Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “decision tree”

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 523 records · Page 29

Incremental Learning for Passive Microwave Precipitation Retrievals using Advanced Technology Microwave Sounder

Spaceborne passive microwave (PMW) radiometry is central to global precipitation monitoring, yet retrieval uncertainties remain substantial, particularly for cross-track sounders whose variable footprints and channel configurations are optimized for atmospheric temperature and moisture profiling rather than precipitation. Consequently, existing operational products often exhibit angular-dependent biases, limited effective swath utilization, unrealistic rainfall probability distributions, and systematic misclassification of precipitation phase. These limitations are further compounded by the scarcity of globally accurate and representative precipitation observations, as training data from the Dual-frequency Precipitation Radar (DPR) and the Cloud Profiling Radar (CPR) are spatially sparse, lack uniform global coverage, and exhibit heterogeneous error characteristics across precipitation regimes. To address these challenges, this study presents a supervised retrieval algorithm that incrementally trains an ensemble of extreme gradient-boosted decision trees by augmenting base learners with pre-training on reanalysis data and post-training on coincident DPR and CPR observations matched with the Advanced Technology Microwave Sounder (ATMS). By transferring prior information from reanalysis to posterior constraints from radar observations and adopting a sequential detection–estimation strategy for precipitation phase and rate retrieval, the proposed approach yields retrievals across the full ATMS swath that are largely free from persistent deficiencies in current Global Precipitation Measurement (GPM) passive microwave operational products. In particular, the method resolves bimodal artifacts in rainfall retrievals and mitigates systematic high-latitude snowfall biases, including overestimation across the Arctic and underestimation across the Antarctic. Validation against independent Multi-Radar Multi-Sensor (MRMS) data over the Contiguous United States (CONUS) further demonstrates improved performance in precipitation phase detection and rate estimation relative to both reanalysis and current GPM PMW products.

Mahyar Garshasbi↗

Observation of single top-quark production with the CDF II experiment

We present the observation of electroweak single top-quark production using up to 3.2 fb{sup -1} of data collected by the CDF experiment. Lepton plus jets candidate events are classified by four parallel analysis techniques: one likelihood discriminant, one matrix-element discriminant, one decision-tree discriminant, and one neural-network discriminant. These outputs are combined with a super discriminant based on a neural-network analysis in order to improve the expected sensitivity. In conjunction with one neural-network discriminant using a complementary dataset of MET plus jets events with a veto on identified leptons we observe a signal consistent with the standard model but inconsistent with the background-only model by 5.0 standard deviations, with a median expected sensitivity in excess of 5.9 standard deviations.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Design, implementation and migration of security systems as an extreme project.

Decision Trees, algorithms, software code, risk management, reports, plans, drawings, change control, presentations, and analysis - all useful tools and efforts but time consuming, resource intensive, and potentially costly for projects that have absolute schedule and budget constraints. What are necessary and prudent efforts when a customer calls with a major security problem that needs to be fixed with a proven, off-the-approval-list, multi-layered integrated system with high visibility and limited funding and expires at the end of the Fiscal Year? Whether driven by budget cycles, safety, or by management decree, many such projects begin with generic scopes and funding allocated based on a rapid management 'guestimate.' Then a Project Manager (PM) is assigned a project with a predefined and potentially limited scope, compressed schedule, and potentially insufficient funding. The PM is tasked to rapidly and cost effectively coordinate a requirements-based design, implementation, test, and turnover of a fully operational system to the customer, all while the customer is operating and maintaining an existing security system. Many project management manuals call this an impossible project that should not be attempted. However, security is serious business and the reality is that rapid deployment of proven systems via an 'Extreme Project' is sometimes necessary. Extreme Projects can be wildly successful but require a dedicated team of security professionals lead by an experienced project manager using a highly-tailored and agile project management process with management support at all levels, all combined with significant interface with the customer. This paper does not advocate such projects or condone eliminating the valuable analysis and project management techniques. Indeed, having worked on a well-planned project provides the basis for experienced team members to complete Extreme Projects. This paper does, however, provide insight into what it takes for projects to be successfully implemented and accepted when completed under extreme conditions.

99 GENERAL AND MISCELLANEOUS↗

Design implementation and migration of security systems as an extreme project.

