Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “false negative analysis”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

A Data-driven Approach for Predicting Nepheline Crystallization in High-Level Waste Glasses

High-level waste (HLW) glasses with high aluminum content are prone to nepheline crystallization during the slow canister cooling that is experienced during large-scale production. Due to its detrimental effects on glass durability, nepheline precipitation must be avoided; however, developing robust, predictive models for nepheline crystallization behavior in HLW glasses is difficult due to their compositional complexity. Using overly conservative constraints to predict nepheline formation can limit the waste loading to lower than the achievable capacity. In this study, a robust data-driven model using five compositional features has been developed to predict nepheline formation. The analysis of the model and the data show that there is an overlap, instead of a distinct compositional boundary, between glasses that form and do not form nepheline. As a result, the model’s predictive accuracy is not the same throughout the feature space and instead is dependent on the location of the glass composition in the dimensionally reduced feature space.

Sargin, Irmak↗
DOE OSTI2020

Leveraging Fine-Grained Occupancy Estimation Patterns for Effective HVAC Control

As occupancy sensing technologies become mature, various occupancy sensors are increasingly deployed in commercial buildings for pervasive occupancy monitoring. These sensors provide occupant-count data, which contains rich spatiotemporal information about occupancy patterns. With long-term occupant-count data collected from a commercial building, we design three different predictive models that capture the occupancy dynamics and examine how a model predictive control of the HVAC system benefits from actual occupancy count prediction. Our analysis reveals that mispredictions of occupancy states, especially false positives and false negatives, may introduce inefficient control that leads to energy waste or user discomfort. To address this issue, we take a step further to design an adaptive model predictive controller that minimizes inefficient control actions according to misprediction types and distributions. A comprehensive evaluation is performed in OpenBuild and EnergyPlus simulators to study the effectiveness of the proposed end-to-end control strategy. The evaluation shows that the proposed solution reduces energy consumption by 29.5% while improving the average weighted occupants comfort by 86.7% in Predicted Mean Vote (PMV) over the fixed schedule strategy.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Ensuring statistical reproducibility of ocean model simulations in the age of hybrid computing

Novel high performance computing systems that feature hybrid architectures require large scale code refactoring to unravel underlying exploitable parallelism. Such redesign can often be accompanied with machine-precision changes as the order of computation cannot always be maintained. For chaotic systems like climate models, these round-off level differences can grow rapidly. Systematic errors may also manifest initially as machine-precision differences. Isolating genuine round off level differences from such errors remains a challenge. Here, we apply two-sample equality of distribution tests to evaluate statistical reproducibility of the ocean model component of US Department of Energy's Energy Exascale Earth System Model (E3SM). A 2-year control simulation ensemble is compared to a modified ensemble as a test case - after a known non-bit-for-bit change in a model component is introduced - to evaluate the null hypothesis that the two ensembles are statistically indistinguishable. To quantify the false negative rates of these tests, we conduct a formal power analysis using a targeted suite of short simulation ensembles. The ensemble suite contains several perturbed ensembles, each with a progressively different climate than the baseline ensemble - obtained by perturbing the magnitude of a single model tuning parameter, the Gent and McWilliams κ, in a controlled manner. The null hypothesis is evaluated for each of perturbed ensembles using these tests. The power analysis informs on the detection limits of the tests for given ensemble size allowing model developers to evaluate the impact of an introduced non-bit-for-bit change to the model.

Mahajan, Salil↗
DOE OSTI2025

Open Specy 1.0: Automated (Hyper)spectroscopy for Microplastics

Microplastic spectral analysis is one of the most time-consuming processes in studying microplastic pollution, often requiring days per sample. Researchers are transitioning to automated batch and hyperspectral image analysis techniques to enhance efficiency. Open Specy, initially aimed at manual single-spectrum analysis, has now integrated automated methods. This updated version, Open Specy 1.0, introduces several new features, including two algorithms for automated processing (smoothing and particle compression), an extensive library containing over 40,000 open-source Raman and FTIR spectra, and two machine learning classifiers (logistic regression and k medoids) developed from this library. Furthermore, it includes a revamped user interface, an R package, and a benchmark data set for testing future advancements in automated techniques. Researchers evaluated various configurations for hyperspectral smoothing, particle identification, compression, and splitting, to achieve combined recovery rates between 50 and 150% particle counts, identities, and sizes with a coefficient of variation (CV) of less than 40% (the accredited standard). Mean absorbance times the standard deviation provided a consistent particle identification. Hyperspectral smoothing led to a 96% combined recovery rate and reduced variability (CV = 38%) compared to the 86% recovery (CV = 83%) of nonsmoothed controls. Additionally, compressing spectra for particles was significantly faster (>3x) and showed similar accuracy but with reduced variability than processing each pixel individually. Key challenges persist in automating spectral analysis, particularly in refining particle splitting algorithms, and improving identification routines to minimize false positives and negatives. In conclusion, new methods in sample preparation for better stabilization and dispersion of particles could overcome some of these issues.

