Search NASA⌕ Search

SEARCH · Search NASA

Results for “regression”

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 145 records · Page 8

Efficient Decision Trees for Tensor Regressions

Here, we proposed the tensor-input tree (TT) method for scalar-on-tensor and tensor-on-tensor regression problems. We first address scalar-on-tensor problem by proposing scalar-output regression tree models whose input variables are tensors (i.e., multi-way arrays). We devised and implemented fast randomized and deterministic algorithms for efficient fitting of scalar-on-tensor trees, making TT competitive against tensor-input GP models (Yu, Li, and Liu; Sun et al.). Based on scalar-on-tensor tree models, we extend our method to tensor-on-tensor problems using additive tree ensemble approaches. Theoretical justification and extensive experiments, including testing robustness to entrywise input tensor noise, are provided on real and synthetic datasets to illustrate the performance of TT. Our implementation is provided at https://github.com/hrluo/TensorDecisionTreeRegressor. Supplementary materials for this article are available online.

Decision tree regressions↗

Identifying microbial drivers in biological phenotypes with a Bayesian network regression model

Abstract In Bayesian Network Regression models, networks are considered the predictors of continuous responses. These models have been successfully used in brain research to identify regions in the brain that are associated with specific human traits, yet their potential to elucidate microbial drivers in biological phenotypes for microbiome research remains unknown. In particular, microbial networks are challenging due to their high dimension and high sparsity compared to brain networks. Furthermore, unlike in brain connectome research, in microbiome research, it is usually expected that the presence of microbes has an effect on the response (main effects), not just the interactions. Here, we develop the first thorough investigation of whether Bayesian Network Regression models are suitable for microbial datasets on a variety of synthetic and real data under diverse biological scenarios. We test whether the Bayesian Network Regression model that accounts only for interaction effects (edges in the network) is able to identify key drivers (microbes) in phenotypic variability. We show that this model is indeed able to identify influential nodes and edges in the microbial networks that drive changes in the phenotype for most biological settings, but we also identify scenarios where this method performs poorly which allows us to provide practical advice for domain scientists aiming to apply these tools to their datasets. BNR models provide a framework for microbiome researchers to identify connections between microbes and measured phenotypes. We allow the use of this statistical model by providing an easy‐to‐use implementation which is publicly available Julia package at https://github.com/solislemuslab/BayesianNetworkRegression.jl .

59 BASIC BIOLOGICAL SCIENCES↗

A precise non-invasive blood glucose measurement system using NIR spectroscopy and Huber’s regression model

Diabetes is one of the prominent diseases around the world. Presently, invasive techniques need a finger prick blood sample . A repetitively painful procedure that produces the chance of infection. To resolve this issue, non-invasive measurement approach is proposed. In this paper, an efficient NIR wave based optical detection system is proposed with optimized post-processing regression model. After real-time data analysis, it has been found that the coefficient of determination (R{sup 2}) is improved with the value of 0.9084 using proposed regression model. Mean absolute derivative is also increased with 3.87 mg/dl corresponding to predicted blood glucose concentration. Mean absolute relative difference has exceeded to 3.25%, and average error is improved with 3.77% using proposed regression model. Average accuaracy has been analyzed 94–95% for predicted blood glucose concentration.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Inverse regression for ridge recovery: a data-driven approach for parameter reduction in computer experiments

Parameter reduction can enable otherwise infeasible design and uncertainty studies with modern computational science models that contain several input parameters. In statistical regression, techniques for sufficient dimension reduction (SDR) use data to reduce the predictor dimension of a regression problem. A computational scientist hoping to use SDR for parameter reduction encounters a problem: a computer prediction is best represented by a deterministic function of the inputs, so data comprised of computer simulation queries fail to satisfy the SDR assumptions. To address this problem, here we interpret SDR methods sliced inverse regression (SIR) and sliced average variance estimation (SAVE) as estimating the directions of a ridge function, which is a composition of a low-dimensional linear transformation with a nonlinear function. Within this interpretation, SIR and SAVE estimate matrices of integrals whose column spaces are contained in the ridge directions’ span; we analyze and numerically verify convergence of these column spaces as the number of computer model queries increases. Moreover, we show example functions that are not ridge functions but whose inverse conditional moment matrices are low-rank. Consequently, the computational scientist should beware when using SIR and SAVE for parameter reduction, since SIR and SAVE may mistakenly suggest that truly important directions are unimportant.

