Search NASA⌕ Search

SEARCH · Search NASA

Results for “classifiers”

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 649 records · Page 36
All sourcesNASA NTRSDOE OSTI
DOE OSTI2016

Verification of Dose Distribution in Carbon Ion Radiation Therapy for Stage I Lung Cancer

Purpose: To evaluate robustness of dose distribution of carbon-ion radiation therapy (C-ion RT) in non-small cell lung cancer (NSCLC) and to identify factors affecting the dose distribution by simulated dose distribution. Methods and Materials: Eighty irradiation fields for delivery of C-ion RT were analyzed in 20 patients with stage I NSCLC. Computed tomography images were obtained twice before treatment initiation. Simulated dose distribution was reconstructed on computed tomography for confirmation under the same settings as actual treatment with respiratory gating and bony structure matching. Dose-volume histogram parameters, such as %D95 (percentage of D95 relative to the prescribed dose), were calculated. Patients with any field for which the %D95 of gross tumor volume (GTV) was below 90% were classified as unacceptable for treatment, and the optimal target margin for such cases was examined. Results: Five patients with a total of 8 fields (10% of total number of fields analyzed) were classified as unacceptable according to %D95 of GTV, although most patients showed no remarkable change in the dose-volume histogram parameters. Receiver operating characteristic curve analysis showed that tumor displacement and change in water-equivalent pathlength were significant predictive factors of unacceptable cases (P<.001 and P=.002, respectively). The main cause of degradation of the dose distribution was tumor displacement in 7 of the 8 unacceptable fields. A 6-mm planning target volume margin ensured a GTV %D95 of >90%, except in 1 extremely unacceptable field. Conclusions: According to this simulation analysis of C-ion RT for stage I NSCLC, a few fields were reported as unacceptable and required resetting of body position and reconfirmation. In addition, tumor displacement and change in water-equivalent pathlength (bone shift and/or chest wall thickness) were identified as factors influencing the robustness of dose distribution. Such uncertainties should be regarded in planning.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2017

Prognostic Relevance of Treatment Failure Patterns in Pediatric High-Grade Glioma: Is There a Role for a Revised Failure Classification System?

Purpose: We sought to investigate the pattern of treatment failure with respect to anatomic extent, radiation dose, and criteria for failure according to the Response Assessment in Neuro-Oncology (RANO). We evaluated the corresponding prognostic significance of these factors in patients with pediatric high-grade glioma (pHGG). Methods and Materials: Fifty-six patients with pHGG were enrolled in an institutional phase 1 to 2 prospective trial that included maximal safe resection and radiation therapy with concurrent and adjuvant erlotinib. The radiation therapy dose administered was 54 to 59.4 Gy at 1.8 Gy/d. Tumor progression was defined according to clinical symptoms and imaging features and was classified in relation to the original extent of the tumor, radiation prescription target volume coverage, and RANO criteria (RANOc). Results: With a median follow-up period of 90 months (range, 70-124 months), progression occurred in 48 patients (85.7%) while 8 (14.3%) were without progression. Central failure represented 42.6% of the total cohort, while in-field, marginal, and distant failures occurred in 7.4%, 9.3%, and 22.2%, respectively. Patients with biopsy or subtotal resection had increased rates of central failure and represented 14.81% and 16.67% of the total cohort, respectively. Tumor progression was classified as local, local plus distant, or distant. Among patients with local failure as a component of failure, 5 were considered to have marginal failure. Patients with frontal, temporal, and parietal disease had the highest rates of multifocal failure. A comparison between responses defined by RANOc demonstrated varied time to death (TTD) from progression. Conclusions: Pediatric high-grade glioma was shown to have high rates of central failure, particularly in cases with limited resection. Patients with central failure had a trend toward more prolonged TTD from failure relative to other failure patterns. The low marginal failure rates seen in this group suggest that less conservative radiation target margins may be possible. TTD from failure varied according to RANO type, suggesting that adult RANOc require modification before being applied to pHGG.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2017