13 HYDRO ENERGY↗
DOE OSTI2022

Condition monitoring and anomaly detection in cyber-physical systems

The modern industrial environment is equipping myriads of smart manufacturing machines where the state of each device can be monitored continuously. Such monitoring can help identify possible future failures and develop a cost-effective maintenance plan. However, it is a daunting task to perform early detection with low false positives and negatives from the huge volume of collected data. This requires developing a holistic machine learning framework to address the issues in condition monitoring of high priority components and develop efficient techniques to detect anomalies that can detect and possibly localize the faulty components. This paper presents a comparative analysis of recent machine learning approaches for robust, cost-effective anomaly detection in cyber-physical systems. While detection has been extensively studied, very few researchers have analyzed the localization of the anomalies. We show that supervised learning outperforms unsupervised algorithms. For supervised cases, we achieve near-perfect accuracy of 98% (specifically for tree-based algorithms). In contrast, the best-case accuracy in the unsupervised cases was 63%—the area under the receiver operating characteristic curve (AUC) exhibits similar outcomes as an additional metric.

Marfo, William↗
DOE OSTI2021

DETECTING FIRE WITH MACHINE LEARNING-ENABLED VISUAL MONITORING FOR NUCLEAR POWER PLANT ENVIRONMENTS

Nuclear power plants are experiencing significant cost challenges to remain competitive with other energy-generation utilities. Unlike other industries, the cost of operation and maintenance activities is mostly attributed to workforce costs. To mitigate this, nuclear power plant stakeholders are increasingly interested in the development and deployment of machine learning methods to potentially automate or augment manually intensive tasks to reduce costs, especially for monitoring activities. One monitoring function that is visually demanding and that can occur frequently to meet the requirements of a fire protection program is visually monitoring an area for fire occurrence. Currently, fire watch activities consist of a worker physically stationed at a given location with the sole responsibility of observing a given area to ensure a fire is detected and mitigated promptly. This effort focused on the development and evaluation of a suitable deep convolutional neural network to classify individual video frames at a sub-second frequency for the occurrence of “fire” and “no fire” in varying industrial environments similar to nuclear power plants. It is believed that a trained neural network model could be integrated with existing facility video surveillance camera feeds to generate alerts when fire inferences occur in individual frames captured at sub-second temporal resolutions. Extensive effort was dedicated to identifying and curating suitable imagery training data representing varying environments and scene settings with and without flame features to maximize generalization in nuclear power plant environments. The data collection effort resulted in the aggregation of a large, labeled image library exceeding 12,000 images to support model training for diverse industrial environments. A deep neural network model incorporating parallel multi-scale capabilities was developed and trained to support accurate image-based detection of flame incidents of varying sizes and spectral feature properties within heterogeneous scenes. Analysis results show that the trained model can achieve high inference accuracy despite heterogeneous scene environments and components. Testing accuracy exceeded 95.0 percent with very low false positive and false negative inferences.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2020

Uranium Mass Attribute System (UMAS) Study: Evaluation of Options against the Arms Control Evaluation Criteria

In this FY19 study, a range of possible measurement systems for confirming a U-235 mass attribute were identified. The systems were reviewed for their applicability in a potential future arms control agreement, and a subset of the eight most plausible systems were selected for further evaluation against the Arms Control Evaluation Criteria (ACEC). The evaluation results were then used to identify a primary and secondary recommended measurement system for confirming a U-235 mass attribute on warheads, nuclear components of warheads, and/or materials as part of a hypothetical arms control agreement.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2026

Random forest models accurately classify synthetic opioids using high-dimensionality mass spectrometry datasets

Detection of novel threat agents presents several challenges, a principle one being the development of untargeted methods to screen an increasing number of threat chemicals whose exact structures are unknown. With the use of Machine Learning (ML) tools, we can guide the development of analytical methods for broad-spectrum detection of unbounded threat chemical families in complex mixtures. Toward this goal, we used nominal mass and high-resolution mass spectrometry data for hundreds of synthetic opioids and non-opioid compounds. We tested two ML techniques, logistic regression and random forest, to develop models towards a practical, implementable method for opioid detection. We found that of these tested ML methods, random forest models resulted in the highest validation accuracy (95+%) for both nominal mass and high-resolution classification of opioids versus non-opioids, with low false positive and false negative rates. The RF models were then used to successfully predict the classification of 10 compounds—five opioids and five non-opioids not part of the training and validation analysis. This application of ML is a critical step towards the development of field-deployable nominal mass spectrometers with ML-driven analyses for classification of emergent threats.

