SEARCH · Engineering Papers

Results for “error vector”

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.

SourceResearch connectionFrom yearThrough year

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

At least 325 records · Page 18

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Development of advanced machine learning models for analysis of plutonium surrogate optical emission spectra

This work investigates and applies machine learning paradigms seldom seen in analytical spectroscopy for quantification of gallium in cerium matrices via processing of laser-plasma spectra. Ensemble regressions, support vector machine regressions, Gaussian kernel regressions, and artificial neural network techniques are trained and tested on cerium-gallium pellet spectra. A thorough hyperparameter optimization experiment is conducted initially to determine the best design features for each model. The optimized models are evaluated for sensitivity and precision using the limit of detection (LoD) and root mean-squared error of prediction (RMSEP) metrics, respectively. Gaussian kernel regression yields the superlative predictive model with an RMSEP of 0.33% and an LoD of 0.015% for quantification of Ga in a Ce matrix. This study concludes that these machine learning methods could yield robust prediction models for rapid quality control analysis of plutonium alloys.

Rao, Ashwin P. (ORCID:0000000319312568)↗

DOE OSTI2015

On approaches to analyze the sensitivity of simulated hydrologic fluxes to model parameters in the community land model

Here, effective sensitivity analysis approaches are needed to identify important parameters or factors and their uncertainties in complex Earth system models composed of multi-phase multi-component phenomena and multiple biogeophysical-biogeochemical processes. In this study, the impacts of 10 hydrologic parameters in the Community Land Model on simulations of runoff and latent heat flux are evaluated using data from a watershed. Different metrics, including residual statistics, the Nash-Sutcliffe coefficient, and log mean square error, are used as alternative measures of the deviations between the simulated and field observed values. Four sensitivity analysis (SA) approaches, including analysis of variance based on the generalized linear model, generalized cross validation based on the multivariate adaptive regression splines model, standardized regression coefficients based on a linear regression model, and analysis of variance based on support vector machine, are investigated. Results suggest that these approaches show consistent measurement of the impacts of major hydrologic parameters on response variables, but with differences in the relative contributions, particularly for the secondary parameters. The convergence behaviors of the SA with respect to the number of sampling points are also examined with different combinations of input parameter sets and output response variables and their alternative metrics. This study helps identify the optimal SA approach, provides guidance for the calibration of the Community Land Model parameters to improve the model simulations of land surface fluxes, and approximates the magnitudes to be adjusted in the parameter values during parametric model optimization.

58 GEOSCIENCES↗

DOE OSTI2022

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (3 rd Annual Report)

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This report primarily focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 ± 0.014, 0.0026 ± 0, and 0.063 ± 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure. This report summarizes the Fiscal Year 2021 research progress encompassing the (1) data cleaning and feature selection necessary for ML applications; (2) development of short-term forecasting models to predict future plant process parameters for both single and multiple time steps ahead; and (3) validation of the feature selection methods and short-term forecasting models given new data from different systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2017

Multiscale Persistent Functions for Biomolecular Structure Characterization

Here in this paper, we introduce multiscale persistent functions for biomolecular structure characterization. The essential idea is to combine our multiscale rigidity functions (MRFs) with persistent homology analysis, so as to construct a series of multiscale persistent functions, particularly multiscale persistent entropies, for structure characterization. To clarify the fundamental idea of our method, the multiscale persistent entropy (MPE) model is discussed in great detail. Mathematically, unlike the previous persistent entropy (Chintakunta et al. in Pattern Recognit 48(2):391–401, 2015; Merelli et al. in Entropy 17(10):6872–6892, 2015; Rucco et al. in: Proceedings of ECCS 2014, Springer, pp 117–128, 2016), a special resolution parameter is incorporated into our model. Various scales can be achieved by tuning its value. Physically, our MPE can be used in conformational entropy evaluation. More specifically, it is found that our method incorporates in it a natural classification scheme. This is achieved through a density filtration of an MRF built from angular distributions. To further validate our model, a systematical comparison with the traditional entropy evaluation model is done. Additionally, it is found that our model is able to preserve the intrinsic topological features of biomolecular data much better than traditional approaches, particularly for resolutions in the intermediate range. Moreover, by comparing with traditional entropies from various grid sizes, bond angle-based methods and a persistent homology-based support vector machine method (Cang et al. in Mol Based Math Biol 3:140–162, 2015), we find that our MPE method gives the best results in terms of average true positive rate in a classic protein structure classification test. More interestingly, all-alpha and all-beta protein classes can be clearly separated from each other with zero error only in our model. Finally, a special protein structure index (PSI) is proposed, for the first time, to describe the “regularity” of protein structures. Basically, a protein structure is deemed as regular if it has a consistent and orderly configuration. Our PSI model is tested on a database of 110 proteins; we find that structures with larger portions of loops and intrinsically disorder regions are always associated with larger PSI, meaning an irregular configuration, while proteins with larger portions of secondary structures, i.e., alpha-helix or beta-sheet, have smaller PSI. Essentially, PSI can be used to describe the “regularity” information in any systems.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2026