Recent publications from the Alzheimer's Disease Neuroimaging Initiative: Reviewing progress toward improved AD clinical trials

Introduction The Alzheimer's Disease Neuroimaging Initiative (ADNI) has continued development and standardization of methodologies for biomarkers and has provided an increased depth and breadth of data available to qualified researchers. This review summarizes the over 400 publications using ADNI data during 2014 and 2015. Methods We used standard searches to find publications using ADNI data. Results (1) Structural and functional changes, including subtle changes to hippocampal shape and texture, atrophy in areas outside of hippocampus, and disruption to functional networks, are detectable in presymptomatic subjects before hippocampal atrophy; (2) In subjects with abnormal β‐amyloid deposition (Aβ+), biomarkers become abnormal in the order predicted by the amyloid cascade hypothesis; (3) Cognitive decline is more closely linked to tau than Aβ deposition; (4) Cerebrovascular risk factors may interact with Aβ to increase white‐matter (WM) abnormalities which may accelerate Alzheimer's disease (AD) progression in conjunction with tau abnormalities; (5) Different patterns of atrophy are associated with impairment of memory and executive function and may underlie psychiatric symptoms; (6) Structural, functional, and metabolic network connectivities are disrupted as AD progresses. Models of prion‐like spreading of Aβ pathology along WM tracts predict known patterns of cortical Aβ deposition and declines in glucose metabolism; (7) New AD risk and protective gene loci have been identified using biologically informed approaches; (8) Cognitively normal and mild cognitive impairment (MCI) subjects are heterogeneous and include groups typified not only by “classic” AD pathology but also by normal biomarkers, accelerated decline, and suspected non‐Alzheimer's pathology; (9) Selection of subjects at risk of imminent decline on the basis of one or more pathologies improves the power of clinical trials; (10) Sensitivity of cognitive outcome measures to early changes in cognition has been improved and surrogate outcome measures using longitudinal structural magnetic resonance imaging may further reduce clinical trial cost and duration; (11) Advances in machine learning techniques such as neural networks have improved diagnostic and prognostic accuracy especially in challenges involving MCI subjects; and (12) Network connectivity measures and genetic variants show promise in multimodal classification and some classifiers using single modalities are rivaling multimodal classifiers. Discussion Taken together, these studies fundamentally deepen our understanding of AD progression and its underlying genetic basis, which in turn informs and improves clinical trial design.

Weiner, Michael W.↗
DOE OSTI2018

Whole-genome sequencing and single nucleotide polymorphisms in multidrug-resistant clinical isolates of Mycobacterium tuberculosis from the Philippines

Thousands of cases of multidrug-resistant tuberculosis (TB) have been observed in the Philippines, but studies on the Mycobacterium tuberculosis (MTB) genotypes that underlie the observed drug resistance profiles are lacking. This study aimed to analyse the whole genomes of clinical MTB isolates representing various resistance profiles to identify single nucleotide polymorphisms (SNPs) in resistance-associated genes. The genomes of ten MTB isolates cultured from banked sputum sources were sequenced. Bioinformatics analysis consisted of assembly, annotation and SNP identification in genes reported to be associated with resistance to isoniazid (INH), rifampicin (RIF), ethambutol (ETH), streptomycin, pyrazinamide (PZA) and fluoroquinolones (FQs). The draft assemblies covered an average of 97.08% of the expected genome size. Seven of the ten isolates belonged to the Indo-Oceanic lineage/EA12-Manila clade. Two isolates were classified into the Euro-American lineage, whilst the pre-XDR (pre-extensively drug-resistant) isolate was classified under the East Asian/Beijing clade. The SNPs katG Ser315Thr, rpoB Ser450Leu and embB Met306Val were found in INH- (4/7), RIF- (3/6) and ETH-resistant (2/6) isolates, respectively, but not in susceptible isolates. Mutations in the inhA promoter and in the pncA and gyrA genes known to be involved in resistance to INH, PZA and FQs, respectively, were also identified. This study represents the first effort to investigate the whole genomes of Philippine clinical strains of MTB exhibiting various multidrug resistance profiles. Whole-genome data can provide valuable insights to the mechanistic and epidemiological qualities of TB in a high-burden setting such as the Philippines.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2017