97 MATHEMATICS AND COMPUTING↗

SymbolFit: Automatic Parametric Modeling with Symbolic Regression

We introduce SymbolFit (API: https://github.com/hftsoi/symbolfit), a framework that automates parametric modeling by using symbolic regression to perform a machine-search for functions that fit the data while simultaneously providing uncertainty estimates in a single run. Traditionally, constructing a parametric model to accurately describe binned data has been a manual and iterative process, requiring an adequate functional form to be determined before the fit can be performed. The main challenge arises when the appropriate functional forms cannot be derived from first principles, especially when there is no underlying true closed-form function for the distribution. In this work, we develop a framework that automates and streamlines the process by utilizing symbolic regression, a machine learning technique that explores a vast space of candidate functions without requiring a predefined functional form because the functional form itself is treated as a trainable parameter, making the process far more efficient and effortless than traditional regression methods. We demonstrate the framework in high-energy physics experiments at the CERN Large Hadron Collider (LHC) using five real proton-proton collision datasets from new physics searches, including background modeling in resonance searches for high-mass dijet, trijet, paired-dijet, diphoton, and dimuon events. We show that our framework can flexibly and efficiently generate a wide range of candidate functions that fit a nontrivial distribution well using a simple fit configuration that varies only by random seed, and that the same fit configuration, which defines a vast function space, can also be applied to distributions of different shapes, whereas achieving a comparable result with traditional methods would have required extensive manual effort.

Tsoi, Ho Fung [Univ. of Pennsylvania, Philadelphia↗

Natural antibody against neuroblastoma of TH-MYCN transgenic mice does not correlate with spontaneous regression

The mechanism underlying the spontaneous regression of neuroblastoma is unclear. Although it was hypothesized that this regression occurs via an immunological mechanism, there is no clinical evidence, and no animal models have been developed to investigate the involvement of immune systems, especially natural antibodies, against neuroblastoma. We performed an immunological analysis of homo- and heterozygous TH-MYCN transgenic mice as a model of aggressive neuroblastoma. Mice with no or small (5 mm) tumors. A significant negative correlation was observed between the tumor diameter and the titer of antitumor antibody. This antibody had complement-dependent cytotoxicity but not antibody-dependent cellular cytotoxicity against neuroblastoma cells. Moreover, B-cell depletion had no effect on the tumor incidence in vivo. We revealed that TH-MYCN transgenic mice have a natural antibody against neuroblastoma that correlate with tumor size. However, this antibody does not correlate with the spontaneous regression of neuroblastoma. Thus, the function of the natural antibody is limited.

60 APPLIED LIFE SCIENCES↗

Gaussian process regression constrained by boundary value problems

We develop a framework for Gaussian processes regression constrained by boundary value problems. The framework may be applied to infer the solution of a well-posed boundary value problem with a known second-order differential operator and boundary conditions, but for which only scattered observations of the source term are available. Scattered observations of the solution may also be used in the regression. The framework combines co-kriging with the linear transformation of a Gaussian process together with the use of kernels given by spectral expansions in eigenfunctions of the boundary value problem. Furthermore, it benefits from a reduced-rank property of covariance matrices. We demonstrate that the resulting framework yields more accurate and stable solution inference as compared to physics-informed Gaussian process regression without boundary condition constraints.

42 ENGINEERING↗

Using hair and fingernails in binary logistic regression for bio-monitoring of heavy metals/metalloid in groundwater in intensively agricultural areas, Thailand