Chemistry↗
DOE OSTI2025

Random forest models accurately classify synthetic opioids using high-dimensionality mass spectrometry datasets

Detection of novel threat agents presents several challenges, a principle one being the development of untargeted methods to screen an increasing number of threat chemicals whose exact structures are unknown. With the use of Machine Learning (ML) tools, we can guide the development of analytical methods for broad-spectrum detection of unbounded threat chemical families in complex mixtures. Toward this goal, we used nominal mass and high-resolution mass spectrometry data for hundreds of synthetic opioids and non-opioid compounds. We tested two ML techniques, logistic regression and random forest, to develop models towards a practical, implementable method for opioid detection. We found that of these tested ML methods, random forest models resulted in the highest validation accuracy (95+%) for both nominal mass and high-resolution classification of opioids versus non-opioids, with low false positive and false negative rates. The RF models were then used to successfully predict the classification of 10 compounds—five opioids and five non-opioids not part of the training and validation analysis. This application of ML is a critical step towards the development of field-deployable nominal mass spectrometers with ML-driven analyses for classification of emergent threats.

Arasteh, Kourosh [Lawrence Livermore National Labo↗
DOE OSTI2023

Evaluation of Minimum Detectable Activities for Stack Sample Analyses

The Rad-NESHAP program takes samples at major point sources to track how much of select nuclides are being emitted out of the stack. Samples are taken at the site where the radiological operations are being performed. The samples are then sent to analytical laboratories for analysis to determine what nuclides exist in the sample. However, due to the sensitivity of the instruments, false positives are often reported. To reduce the number of false positives, the results reported from the analytical labs are compared to set detection limits. Anything below the set detection limit is considered part of the background while anything above the limit is considered a positive hit. Therefore, the detection limit must be set low enough that any false negatives do not result in a significant dose missed at the end of the year but high enough that there are not enough false positives to skew the annual dose being reported. All detection limits listed in this section for the analyses below were designed to meet the stated equivalent emissions rate and subsequent off-site doses. These minimum detectable activities (MDAs) were developed in the 1990s and documented in the memo cited for each analysis below. These limits and memos are all currently referenced in the Quality Assurance Project Plan (QAPP) for the Rad-NESHAP Compliance Task, which is being updated to a Project Implementation Plan (PIP) concurrently with this document. As part of this update process, the original MDAs defined in this section needed to be verified that they were still conservative and meet the off-site dose levels stated.

2019 MDA↗
DOE OSTI2022

Planning, design and logistics of a decision analysis study: The FBI/Ames study involving forensic firearms examiners

This paper describes design and logistical aspects of a decision analysis study to assess the performance of qualified firearms examiners working in accredited laboratories in the United States in terms of accuracy (error rate), repeatability, and reproducibility of decisions involving comparisons of fired bullets and cartridge cases. The purpose of the study was to validate current practice of the forensic discipline of firearms/toolmarks (F/T) examination. It elicited error rate data by counting the number of false positive and false negative conclusions. Preceded by the experimental design, decisions, and logistics described herein, testing was ultimately administered 173 qualified, practicing F/T examiners in public and private crime laboratories. The first round of testing evaluated accuracy, while two subsequent rounds evaluated repeatability and reproducibility of examiner conclusions. This project expands on previous studies by involving many F/T examiners in challenging comparisons and by executing the study in the recommended double-blind format.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2020

A robust benchmark for detection of germline large deletions and insertions

New technologies and analysis methods are enabling genomic structural variants (SVs) to be detected with ever-increasing accuracy, resolution and comprehensiveness. To help translate these methods to routine research and clinical practice, we developed a sequence-resolved benchmark set for identification of both false-negative and false-positive germline large insertions and deletions. To create this benchmark for a broadly consented son in a Personal Genome Project trio with broadly available cells and DNA, the Genome in a Bottle Consortium integrated 19 sequence-resolved variant calling methods from diverse technologies. The final benchmark set contains 12,745 isolated, sequence-resolved insertion (7,281) and deletion (5,464) calls ≥50 base pairs (bp). The Tier 1 benchmark regions, for which any extra calls are putative false positives, cover 2.51 Gbp and 5,262 insertions and 4,095 deletions supported by ≥1 diploid assembly. We demonstrate that the benchmark set reliably identifies false negatives and false positives in high-quality SV callsets from short-, linked- and long-read sequencing and optical mapping.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