Automating cell detection and classification in human brain fluorescent microscopy images using dictionary learning and sparse coding

Background Immunofluorescence (IF) plays a major role in quantifying protein expression in situ and understanding cell function. It is widely applied in assessing disease mechanisms and in drug discovery research. Automation of IF analysis can transform studies using experimental cell models. However, IF analysis of postmortem human tissue relies mostly on manual interaction, often subjected to low-throughput and prone to error, leading to low inter and intra-observer reproducibility. Human postmortem brain samples challenges neuroscientists because of the high level of autofluorescence caused by accumulation of lipofuscin pigment during aging, hindering systematic analyses. We propose a method for automating cell counting and classification in IF microscopy of human postmortem brains. Our algorithm speeds up the quantification task while improving reproducibility. New method Dictionary learning and sparse coding allow for constructing improved cell representations using IF images. These models are input for detection and segmentation methods. Classification occurs by means of color distances between cells and a learned set. Results Our method successfully detected and classified cells in 49 human brain images. We evaluated our results regarding true positive, false positive, false negative, precision, recall, false positive rate and F1 score metrics. We also measured user-experience and time saved compared to manual countings. Comparison with existing methods We compared our results to four open-access IF-based cell-counting tools available in the literature. Lastly, our method showed improved accuracy for all data samples. Conclusion The proposed method satisfactorily detects and classifies cells from human postmortem brain IF images, with potential to be generalized for applications in other counting tasks.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Quantifying the Influence of Size, Shape, and Density of Microplastics on Their Transport Modes: A Modeling Approach

Microplastics (MPs) pose significant risks to marine ecosystems and human health, necessitating accurate predictions of their distributions in aquatic environments for effective risk mitigation. However, understanding MP transport dynamics is challenging because of the inadequate representation of MP characteristics such as size, shape, and density in numerical models. Further, the accuracy of the MP vertical profiles in existing models has not been thoroughly validated. Thus, we developed an MP transport model within the Finite Volume Community Ocean Model framework (FVCOM-MP) by integrating MP characteristics. We validated FVCOM-MP against experimental and analytical data, focusing on various MP transport modes and transitions. FVCOM-MP successfully replicates MP profiles in different transport modes, including the bedload, surface-load, suspended-load, and mixed-load modes. Additionally, we introduce phase diagrams for classifying MP transport modes based on particle characteristics, enhancing our understanding of MP dynamics in aquatic systems. The transport modes for a number of real-world MP particles, including fishing line, plastic bag/bottle fragments, synthetic fibers, tire wear particles, polyvinyl chloride and expanded polystyrene pellets, were analyzed with these phase diagrams.

Microplastic transport, Settling velocity, Rising ↗
DOE OSTI2014

Orientation dependence of the dislocation microstructure in compressed body-centered cubic molybdenum

The orientation dependence of the deformation microstructure has been investigated in commercial pure molybdenum. After deformation, the dislocation boundaries of compressed molybdenum can be classified, similar to that in face-centered cubic metals, into three types: dislocation cells (Type 2), and extended planar boundaries parallel to (Type 1) or not parallel to (Type 3) a (110) trace. However, it shows a reciprocal relationship between face-centered cubic metals and body-centered cubic metals on the orientation dependence of the deformation microstructure. The higher the strain, the finer the microstructure is and the smaller the inclination angle between extended planar boundaries and the compression axis is. - Highlights: • A reciprocal relationship between FCC metals and BCC metals is confirmed. • The dislocation boundaries can be classified into three types in compressed Mo. • The dislocation characteristic of different dislocation boundaries is different.