Highlights: • The heavy metals (HMs) in hairs and nails of people in agricultural areas were measured. • HMs in hairs and nails from GW drinking group were significantly higher than the other. • High drinking rate for long term of GW even low concentration of HMs had adverse health effects to human. • The associated factors and probabilities were found by χ{sup 2} statistic and binary logistic regression. • Not only HMs in groundwater, but this study found other associated factors affecting to human. In this study, the hair and fingernails of the local people in an intensively cultivated agricultural area in Ubon Ratchathani province, Thailand, were used as biomarkers of exposure to arsenic (As) and heavy metals. The study area has shallow acidic groundwater that is contaminated with As and heavy metals. The local people often consume this shallow groundwater; thus, they are exposed to As and heavy metals. Hair and fingernail samples were collected to characterize the differences between shallow groundwater drinking (SGWD) and tap water drinking (TWD) residents. The concentrations of As and the heavy metals Cd, Pb and Hg were significantly higher in the hair samples from the SGWD group than those from the TWD group, especially for As (0.020–0.571 vs. 0.024–0.359 µg/g) and Cd (0.009–0.575 vs. 0.013–0.230 µg/g). Similarly, the concentrations of As and the heavy metals in the fingernail samples collected from the SGWD group were larger than those of the TWD group, especially for As (0.039–2.440 µg/g vs. 0.049–0.806 µg/g). The χ{sup 2} statistic and binary logistic regression were used to find the associated factors and assess the associated probabilities. The regression results show that the factors associated with the concentrations of As and the heavy metals in the hair samples were drinking water source, rate of water consumption, gender, bathing water source, education, smoking and underlying disease, whereas the factors associated with the concentrations of these species in the fingernail samples were drinking water source, gender, occupation, work hours per day, alcohol consumption, and the use of pesticides.

54 ENVIRONMENTAL SCIENCES↗

Dose Response for Radiation Cataractogenesis: A Meta-Regression of Hematopoietic Stem Cell Transplantation Regimens

Purpose/Objective(s): To perform a meta-regression on published data and to model the 5-year probability of cataract development after hematopoietic stem cell transplantation (HSCT) with and without total body irradiation (TBI). Methods and Materials: Eligible studies reporting cataract incidence after HSCT with TBI were identified by a PubMed search. Seventeen publications provided complete information on radiation dose schedule, fractionation, dose rate, and actuarial cataract incidence. Chemotherapy-only regimens were included as zero radiation dose regimens. Multivariate meta-regression with a weighted generalized linear model was used to model the 5-year cataract incidence and contributory factors. Results: Data from 1386 patients in 21 series were included for analysis. TBI was administered to a total dose of 0 to 15.75 Gy with single or fractionated schedules with a dose rate of 0.04 to 0.16 Gy/min. Factors significantly associated with 5-year cataract incidence were dose, dose times dose per fraction (D•dpf), pediatric versus adult status, and the absence of an ophthalmologist as an author. Dose rate, graft versus host disease, steroid use, hyperfractionation, and number of fractions were not significant. Five-fold internal cross-validation showed a model validity of 83% ± 8%. Regression diagnostics showed no evidence of lack-of-fit and no patterns in the studentized residuals. The α/β ratio from the linear quadratic model, estimated as the ratio of the coefficients for dose and D•dpf, was 0.76 Gy (95% confidence interval [CI], 0.05-1.55). The odds ratio for pediatric patients was 2.8 (95% CI, 1.7-4.6) relative to adults. Conclusions: Dose, D•dpf, pediatric status, and regimented follow-up care by an ophthalmologist were predictive of 5-year cataract incidence after HSCT. The low α/β ratio indicates the importance of fractionation in reducing cataracts. Dose rate effects have been observed in single institution studies but not in the combined data analyzed here. Although data were limited to articles with 5-year actuarial estimates, the development of radiation-induced cataracts extends beyond this time.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Reduction of spectral interferences and noise effects in laser ablation molecular isotopic spectrometry with partial least square regression – a computer simulation study