Decision Trees, algorithms, software code, risk management, reports, plans, drawings, change control, presentations, and analysis - all useful tools and efforts but time consuming, resource intensive, and potentially costly for projects that have absolute schedule and budget constraints. What are necessary and prudent efforts when a customer calls with a major security problem that needs to be fixed with a proven, off-the-approval-list, multi-layered integrated system with high visibility and limited funding and expires at the end of the Fiscal Year? Whether driven by budget cycles, safety, or by management decree, many such projects begin with generic scopes and funding allocated based on a rapid management 'guestimate.' Then a Project Manager (PM) is assigned a project with a predefined and potentially limited scope, compressed schedule, and potentially insufficient funding. The PM is tasked to rapidly and cost effectively coordinate a requirements-based design, implementation, test, and turnover of a fully operational system to the customer, all while the customer is operating and maintaining an existing security system. Many project management manuals call this an impossible project that should not be attempted. However, security is serious business and the reality is that rapid deployment of proven systems via an 'Extreme Project' is sometimes necessary. Extreme Projects can be wildly successful but require a dedicated team of security professionals lead by an experienced project manager using a highly-tailored and agile project management process with management support at all levels, all combined with significant interface with the customer. This paper does not advocate such projects or condone eliminating the valuable analysis and project management techniques. Indeed, having worked on a well-planned project provides the basis for experienced team members to complete Extreme Projects. This paper does, however, provide insight into what it takes for projects to be successfully implemented and accepted when completed under extreme conditions.

99 GENERAL AND MISCELLANEOUS↗

Error minimizing algorithms for nearest eighbor classifiers

Stack Filters define a large class of discrete nonlinear filter first introd uced in image and signal processing for noise removal. In recent years we have suggested their application to classification problems, and investigated their relationship to other types of discrete classifiers such as Decision Trees. In this paper we focus on a continuous domain version of Stack Filter Classifiers which we call Ordered Hypothesis Machines (OHM), and investigate their relationship to Nearest Neighbor classifiers. We show that OHM classifiers provide a novel framework in which to train Nearest Neighbor type classifiers by minimizing empirical error based loss functions. We use the framework to investigate a new cost sensitive loss function that allows us to train a Nearest Neighbor type classifier for low false alarm rate applications. We report results on both synthetic data and real-world image data.

97 MATHEMATICS AND COMPUTING↗

Bridging Human Reliability Analysis and Psychology, Part 1: The Psychological Literature Review for the IDHEAS Method

In response to Staff Requirements Memorandum (SRM) SRM-M061020, the U.S. Nuclear Regulatory Commission (NRC) is sponsoring work to update the technical basis underlying human reliability analysis (HRA) in an effort to improve the robustness of HRA. The ultimate goal of this work is to develop a hybrid of existing methods addressing limitations of current HRA models and in particular issues related to intra- and inter-method variabilities and results. This hybrid method is now known as the Integrated Decision-tree Human Event Analysis System (IDHEAS). Existing HRA methods have looked at elements of the psychological literature, but there has not previously been a systematic attempt to translate the complete span of cognition from perception to action into mechanisms that can inform HRA. Therefore, a first step of this effort was to perform a literature search of psychology, cognition, behavioral science, teamwork, and operating performance to incorporate current understanding of human performance in operating environments, thus affording an improved technical foundation for HRA. However, this literature review went one step further by mining the literature findings to establish causal relationships and explicit links between the different types of human failures, performance drivers and associated performance measures ultimately used for quantification. This is the first of two papers that detail the literature review (paper 1) and its product (paper 2). This paper describes the literature review and the high-level architecture used to organize the literature review, and the second paper (Whaley, Hendrickson, Boring, & Xing, these proceedings) describes the resultant cognitive framework.

99 GENERAL AND MISCELLANEOUS↗

Methods for heel retrieval for tanks C-101, C-102, and C-111 at the Hanford Site

The purpose of this paper is to evaluate the prospects of using bulk waste characteristics to determine the most appropriate heel retrieval technology. If the properties of hard to remove heels can be determined before bulk retrieval, then a heel retrieval technology can be selected before bulk retrieval is complete. This would save substantially on sampling costs and would allow the deployment of the heel retrieval technology immediately after bulk retrieval. The latter would also accelerate the heel removal schedule. A number of C-farm retrievals have been fully or partially completed at the time of this writing. Thus, there is already substantial information on the success of different technologies and the composition of the heels. There is also substantial information on the waste types in each tank based on historical records. Therefore, this study will correlate the performance of technologies used so far and compare them to the known waste types in the tanks. This will be used to estimate the performance of future C Farm heel retrievals. An initial decision tree is developed and employed on tanks C-101, C-102, and C 111. An assumption of this study is that no additional characterization information would be available, before or after retrieval. Note that collecting additional information would substantially increase the probability of success. Deploying some in-situ testing technologies, such as a water lance or an in-situ Raman probe, might substantially increase the probability of successfully selecting the process conditions without having to take samples from the tanks for laboratory analysis.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Image Change Detection via Ensemble Learning