36 MATERIALS SCIENCE↗
DOE OSTI2014

Microstructure characterization based on the type of deformed grains in cold-rolled, Cu-added, bake-hardenable steel

The electron backscatter diffraction technique has been used to characterize the microstructure of deformed grains in cold-rolled, Cu-added, bake-hardenable steel. A new scheme based on the kind and number of average orientations, as determined from a unique grain map of the deformed grains, was developed in order to classify deformed grains by type. The α-fiber components, γ-fiber components and random orientations, those which could not be assigned to either γ-fiber or α-fiber components, were used to define the average orientation of unique grains within individual deformed grains. The microstructures of deformed grains in as-rolled specimens were analyzed based on the Taylor factor, stored energy, and misorientation. The relative levels and distributions of the Taylor factor, the stored energy and the misorientation were examined in terms of the types of deformed grains. - Highlights: • We characterized the microstructure of Cu-added BH steel using EBSD. • A new scheme was developed in order to classify deformed grains by type. • Stored energy and misorientation are strongly dependent on the type of deformed grains. • Microstructure was examined in terms of the types of deformed grains.

36 MATERIALS SCIENCE↗
DOE OSTI2018

A study on spherical particles in Al65Cu20Fe15 alloy prepared by arc melting

Highlights: • Spherical particles and facets were found. • Spherical particles consist of quasicrystalline grains embedded in single crystal matrix. • Facets were found on the surface of spherical particles, which can be classified to three types. • A model for the formation of spherical particles is suggested. • Reasons for the formation of facets are discussed. - Abstract: Al-Cu-Fe alloys are important due to reports that stable icosahedral quasicrystalline phase with composition in the vicinity of Al{sub 65}Cu{sub 20}Fe{sub 15} can be prepared. However, it has been widely reported that the as-prepared alloy, very often by arc-melting, is porous, consisting of particles with different morphologies. Among these, one type of particles of a spherical shape is considered as pure cubic β phase in previous reports. In this research, this spherical particle was studied using a Scanning Electron Microscope, Energy Dispersive X-ray Spectroscopy, Transmission Electron Microscope, and Electron Diffraction. It was found that the particles are not single phase, consisting of icosahedral quasicrystalline grains embedded inside single crystal matrix of τ phase. Additionally, there are places where the τ phase appears to have out-most layer enriched in Cu. The surface of the particles is faceted and the facets can be classified to three types according to their detailed structures. A close examination and analysis led to the conclusion that these three types are parallel to the atomic planes of {1 1 0}, {1 1 1}, and {1 0 0}, respectively. A model for the spherical particle formation is suggested and the reasons for the formation of facets are discussed. This report is valuable in clarifying some discrepancies in previous reports, and in understanding the phase development in an Al-Cu-Fe alloy system.

36 MATERIALS SCIENCE↗
DOE OSTI2018

Crystallography of intergranular corrosion in sensitized austenitic stainless steel

Highlights: • Intergranular corrosion (IGC) in stainless steel was crystallographically discussed. • Grain boundaries (GBs) were classified based on the coincidence site lattice (CSL). • Influence of the Σ value on their IGC susceptibility had a wide range scatter. • IGC susceptibility was characterized by the Σ value and unit cell area of CSL GBs. - Abstract: This study deals with the susceptibility to intergranular corrosion (IGC) in type 304 austenitic stainless steel from a crystallographic viewpoint. An IGC test was conducted using oxalic acid and sensitized stainless steel, whose crystal orientation was analyzed by electron backscattered diffraction (EBSD). GBs were classified according to the misorientation of adjacent grains, and subclassified using the Σ value based on the coincidence site lattice (CSL) model. The width of corroded groove was measured for each GB category, and the effect of GB category on the susceptibility to IGC was examined. Then, the area of the unit cell of CSL boundaries was used to characterize the susceptibility to IGC of CSL boundaries. It was found that no IGC occurred in low-angle GBs with a misorientation of 15°, the width of corroded groove at each Σ boundary exhibited large scatter. The relationship between the width and unit cell area was characterized by a sigmoid curve, and the susceptibility to IGC was well described by the unit cell area.