The fundamental analytical accuracies and precisions attainable by laser ablation molecular isotopic spectrometry (LAMIS), with emphasis on the impacts from spectral interferences and measurement noise, were investigated by means of computer simulation. The study focused on the analysis of a minor isotope at sub- to single-percentage abundance level. With a natural abundance about 1.1% for 13 C, the C 2 Swan band (d 3 II g - a 3 II u ) with Δν = + 1 was selected as a representative system. The characteristics (e.g., noise amplitude and distribution, signal strength, and signal-to-background ratio) of the simulated spectra were experimentally characterized. Partial least square (PLS) regression was used to extract isotopic information from the simulated molecular spectra. In the absence of any spectral interference and with the use of a calibration set consisting of eleven isotopic standards, the theoretical accuracies and precisions with signal accumulation from 100 laser shots are about 0.002% and 0.001%, respectively, in absolute percentage abundance of 13 C. The theoretical analytical accuracies slightly degrade, but are adequate for many applications, to 0.004% and 0.008% respectively, for calibrations involving only three and two isotopic standards. It was found that PLS regression is not only immune to both source-flicker and photon-shot noise, but is also effective in differentiating the spectral patterns from the analyte against those from spectral interferences. The influences of spectral interference from single or multiple atomic emission lines were simulated, and new ways to minimize their impacts were formulated and demonstrated. It was found that the wavelength range selected for the computation of the normalization factor should not contain any spectral-interfering peak, and a properly chosen wavelength range increases the tolerance of spectral interference by at least one order of magnitude. With matrix-matched calibration standards, the precisions (expressed as RSDs of the determined 13 C isotopic abundances) degrade from ~ 1% in the absence of spectral interference, to ~ 3&#8240, 10&#8240 and 20&#8240 with multiple spectral-interfering peaks that are 10 ×, 100 × and 1000 ×, respectively, stronger than the molecular bandhead of the analyte. The study concluded that PLS regression is a powerful and indispensable tool for extraction of isotopic information from LAMIS spectra.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Toward Guided Mutagenesis: Gaussian Process Regression Predicts MHC Class II Antigen Mutant Binding

Antigen-specific immunotherapies (ASI) require successful loading and presentation of antigen peptides into the major histocompatibility complex (MHC) binding cleft. One route of ASI design is to mutate native antigens for either stronger or weaker binding interaction to MHC. Exploring all possible mutations is costly both experimentally and computationally. To reduce experimental and computational expense, here we investigate the minimal amount of prior data required to accurately predict the relative binding affinity of point mutations for peptide-MHC class II (pMHCII) binding. Using data from different residue subsets, we interpolate pMHCII mutant binding affinities by Gaussian process (GP) regression of residue volume and hydrophobicity. We apply GP regression to an experimental data set from the Immune Epitope Database, and theoretical data sets from NetMHCIIpan and Free Energy Perturbation calculations. We find that GP regression can predict binding affinities of nine neutral residues from a six-residue subset with an average R 2 coefficient of determination value of 0.62 ± 0.04 (±95% CI), average error of 0.09 ± 0.01 kcal/mol (±95% CI), and with an receiver operating characteristic (ROC) AUC value of 0.92 for binary classification of enhanced or diminished binding affinity. Similarly, metrics increase to an R2 value of 0.69 ± 0.04, average error of 0.07 ± 0.01 kcal/mol, and an ROC AUC value of 0.94 for predicting seven neutral residues from an eight-residue subset. Our work finds that prediction is most accurate for neutral residues at anchor residue sites without register shift. This work holds relevance to predicting pMHCII binding and accelerating ASI design.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Coupling High-Throughput Experiments and Regression Algorithms to Optimize PGM-Free ORR Electrocatalyst Synthesis

Over the past decades, significant improvement has been achieved in the performance of platinum group metal-free (PGM-free) materials as an alternative to Pt-based electrocatalysts for oxygen reduction reaction (ORR). However, further progress in ORR activity requires evaluation of precursors and synthesis approaches. In response to this challenge, we generated a first of its kind experimental data set of 36 samples using high-throughput synthesis and activity measurements. Several control parameters (e.g., Fe precursor identity, the precursor content, and pyrolysis temperature) were varied. We then developed several state-of-the-art machine learning (ML) based regression models to predict ORR activity, dependent on selected synthesis variables. Through an iterative algorithm, higher prediction accuracy (smaller root-mean-square error) was achieved. We identified that gradient boosting regression (GBR) and support vector regression (SVR), among several methods, work best for this data set. Aided by our ML-based surrogate models, we decided to alter catalyst synthesis conditions, which resulted in a 36% increase in measured ORR activity in comparison to the maximum ORR mass activity value of 21.9 A/g catalyst in the original data set. Overall, this combined experiment and machine learning approach represents a promising path forward toward developing highly efficient next-generation ORR electrocatalysts and, more generally, functional materials.