A Metabolomics Assay to Diagnose Citrus Huanglongbing Disease and to Aid in Assessment of Treatments to Prevent or Cure Infection

Citrus greening disease, or Huanglongbing (HLB), has devastated citrus crops globally in recent years. The causal bacterium, ‘ Candidatus Liberibacter asiaticus’, presents a sampling issue for qPCR diagnostics and results in a high false negative rate. In this work, we compared six metabolomics assays to identify HLB-infected citrus trees from leaf tissue extracted from 30 control and 30 HLB-infected trees. A liquid chromatography-mass spectrometry-based assay was most accurate. A final partial least squares-discriminant analysis (PLS-DA) model was trained and validated on 690 leaf samples with corresponding qPCR measures from three citrus varieties (Rio Red grapefruit, Hamlin sweet orange, and Valencia sweet orange) from orchards in Florida and Texas. Trees were naturally infected with HLB transmitted by the insect vector Diaphorina citri. In a randomized validation set, the assay was 99.9% accurate to classify diseased from nondiseased samples. This model was applied to samples from trees receiving plant defense-inducer compounds or biological treatments to prevent or cure HLB infection. From two trials, HLB-related metabolite abundances and PLS-DA scores were tracked longitudinally and compared with those of control trees. We demonstrate how our assay can assess tree health and the efficacy of HLB treatments and conclude that no trialed treatment was efficacious.

Plant Sciences↗
DOE OSTI2021

A novel experimental system for the KDK measurement of the 40 K decay scheme relevant for rare event searches

Potassium-40 ( 40 K) is a long-lived, naturally occurring radioactive isotope. The decay products are prominent backgrounds for many rare event searches, including those involving NaI-based scintillators. 40 K also plays a role in geochronological dating techniques. The branching ratio of the electron capture directly to the ground state of argon-40 has never been measured, which can cause difficulty in interpretingcertain results or can lead to lack of precision depending on the field and analysis technique. Additionally, the KDK (Potassium (K) Decay (DK)) collaboration is measuring this decay. A composite method has a silicon drift detector with an enriched, thermally deposited 40 K source inside the Modular Total Absorption Spectrometer. This setup has been characterized in terms of energy calibration, gamma tagging efficiency, live time and false negatives and positives. A complementary, homogeneous, method is also discussed; it employs a KSr 2 I 5 :Eu scintillator as source and detector.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Data-driven modeling of dynamic occupant thermostat override behavior for demand response applications

Buildings consume nearly 40% of global energy and produce similar emissions. Whiletechnological advances address efficiency, occupant behavior causes energy use variations up to 300% between identical buildings. This gap between predicted and actual building performance impacts building design, operations, and grid demand management programs. Through analyses of smart thermostat data from 1,400 single-occupant homes, the researchdemonstrates that occupants respond to 8°F thermostat setpoint changes within a median of 15 minutes, while 2°F changes trigger responses within a median of 30 minutes. This highlights an understudied temporal relationship between thermostat setbacks and response time of occupant behaviors. Models of such behavior dynamics are required to incorporate occupant impacts into building performance simulation. A key contribution of this dissertation is the Thermal Frustration Theory (TFT), which positsthat thermal discomfort driven behaviors are caused by the time-accumulation of discomfort, not simply a temperature deviation threshold or a delay from an initiating event. Using a dataset of 634 thermostats, each with 25+ manual setpoint changes, a comparative analysis of TFT and comfort zone and a delayed response theories demonstrated that personalized TFT models better predict when manual setpoint change occur. This was measured by the area under the curve statistical measure (AUC); all three models perform similarly by a Matthews Correlation Coefficient measure. Higher AUC performance is especially important for modeling occupant behavior in demand response programs where false negatives of rare occupant interactions could adversely affect grid stability. EnergyPlus based simulations were conducted with TFT-derived occupant models, demonstrating the ability to identify parameters of known TFT models from only data observable with smart thermostats, even under the presence of noise from routine overrides. Overall, the dissertation highlights that thermostat interactions are neither static,instantaneous, nor driven solely by the environment. Instead, temporal accumulation of discomfort and routine-based behavior play important roles. The methodology and results offer a pathway towards more accurate modeling of human-building interactions for policy assessment, building design, and demand response programs.