36 MATERIALS SCIENCE↗
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

Diagnosis and prognosis of Alzheimer's disease using brain morphometry and white matter connectomes

Accurate, reliable prediction of risk for Alzheimer's disease (AD) is essential for early, disease-modifying therapeutics. Multimodal MRI, such as structural and diffusion MRI, is likely to contain complementary information of neurodegenerative processes in AD. Here we tested the utility of the multimodal MRI (T1-weighted structure and diffusion MRI), combined with high-throughput brain phenotyping—morphometry and structural connectomics—and machine learning, as a diagnostic tool for AD. We used, firstly, a clinical cohort at a dementia clinic (National Health Insurance Service-Ilsan Hospital [NHIS-IH]; N = 211; 110 AD, 64 mild cognitive impairment [MCI], and 37 cognitively normal with subjective memory complaints [SMC]) to test the diagnostic models; and, secondly, Alzheimer's Disease Neuroimaging Initiative (ADNI)-2 to test the generalizability. Our machine learning models trained on the morphometric and connectome estimates (number of features = 34,646) showed optimal classification accuracy (AD/SMC: 97% accuracy, MCI/SMC: 83% accuracy; AD/MCI: 97% accuracy) in NHIS-IH cohort, outperforming a benchmark model (FLAIR-based white matter hyperintensity volumes). In ADNI-2 data, the combined connectome and morphometry model showed similar or superior accuracies (AD/HC: 96%; MCI/HC: 70%; AD/MCI: 75% accuracy) compared with the CSF biomarker model (t-tau, p-tau, and Amyloid β, and ratios). In predicting MCI to AD progression in a smaller cohort of ADNI-2 (n = 60), the morphometry model showed similar performance with 69% accuracy compared with CSF biomarker model with 70% accuracy. Our comparisons of the classifiers trained on structural MRI, diffusion MRI, FLAIR, and CSF biomarkers showed the promising utility of the white matter structural connectomes in classifying AD and MCI in addition to the widely used structural MRI-based morphometry, when combined with machine learning.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2017

Multivariate analysis of gamma spectra to characterize used nuclear fuel

Abstract—The Multi-Isotope Process (MIP) Monitor provides an efficient approach to monitoring the process conditions in used nuclear fuel reprocessing facilities to support process verification and validation. The MIP Monitor applies multivariate analysis to gamma spectroscopy of reprocessing streams in order to detect small changes in the gamma spectrum, which may indicate changes in process conditions. This research extends the MIP Monitor by characterizing a used fuel sample after initial dissolution according to the type of reactor of origin (pressurized or boiling water reactor), initial enrichment, burn up, and cooling time. Simulated gamma spectra were used to develop and test three fuel characterization algorithms. The classification and estimation models employed are based on the partial least squares regression (PLS) algorithm. A PLS discriminate analysis model was developed which perfectly classified reactor type. Locally weighted PLS models were fitted on-the-fly to estimate continuous fuel characteristics. Burn up was predicted within 0.1% root mean squared percent error (RMSPE) and both cooling time and initial enrichment within approximately 2% RMSPE. This automated fuel characterization can be used to independently verify operator declarations of used fuel characteristics and inform the MIP Monitor anomaly detection routines at later stages of the fuel reprocessing stream to improve sensitivity to changes in operational parameters and material diversions.

Multivariate Analysis for Characterization of Used↗
DOE OSTI2018

Pulse discrimination with a Gaussian mixture model on an FPGA

A Gaussian Mixture Model (GMM) based machine learning algorithm has been applied to the problem of gamma/neutron pulse shape discrimination (PSD). The algorithm has been successfully implemented on a standard PC as well as a field programmable gate array (FPGA). We describe the GMM classifier and its implementation on these two different types of hardware. We compare the performance of the algorithm on these two platforms against each other, along with other standard techniques applied in PSD. Our results show that the FPGA-based GMM classifier outperforms the standard PSD techniques in terms of classification accuracy at low particle energy and executes more quickly than its CPU-based counterpart.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Noise signal identification in time projection chamber data using deep learning model