Transplatformer: translating toxicogenomic profiles between generations of platforms

Background Transcriptomic profiling technologies have advanced the analysis of biological and toxicological responses. However, substantial differences in probe design, dynamic range, gene coverage, and preprocessing pipelines across platforms introduce artifacts that limit cross-study integration and hinder the reuse of historical datasets. We aim to develop computational methods for accurate cross-platform translation to maximize the value of legacy resources. Results We present TransPlatformer a deep learning framework for translating gene expression profiles across heterogeneous toxicogenomics platforms. TransPlatformer employs a novel attention-based architecture to map high-dimensional fold-change vectors from legacy microarray technologies to current platforms. Models are trained and evaluated using DrugMatrix, spanning three technological generations. We investigate mixed-tissue, single-tissue, and cross-tissue training paradigms and benchmark performance against multilayer perceptron and matrix-completion baselines. In mixed-tissue training, TransPlatformer achieves a greater than 50% reduction in mean absolute error (0.043 vs. 0.09) and nearly doubles Pearson correlation ( ≈ 0.71 vs. 0.37) relative to baseline methods. Importantly, TransPlatformer preserves rare but biologically meaningful over- and under-expressed signals, with mean absolute error below 0.22. Single-tissue models yield further improvements for well-represented organs, such as a 10% reduction in liver mean absolute error, while underscoring the need for data augmentation strategies in low-sample tissues.ra Conclusions TransPlatformer provides an effective and scalable computational solution for cross-platform transcriptomic translation. By enabling biologically faithful harmonization of gene expression data, the proposed approach facilitates the reuse of legacy toxicogenomics datasets, enhances downstream biomarker discovery, and supports more reproducible predictive modeling in toxicology.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2013

Anisotropic Margin Expansions in 6 Anatomic Directions for Oropharyngeal Image Guided Radiation Therapy

Purpose: The purpose of this work was to determine the expansions in 6 anatomic directions that produced optimal margins considering nonrigid setup errors and tissue deformation for patients receiving image-guided radiation therapy (IGRT) of the oropharynx. Methods and Materials: For 20 patients who had received IGRT to the head and neck, we deformably registered each patient's daily images acquired with a computed tomography (CT)-on-rails system to his or her planning CT. By use of the resulting vector fields, the positions of volume elements within the clinical target volume (CTV) (target voxels) or within a 1-cm shell surrounding the CTV (normal tissue voxels) on the planning CT were identified on each daily CT. We generated a total of 15,625 margins by dilating the CTV by 1, 2, 3, 4, or 5 mm in the posterior, anterior, lateral, medial, inferior, and superior directions. The optimal margins were those that minimized the relative volume of normal tissue voxels positioned within the margin while satisfying 1 of 4 geometric target coverage criteria and 1 of 3 population criteria. Results: Each pair of geometric target coverage and population criteria resulted in a unique, anisotropic, optimal margin. The optimal margin expansions ranged in magnitude from 1 to 5 mm depending on the anatomic direction of the expansion and on the geometric target coverage and population criteria. Typically, the expansions were largest in the medial direction, were smallest in the lateral direction, and increased with the demand of the criteria. The anisotropic margin resulting from the optimal set of expansions always included less normal tissue than did any isotropic margin that satisfied the same pair of criteria. Conclusions: We demonstrated the potential of anisotropic margins to reduce normal tissue exposure without compromising target coverage in IGRT to the head and neck.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

DOE OSTI2014

SDSS/SEGUE spectral feature analysis for stellar atmospheric parameter estimation

