard problem because it requires teaching a computer to recognize shapes. We adapt the naïve Bayes classifier from the machine learning community for use on atom-to-atom pairwise contacts. The result is an unsupervised learning algorithm that samples a ‘distribution’ over potential classification schemes. We apply the classifier to a series of test structures and one real protein, showing that it identifies the conformational transition with >95% accuracy in most cases. A nontrivial feature of our adaptation is a new connection to information entropy that allows us to vary the level of structural detail without spoiling the categorization. This is confirmed by comparing results as the number of atoms and time-samples are varied over 1.5 orders of magnitude. Further, the method’s derivation from Bayesian analysis on the set of inter-atomic contacts makes it easy to understand and extend to more complex cases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Preprocessing for Unintended Conducted Emissions Classification with ResNet

Characterization of Unintended Conducted Emissions (UCE) from electronic devices is important when diagnosing electromagnetic interference, performing nonintrusive load monitoring (NILM) of power systems, and monitoring electronic device health, among other applications. Prior work has demonstrated that UCE analysis can serve as a diagnostic tool for energy efficiency investigations and detailed load analysis. While explaining the feature selection of deep networks with certainty is often not fully comprehensive, or in other applications, quite lacking, additional tools/methods for further corroboration and confirmation can help further the understanding of the researcher. This is true especially in the subject application of the study in this paper. Often the focus of such efforts is the selected features themselves, and there is not as much understanding gained about the noise in the collected data. If selected feature and noise characteristics are known, it can be used to further shape the design of the deep network or associated preprocessing. This is additionally difficult when the available data are limited, as in the case which the authors investigated in this study. Here, the authors present a novel work (which is a proposed complementary portion of the overall solution to the deep network classification explainability problem for this application) by applying a systematic progression of preprocessing and a deep neural network (ResNet architecture) to classify UCE data obtained via current transformers. By using a methodical application of preprocessing techniques prior to a deep classifier, hypotheses can be produced concerning what features the deep network deems important relative to what it perceives as noise. For instance, it is hypothesized in this particular study as a result of execution of the proposed method and periodic inspection of the classifier output that the UCE spectral features are relatively close to each other or to the interferers, as systematically reducing the beta parameter of the Kaiser window produced progressively better classification performance, but only to a point, as going below the Beta of eight produced decreased classifier performance, as well as the hypothesis that further spectral feature resolution was not as important to the classifier as rejection of the leakage from a spectrally distant interference. This can be very important in unpredictable low-FNR applications, where knowing the difference between features and noise is difficult. As a side-benefit, much was learned regarding the best preprocessing to use with the selected deep network for the UCE collected from these low power consumer devices obtained via current transformers. Baseline rectangular windowed FFT preprocessing provided a 62% classification increase versus using raw samples. After performing a more optimal preprocessing, more than 90% classification accuracy was achieved across 18 low-power consumer devices for scenarios in which the in-band features-to-noise ratio (FNR) was very poor.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2015

SU-E-T-517: Investigation of Factors Contributing to Extracranial Radiation Doses From Leksell Gamma Knife

Purpose The purpose of this study is to investigate dominant factors for doses to extracranial sites in treatment with Leksell Gamma Knife (LGK). Methods Monte Carlo simulation was implemented using EGS5 version 1.4.401. The simulation was divided into two major steps for the purpose of efficiency. As the first step, phase-space files were obtained at a scoring plane located just below patient-side surface of the collimator helmet of LGK. Scored particles were classified into three groups, primary, leakage and scatter, using their history information until their arrival to the scoring plane. Then classification was used at the following second step simulation to investigate which type of particle is dominant in the deposited energy at extra-cranial sites. In the second stage, a cylindrical phantom with a semisphere shaped head was modeled such that the geometrical center of the phantom’s head corresponds to the unit center point (UCP) of LGK. Scoring regions were arranged at 10 cm intervals from the UCP to 70 cm away on the central axis of the phantom. Energy deposition from each type of particles and location of interaction were recorded. Results The dominant factor of deposited energy depended on the collimator size. In the case of smaller collimator size, leakage was dominant. However, contribution of leakage was relatively small in the case of larger collimator size. The contribution of internal scatter varied with the distance from the UCP. In the proximal areas, internal scatter was dominant, whereas in the distal areas, particles interacting with machine components became dominant factor. Conclusion The Result of this study indicates that the dominant factor to dose to an extracranial site can vary with the distance from UCP and with collimator size. This means that the variation of this contribution must be considered for modeling of the extracranial dose especially in the distal area. This work was partly supported by the JSPS Core-to-Core Program (No. 23003)

60 APPLIED LIFE SCIENCES↗