25 ENERGY STORAGE↗

Adiabatic quantum linear regression

Abstract A major challenge in machine learning is the computational expense of training these models. Model training can be viewed as a form of optimization used to fit a machine learning model to a set of data, which can take up significant amount of time on classical computers. Adiabatic quantum computers have been shown to excel at solving optimization problems, and therefore, we believe, present a promising alternative to improve machine learning training times. In this paper, we present an adiabatic quantum computing approach for training a linear regression model. In order to do this, we formulate the regression problem as a quadratic unconstrained binary optimization (QUBO) problem. We analyze our quantum approach theoretically, test it on the D-Wave adiabatic quantum computer and compare its performance to a classical approach that uses the Scikit-learn library in Python. Our analysis shows that the quantum approach attains up to $${2.8 \times }$$ 2.8 × speedup over the classical approach on larger datasets, and performs at par with the classical approach on the regression error metric. The quantum approach used the D-Wave 2000Q adiabatic quantum computer, whereas the classical approach used a desktop workstation with an 8-core Intel i9 processor. As such, the results obtained in this work must be interpreted within the context of the specific hardware and software implementations of these machines.

97 MATHEMATICS AND COMPUTING↗

Analyzing degradation data with a random effects spline regression model

This study proposes using a random effects spline regression model to analyze degradation data. Spline regression avoids having to specify a parametric function for the true degradation of an item. A distribution for the spline regression coefficients captures the variation of the true degradation curves from item to item. We illustrate the proposed methodology with a real example using a Bayesian approach. The Bayesian approach allows prediction of degradation of a population over time and estimation of reliability is easy to perform.

97 MATHEMATICS AND COMPUTING↗

Regression of exchangeable relational arrays

Relational arrays represent measures of association between pairs of actors, often in varied contexts or over time. Trade flows between countries, financial transactions between individuals, contact frequencies between school children in classrooms and dynamic protein-protein interactions are all examples of relational arrays. Elements of a relational array are often modelled as a linear function of observable covariates. Uncertainty estimates for regression coefficient estimators, and ideally the coefficient estimators themselves, must account for dependence between elements of the array, e.g., relations involving the same actor. Existing estimators of standard errors that recognize such relational dependence rely on estimating extremely complex, heterogeneous structure across actors. This paper develops a new class of parsimonious coefficient and standard error estimators for regressions of relational arrays. Here we leverage an exchangeability assumption to derive standard error estimators that pool information across actors, and are substantially more accurate than existing estimators in a variety of settings. This exchangeability assumption is pervasive in network and array models in the statistics literature, but not previously considered when adjusting for dependence in a regression setting with relational data. We demonstrate improvements in inference theoretically, via a simulation study, and by analysis of a dataset involving international trade.

97 MATHEMATICS AND COMPUTING↗

Generalized parton distributions from symbolic regression

AI/ML informed Symbolic Regression is the next stage of scientific modeling. We utilize a highly customizable symbolic regression package “PySR” to model the x and t dependence of the flavor isovector combination Hu-d(x, t, ) at = 0. These PySR models were trained on GPD results provided by both Lattice QCD and phenomenological sources GGL, GK, and VGG. We demonstrate, for the first time, the consistency and systematic convergence of Symbolic Regression by quantifying the disparate models through their Taylor expansion coefficients. In addition to PySR penalizing models with higher complexity and mean-squared error, we implement schemes that test specific physics hypotheses, including force-factorized x and t dependence and Regge behavior in PySR GPDs. We show that PySR can identify factorizing GPD sources based on their response to the Force-Factorized model. Here, knowing the precise behavior of the GPDs, and their uncertainties in a wide range in x and t, crucially impacts our ability to concretely and quantitatively predict hadronic spatial distributions and their derived quantities.

Dotson, Andrew [New Mexico State University, Las C↗

Inverse Regression for Extraction of Tumor Site from Cancer Pathology Reports

Pathology reports are the primary source of information for cancer diagnosis of millions of the cancer patients across the United States. Cancer registries label these reports every year. The coded labels incorporate pertinent information such as cancer location, behavior, and histology. This information when combined with clinical information, medical imaging and even genomic information have a great potential to fuel discoveries in cancer research. The coding process is manual and requires many human experts to label the large volume of pathology reports in a timely manner. In this study, we have developed a supervised inverse regression based auto-labeler to automate the task. The experiments were conducted on a set of 942 pathology reports with human expert labels as the ground truth. We observed that the inverse regression based auto-labeler consistently performed better than or comparable to the best performing state-of-the-art method. These results demonstrate the potential of inverse regression for reliable information extraction from the pathology reports.

Dubey, Abhishek↗