Large-scale and deep sky survey missions are rapidly collecting a large amount of stellar spectra, which necessitate the estimation of atmospheric parameters directly from spectra and make it feasible to statistically investigate latent principles in a large data set. We present a technique for estimating parameters T{sub eff}, log g, and [Fe/H] from stellar spectra. With this technique, we first extract features from stellar spectra using the LASSO algorithm; then, the parameters are estimated from the extracted features using the support vector regression. On a subsample of 20,000 stellar spectra from the Sloan Digital Sky Survey (SDSS) with reference parameters provided by the SDSS/SEGUE Spectroscopic Parameter Pipeline, estimation consistency are 0.007458 dex for log T{sub eff} (101.609921 K for T{sub eff}), 0.189557 dex for log g, and 0.182060 for [Fe/H], where the consistency is evaluated by mean absolute error. Prominent characteristics of the proposed scheme are sparseness, locality, and physical interpretability. In this work, each spectrum consists of 3821 fluxes, and 10, 19, and 14 typical wavelength positions are detected, respectively, for estimating T{sub eff}, log g, and [Fe/H]. It is shown that the positions are related to typical lines of stellar spectra. This characteristic is important in investigating physical indications from analysis results. Then, stellar spectra can be described by the individual fluxes on the detected positions (PD) or local integration of fluxes near them (LI). The aforementioned consistency is the result based on features described by LI. If features are described by PD, consistency is 0.009092 dex for log T{sub eff} (124.545075 K for T{sub eff}), 0.198928 dex for log g, and 0.206814 dex for [Fe/H].

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2016

Spectral functions with the density matrix renormalization group: Krylov-space approach for correction vectors

Frequency-dependent correlations, such as the spectral function and the dynamical structure factor, help illustrate condensed matter experiments. Within the density matrix renormalization group (DMRG) framework, an accurate method for calculating spectral functions directly in frequency is the correction-vector method. The correction vector can be computed by solving a linear equation or by minimizing a functional. Our paper proposes an alternative to calculate the correction vector: to use the Krylov-space approach. Further, this paper also studies the accuracy and performance of the Krylov-space approach, when applied to the Heisenberg, the t-J, and the Hubbard models. The cases we studied indicate that the Krylov-space approach can be more accurate and efficient than the conjugate gradient, and that the error of the former integrates best when a Krylov-space decomposition is also used for ground state DMRG.

36 MATERIALS SCIENCE↗

DOE OSTI2016

Identification of the Diffusion Parameter in Nonlocal Steady Diffusion Problems

The problem of identifying the diffusion parameter appearing in a nonlocal steady diffusion equation is considered. The identification problem is formulated as an optimal control problem having a matching functional as the objective of the control and the parameter function as the control variable. The analysis makes use of a nonlocal vector calculus that allows one to define a variational formulation of the nonlocal problem. In a manner analogous to the local partial differential equations counterpart, we demonstrate, for certain kernel functions, the existence of at least one optimal solution in the space of admissible parameters. We introduce a Galerkin finite element discretization of the optimal control problem and derive a priori error estimates for the approximate state and control variables. Using one-dimensional numerical experiments, we illustrate the theoretical results and show that by using nonlocal models it is possible to estimate non-smooth and discontinuous diffusion parameters.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2015

Improved methods for Feynman path integral calculations and their application to calculate converged vibrational–rotational partition functions, free energies, enthalpies, entropies, and heat capacities for methane

We present an improved version of our “path-by-path” enhanced same path extrapolation scheme for Feynman path integral (FPI) calculations that permits rapid convergence with discretization errors ranging from O(P{sup −6}) to O(P{sup −12}), where P is the number of path discretization points. We also present two extensions of our importance sampling and stratified sampling schemes for calculating vibrational–rotational partition functions by the FPI method. The first is the use of importance functions for dihedral angles between sets of generalized Jacobi coordinate vectors. The second is an extension of our stratification scheme to allow some strata to be defined based only on coordinate information while other strata are defined based on both the geometry and the energy of the centroid of the Feynman path. These enhanced methods are applied to calculate converged partition functions by FPI methods, and these results are compared to ones obtained earlier by vibrational configuration interaction (VCI) calculations, both calculations being for the Jordan–Gilbert potential energy surface. The earlier VCI calculations are found to agree well (within ∼1.5%) with the new benchmarks. The FPI partition functions presented here are estimated to be converged to within a 2σ statistical uncertainty of between 0.04% and 0.07% for the given potential energy surface for temperatures in the range 300–3000 K and are the most accurately converged partition functions for a given potential energy surface for any molecule with five or more atoms. We also tabulate free energies, enthalpies, entropies, and heat capacities.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2015