Sharma, Kunind [Northeastern University] (ORCID:00↗
DOE OSTI2020

Deep Learning for Automated Identification of Eels in Sonar Data

Freshwater eels, such as the American eel (Anguilla rostrata) present numerous challenges related to safe downstream fish passage at hydroelectric facilities. One of those challenges is effective monitoring of their abundance, movements, and behavior to facilitate design and operation of eel protection and passage facilities. A previous EPRI study documented the ability of human analysts to reliably identify American eels in data obtained with a 1100/1800 kHz, multibeam sonar. This report describes a project to develop deep learning (a subset of artificial intelligence) tools to automate the time-consuming, subjective process of eel identification in multibeam sonar data. The project exploited new data collected in the laboratory and the existing data from the prior EPRI field study to develop and test deep learning and other data analytic tools, including wavelet filtering, differencing for static object removal, and convolutional neural network analysis. The analysis of the laboratory data demonstrated feasibility of the approach, revealed object characteristics observed with the sonar that distinguish eels from similarly sized and shaped acoustic targets, and provided additional data for algorithm selection and training. Deep learning algorithms trained and tested on the laboratory data alone achieved accuracy rates of greater than 98% when classifying acoustic images of eels and similar-sized neutrally buoyant sticks. The algorithm trained and tested on the pre-existing field data alone, and yielded classification accuracy of 9.3% false positives and 13.3% false negatives when distinguishing between eels and sticks/PVC pipes based on video clips (i.e., multiple, consecutive images). This performance is comparable to the classification accuracy achieved by human analysts in the prior study. The deep learning algorithm trained on a combination of video clips obtained in the laboratory and the field and tested on video clips from the field, was able to distinguish eels from sticks and PVC pipes (a river debris analog) of similar size with 100% accuracy. Outreach to the hardware, software, and end-user communities early in the project helped to identify needs and specify the application space. Outreach to those communities at the end of the project communicated project results and opportunities for further development. The project achieved proof of concept for automated identification of eel in multibeam sonar data. Future work should focus on acquisition of additional data for more robust algorithm training and testing; modification of the software tools to accommodate multiple acoustic targets in the acoustic field at a given time; identification of additional object classes; incorporation of motion in the object identification and classification algorithms; operationalizing the software tools, including integration with other existing sonar data analysis tools; and partnering with hardware and software providers for distribution of the software tools with their commercial products.

13 HYDRO ENERGY↗
DOE OSTI2025

Jensen–Shannon divergence based novel loss functions for Bayesian neural networks

Bayesian neural networks (BNNs) are state-of-the-art machine learning methods that can naturally regularize and systematically quantify uncertainties using their stochastic parameters. Kullback–Leibler (KL) divergence-based variational inference used in BNNs suffer from unstable optimization and challenges in approximating light-tailed posteriors due to the unbounded nature of the KL divergence. To resolve these issues, we formulate a novel loss function for BNNs based on a new modification to the generalized Jensen–Shannon (JS) divergence, which is bounded. In addition, we propose a Geometric JS divergence-based loss, which is computationally efficient since it can be evaluated analytically. We found that the JS divergence-based variational inference is intractable, and hence employed a constrained optimization framework to formulate these losses. Our theoretical analysis and empirical experiments on multiple regression and classification data sets suggest that the proposed losses perform better than the KL divergence-based loss, especially when the data sets are noisy or biased. Specifically, there are approximately 5% and 8% improvements in accuracy for a noise-added CIFAR-10 dataset and a regression dataset, respectively. There is about 13% reduction in false negative predictions of a biased histopathology dataset. Additionally, we quantify and compare the uncertainty metrics for the regression and classification tasks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Neural Network Approaches for Mobile Spectroscopic Gamma-Ray Source Detection

Artificial neural networks (ANNs) for performing spectroscopic gamma-ray source identification have been previously introduced, primarily for applications in controlled laboratory settings. To understand the utility of these methods in scenarios and environments more relevant to nuclear safety and security, this work examines the use of ANNs for mobile detection, which involves highly variable gamma-ray background, low signal-to-noise ratio measurements, and low false alarm rates. Simulated data from a 2” × 4” × 16” NaI(Tl) detector are used in this work for demonstrating these concepts, and the minimum detectable activity (MDA) is used as a performance metric in assessing model performance.In addition to examining simultaneous detection and identification, binary spectral anomaly detection using autoencoders is introduced in this work, and benchmarked using detection methods based on Non-negative Matrix Factorization (NMF) and Principal Component Analysis (PCA). On average, the autoencoder provides a 12% and 23% improvement over NMF- and PCA-based detection methods, respectively. Additionally, source identification using ANNs is extended to leverage temporal dynamics by means of recurrent neural networks, and these time-dependent models outperform their time-independent counterparts by 17% for the analysis examined here. The paper concludes with a discussion on tradeoffs between the ANN-based approaches and the benchmark methods examined here.

Bilton, Kyle J. (ORCID:0000000184553689)↗