Deep learning has been employed in various scientific fields and has provided promising results. Here, in this study, a deep learning classifier was implemented to improve the quality of data obtained from a time projection chamber. Digital waveforms of the detected signals were classified into the following three categories: particles, noises, and particles piled up with noises. A simple 1-dimensional convolutional neural network was developed for the classification. The model demonstrated an excellent performance on the test dataset. Its practical performance was also examined using track images and particle identification plots by comparing the original and clean data without the noise signals. The comparison clearly showed that the deep learning model improved the quality of data. The current study presents an effective application of the deep learning model for the time projection chamber data.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Classification of events from α -induced reactions in the MUSIC detector via statistical and ML methods

The Multi-Sampling Ionization Chamber (MUSIC) detector is typically used to measure nuclear reaction cross sections relevant for nuclear astrophysics, fusion studies, and other applications. From the MUSIC data produced in one experiment scientists carefully extract an order of 10 3 events of interest from about 10 9 total events, where each event can be represented by an 18-dimensional vector. However, the standard data classification process is based on expert driven, manually intensive data analysis techniques that require several months to identify patterns and classify the relevant events from the collected data. Here, to address this issue, we present a method for the classification of events originating from specific α-induced reactions by combining statistical and machine learning methods that require significantly less input from the domain scientist, relative to the standard technique. Here, we applied the new method to two experimental data sets and compared our results with those obtained using traditional methods. With few exceptions, the number of events classified by our method agrees within ±20% with the results obtained using traditional methods. With the present method, which is the first of its kind for the MUSIC data, we have established the foundation for the automated extraction of physical events of interest from experiments using the MUSIC detector.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Machine learning framework for predicting uranium enrichments from M400 CZT gamma spectra

A machine learning framework was developed for predicting uranium enrichments from M400 CZT gamma spectra. This framework leverages the availability of a large amount of measured M400 gamma spectra and uses a recently updated version of Gamma Detector Response and Analysis Software (GADRAS) for gamma spectrum analysis and generation. It also leverages the existing machine learning modules in Python for gamma spectrum data processing, curation, model training, benchmarking, and optimization of the deep machine learning models. The framework is used to develop a deep learning model to analyze gamma spectra from a set of U 3 O 8 samples with enrichments ranging from 0.31 to 93.17% and UF 6 cylinders with enrichments ranging from 0.2 to 4.95%, and the model performance is tested using a set of measured spectra and the respective declared enrichment values. Results show that the model can correctly classify 99.35% of the U 3 O 8 sample enrichments, and can predict the samples’ enrichments within an average absolute error of 0.099% (in percentage points of enrichment). For the UF 6 cylinders, the average absolute error was approximately 0.03%, with an accuracy of 98% in classifying discrete enrichment values of UF 6 samples. Finally, the results also show that the model has performed significantly better in terms of predicting enrichments in UF 6 cylinders based on measured gamma spectra than the GEM code, with a standard deviation (of the relative errors) of 2.23% (compared with the 11.51% value for the GEM code) based on results from a set of test data.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

A machine learning framework for accurate and robust analysis of radiation detector pulses

The microscopic properties of atomic nuclei are used to study various scientific questions. They are essential for understanding the fundamental forces of nature and the chemical evolution of the universe. Detecting decay radiation from radioactive nuclei makes it possible to probe these fundamental nuclear properties. Detector waveform traces may contain additional information about the radiation. Generally, advanced signal processing techniques are needed to extract this additional information, often involving fitting the waveform with model response functions using non-linear least-squares optimization with second-order gradient methods. While this is a powerful technique, it is also computationally expensive, leading to slow processing time, which scales with the volume of data. To address this problem, we have developed a machine learning (ML) approach that infers the characteristics of traces from a model detector response function. In particular, we are interested in classifying whether a single recorded trace consists of one or two pulse constituents and estimating the pulse parameters. Furthermore, our proposed ML method can precisely extract the pulses’ parameters, such as energy and timing information, and accurately classify the pulse multiplicity of a trace. Unlike non-learning-based approaches, our ML approach uses neural networks that are significantly faster at inference, as they do not require any optimization during this stage.

Curve fitting↗