Isovector and isoscalar tensor charges of the nucleon from lattice QCD

We present results for the iso-vector and flavor diagonal tensor charges $g$$^{u−d}_{T}$, $g$$^{u}_{T}$, $g$$^{d}_{T}$, and $g$$^{s}_{T}$ needed to probe novel tensor interactions at the TeV scale in neutron and nuclear β-decays and the contribution of the quark electric dipole moment (EDM) to the neutron EDM. The lattice QCD calculations were done using nine ensembles of gauge configurations generated by the MILC collaboration using the HISQ action with 2+1+1 dynamical flavors. These ensembles span three lattice spacings a ≈ 0.06, 0.09 and 0.12 fm and three quark masses corresponding to the pion masses M π ≈ 130, 220 and 310 MeV. Using estimates from these ensembles, we quantify all systematic uncertainties and perform a simultaneous extrapolation in the lattice spacing, volume and light quark masses for the connected contributions. The final estimates of the connected nucleon (proton) tensor charge for the iso-vector combination is $g$$^{u−d}_{T}$ = 1.020(76) in the MS scheme at 2 GeV. The additional disconnected quark loop contributions needed for the flavor-diagonal matrix elements are calculated using a stochastic estimator employing the truncated solver method with the all-mode-averaging technique. We find that the size of the disconnected contribution is smaller than the statistical error in the connected contribution. This allows us to bound the disconnected contribution and include it as an additional uncertainty in the flavor-diagonal charges. After a continuum extrapolation, we find $g$$^{u}_{T}$ = 0.774(66), $g$$^{d}_{T}$ = −0.233(28) and $g$$^{u+d}_{T}$ = 0.541(67). The strangeness tensor charge, that can make a significant contribution to the neutron EDM due to the large ratio ms/mu,d, is $g$$^{s}_{T}$ = 0.008(9) in the continuum limit.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2023

𝐷-meson semileptonic decays to pseudoscalars from four-flavor lattice QCD

We present lattice-QCD calculations of the hadronic form factors for the semileptonic decays D → πℓν, D → Kℓν, and D s → Kℓν. Our calculation uses the highly improved staggered quark (HISQ) action for all valence and sea quarks and includes N f = 2 + 1 + 1 MILC ensembles with lattice spacings ranging from a ≈ 0.12 fm down to 0.042 fm. At most lattice spacings, an ensemble with physical-mass light quarks is included. The HISQ action allows all the quarks to be treated with the same relativistic light-quark action, allowing for nonperturbative renormalization using partial conservation of the vector current. We combine our results with experimental measurements of the differential decay rates to determine |V cd | D → π = 0.2238(11) Expt (15) QCD (04) EW (02) SIB [22] QED and |V cs | D → K = 0.9589 (23) Expt (40) QCD (15) EW (05) SIB [95] QED . This result for |V cd | is the most precise to date, with a lattice-QCD error that is, for the first time for the semileptonic extraction, at the same level as the experimental error. Using recent measurements from BES III, we also give the first-ever determination of |V cd | D s → K = 0.258(15) Expt (01) QCD [03] QED from D s → Klν. Our results also furnish new Standard Model calculations of the lepton flavor universality ratios $R$$^{D → π}_{μ/e}$ = 0.98671(17) QCD [500] QED , $R$$^{D → π}_{μ/e}$ = 0.97606(16) QCD [500] QED , and $R$$^{D → π}_{μ/e}$ = 0.98099(10) QCD [500] QED , which are consistent within 2σ with experimental measurements. Our extractions of |V cd | and |V cs |, when combined with a value for |V cb |, provide the most precise test of second-row Cabibbo-Kobayashi-Maskawa unitarity, finding agreement with unitarity at the level of one standard deviation.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2016

MWR3C physical retrievals of precipitable water vapor and cloud liquid water path

The data set contains physical retrievals of PWV and cloud LWP retrieved from MWR3C measurements during the MAGIC campaign. Additional data used in the retrieval process include radiosondes and ceilometer. The retrieval is based on an optimal estimation technique that starts from a first guess and iteratively repeats the forward model calculations until a predefined convergence criterion is satisfied. The first guess is a vector of [PWV,LWP] from the neural network retrieval fields in the netcdf file. When convergence is achieved the 'a posteriori' covariance is computed and its square root is expressed in the file as the retrieval 1-sigma uncertainty. The closest radiosonde profile is used for the radiative transfer calculations and ceilometer data are used to constrain the cloud base height. The RMS error between the brightness temperatures is computed at the last iterations as a consistency check and is written in the last column of the output file.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2016

Application of mixed kernels function (MKF) based support vector regression model (SVR) for CO 2 – Reservoir oil minimum miscibility pressure prediction

Carbon dioxide (CO 2 ) injection into oil reservoirs is considered a mature enhanced oil recovery (EOR) technique for conventional reservoirs. The local displacement efficiency of the CO 2 -EOR process is highly dependent on the minimum miscibility pressure (MMP), estimating this parameter is critical to design of the CO 2 injection process. Traditional empirical methods to test the CO 2 -oil MMP are time consuming and expensive; derived correlations are fast but not accurate. Therefore, an efficient and reliable method to determine MMP is beneficial. Here in this study, a mixed kernels function (MKF) based support vector regression (SVR) model was developed and used to predict the MMP for both pure and impure CO 2 injection cases. Four parameters were chosen as input parameters: (1) reservoir temperature; (2) average critical temperature; (3) molecular weight of pentane plus (C 5+ ) fraction of crude oil, and; (4) the ratio of volatile components to intermediate components in crude oil. MMP was selected as the desired output parameter to train and test this newly developed model. The performance of basic kernels function based SVR model is compared with that of this newly developed MKF-SVR model. The well-trained MFK-SVR was compared with three well-established published correlations, demonstrated the highest correlation coefficient (R of 0.9381), lowest root mean square error (RMSE of 1.9151), smallest average absolute error (AAE of 1.1406) and maximum absolute error (MAE of 4.6291). We believe that the proposed MFK-SVM model is a more reliable and stable regression model to predict MMP. In addition, a sensitivity analysis was conducted to evaluate the physical correctness. It indicates that the predicted results from the newly developed model are in excellent agreement with previous empirical work.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2020

General Protocol for the Accurate Prediction of Molecular 13 C/ 1 H NMR Chemical Shifts via Machine Learning Augmented DFT

An accurate prediction of NMR chemical shifts at affordable computational cost is very important for different types of structural assignments in experimental studies. Density functional theory (DFT) and gauge-including atomic orbital (GIAO) are two of the most popular computational methods for NMR calculation, yet they often fail to resolve ambiguities in structural assignments. In this work, we present a new method that uses machine learning (ML) techniques (DFT + ML) that significantly increases the accuracy of 13 C/ 1 H NMR chemical shift prediction for a variety of organic molecules. The input of the generalizable DFT + ML model contains two critical parts: one is a vector providing insights into chemical environments, which can be evaluated without knowing the exact geometry of the molecule; the other one is the DFT-calculated isotropic shielding constant. The DFT + ML model was trained with a data set containing 476 13 C and 270 1 H experimental chemical shifts. For the DFT methods used here, the root mean square deviations (RMSDs) for the errors between predicted and experimental 13 C/ 1 H chemical shifts can be as small as 2.10/0.18 ppm, which is much lower than those from simple DFT (5.54/0.25 ppm), or DFT + linear regression (LR) (4.77/0.23 ppm) approaches. It also has a smaller maximum absolute error than two previously proposed NMR-predicting ML models. The robustness of the DFT + ML model is tested on two classes of organic molecules (TIC10 and hyacinthacines), where the correct isomers were unambiguously assigned to the experimental ones. Overall, the DFT + ML model shows promise for structural assignments in a variety of systems, including stereoisomers, that are often challenging to determine experimentally.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2015

SU-E-J-91: Biomechanical Deformable Image Registration of Longitudinal Lung CT Images

Purpose: Spatial correlation of lung tissue across longitudinal images, as the patient responds to treatment, is a critical step in adaptive radiotherapy. The goal of this work is to expand a biomechanical model-based deformable registration algorithm (Morfeus) to achieve accurate registration in the presence of significant anatomical changes. Methods: Four lung cancer patients previously treated with conventionally fractionated radiotherapy that exhibited notable tumor shrinkage during treatment were retrospectively evaluated. Exhale breathhold CT scans were obtained at treatment planning (PCT) and following three weeks (W3CT) of treatment. For each patient, the PCT was registered to the W3CT using Morfeus, a biomechanical model-based deformable registration algorithm, consisting of boundary conditions on the lungs and incorporating a sliding interface between the lung and chest wall. To model the complex response of the lung, an extension to Morfeus has been developed: (i) The vessel tree was segmented by thresholding a vesselness image based on the Hessian matrix’s eigenvalues and the centerline was extracted; (ii) A 3D shape context method was used to find correspondences between the trees of the two images; (ii) Correspondences were used as additional boundary conditions (Morfeus+vBC). An expert independently identified corresponding landmarks well distributed in the lung to compute Target Registration Errors (TRE). Results: The TRE within 15mm of the tumor boundaries (on average 11 landmarks) is: 6.1±1.8, 4.6±1.1 and 3.8±2.3 mm after rigid registration, Morfeus and Morfeus+vBC, respectively. The TRE in the rest of the lung (on average 13 landmarks) is: 6.4±3.9, 4.7±2.2 and 3.6±1.9 mm, which is on the order of the 2mm isotropic dose grid vector (3.5mm). Conclusion: The addition of boundary conditions on the vessels improved the accuracy in modeling the response of the lung and tumor over the course of radiotherapy. Minimizing and modeling these geometrical uncertainties will enable future plan adaptation strategies. This work was funded in part by NIH 2P01CA059827-16.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2015

MO-F-CAMPUS-J-02: Automatic Recognition of Patient Treatment Site in Portal Images Using Machine Learning

Purpose: To investigate the method to automatically recognize the treatment site in the X-Ray portal images. It could be useful to detect potential treatment errors, and to provide guidance to sequential tasks, e.g. automatically verify the patient daily setup. Methods: The portal images were exported from MOSAIQ as DICOM files, and were 1) processed with a threshold based intensity transformation algorithm to enhance contrast, and 2) where then down-sampled (from 1024×768 to 128×96) by using bi-cubic interpolation algorithm. An appearance-based vector space model (VSM) was used to rearrange the images into vectors. A principal component analysis (PCA) method was used to reduce the vector dimensions. A multi-class support vector machine (SVM), with radial basis function kernel, was used to build the treatment site recognition models. These models were then used to recognize the treatment sites in the portal image. Portal images of 120 patients were included in the study. The images were selected to cover six treatment sites: brain, head and neck, breast, lung, abdomen and pelvis. Each site had images of the twenty patients. Cross-validation experiments were performed to evaluate the performance. Results: MATLAB image processing Toolbox and scikit-learn (a machine learning library in python) were used to implement the proposed method. The average accuracies using the AP and RT images separately were 95% and 94% respectively. The average accuracy using AP and RT images together was 98%. Computation time was ∼0.16 seconds per patient with AP or RT image, ∼0.33 seconds per patient with both of AP and RT images. Conclusion: The proposed method of treatment site recognition is efficient and accurate. It is not sensitive to the differences of image intensity, size and positions of patients in the portal images. It could be useful for the patient safety assurance. The work was partially supported by a research grant from Varian Medical System.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2022

Using artificial intelligence to detect human errors in nuclear power plants: A case in operation and maintenance

Human error (HE) is an important concern in safety-critical systems such as nuclear power plants (NPPs). HE has played a role in many accidents and outage incidents in NPPs. Despite the increased automation in NPPs, HE remains unavoidable. Hence, the need for HE detection is as important as HE prevention efforts. In NPPs, HE is rather rare. Hence, anomaly detection, a widely used machine learning technique for detecting rare anomalous instances, can be repurposed to detect potential HE. In this study, we develop an unsupervised anomaly detection technique based on generative adversarial networks (GANs) to detect anomalies in manually collected surveillance data in NPPs. More specifically, our GAN is trained to detect mismatches between automatically recorded sensor data and manually collected surveillance data, and hence, identify anomalous instances that can be attributed to HE. We test our GAN on both a real-world dataset and an external dataset obtained from a testbed, and we benchmark our results against state-of-the-art unsupervised anomaly detection algorithms, including one-class support vector machine and isolation forest. Our results show that the proposed GAN provides improved anomaly detection performance. Our study is promising for the future development of artificial intelligence based HE detection systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