The concept of geographic change detection is relevant in many areas. Changes in geography can reveal much information about a particular location. For example, analysis of changes in geography can identify regions of population growth, change in land use, and potential environmental disturbance. A common way to perform change detection is to use a simple method such as differencing to detect regions of change. Though these techniques are simple, often the application of these techniques is very limited. Recently, use of machine learning methods such as neural networks for change detection has been explored with great success. In this work, we explore the use of ensemble learning methodologies for detecting changes in bitemporal synthetic aperture radar (SAR) images. Ensemble learning uses a collection of weak machine learning classifiers to create a stronger classifier which has higher accuracy than the individual classifiers in the ensemble. The strength of the ensemble lies in the fact that the individual classifiers in the ensemble create a mixture of experts in which the final classification made by the ensemble classifier is calculated from the outputs of the individual classifiers. Our methodology leverages this aspect of ensemble learning by training collections of weak decision tree based classifiers to identify regions of change in SAR images collected of a region in the Staten Island, New York area during Hurricane Sandy. Preliminary studies show that the ensemble method has approximately 11.5% higher change detection accuracy than an individual classifier.

Martin, Benjamin W↗

IDHEAS – A NEW APPROACH FOR HUMAN RELIABILITY ANALYSIS

This paper describes a method, IDHEAS (Integrated Decision-Tree Human Event Analysis System) that has been developed jointly by the US NRC and EPRI as an improved approach to Human Reliability Analysis (HRA) that is based on an understanding of the cognitive mechanisms and performance influencing factors (PIFs) that affect operator responses. The paper describes the various elements of the method, namely the performance of a detailed cognitive task analysis that is documented in a crew response tree (CRT), and the development of the associated time-line to identify the critical tasks, i.e. those whose failure results in a human failure event (HFE), and an approach to quantification that is based on explanations of why the HFE might occur.

99 GENERAL AND MISCELLANEOUS↗

Apollo

Modern performance portability frameworks provide application developers with a flexible way to determine how to run application kernels, however, they provide no guidance as to the best configuration for a given kernel. Apollo provides a model-generation framework that, when integrated with the RAJA library, uses lightweight decision tree models to select the fastest execution configuration on a per-kernel basis

Beckingsal, David↗

Progress Towards a Neutral Current $\pi^0$ Cross Section Analysis in the NOvA Near Detector

The NOvA neutrino experiment is attempting to measure properties of neutrinos in order to figure out information about the universe. To detect the signal neutrino interactions, we must determine methods to identify and isolate background events. Research focused on a specific background interaction called a single prong neutral current $\pi^0$ interaction. To do this, a basic cuts based analysis was performed, followed by feeding data into a multi-variate analysis package using a boosted decision tree (BDT) algorithm. Using the BDT, a a new variable was generated which separates signal and background very efficiently. Further work must still be done in order to continue improving the performance of the BDT. This research is valuable to the field of studying neutrino cross sections as it is a background which will always be present in this type of analysis.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

MicroBooNE's Search for Photon-Like Low Energy Excess Under a Neutral Current $\Delta \to N_{\gamma}$ Hypothesis

MicroBooNE is a Liquid Argon Time Projection Chamber which has been taking neutrino data at Fermilab’s Booster Neutrino Beamline since October 2015. One of its primary goals is to investigate the Low Energy Excess of neutrino events observed by the MiniBooNE experiment, for which one candidate interpretation is neutrino neutral current (NC) resonant ∆ production with subsequent radiative decay. This is a standard model (SM) source of low energy single-photon events that has never been directly measured in neutrino scattering. If found to have a higher than SM-predicted rate it could be a sizable contribution to the Low Energy Excess. In MicroBooNE it would be identified with an event signature of one detached photon shower and some number of proton tracks associated with a reconstructed neutrino vertex. This poster will describe the analysis developed to search for NC ∆ radiative events in MicroBooNE, consisting of a Boosted Decision Tree based event selection wit h enhanced background reduction using a Semantic Segmentation Network to target the dominant NC π0 background.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Restricted Boltzmann Machines for galaxy morphology classification with a quantum annealer

We present the application of Restricted Boltzmann Machines (RBMs) to the task of astronomical image classification using a quantum annealer built by D-Wave Systems. Morphological analysis of galaxies provides critical information for studying their formation and evolution across cosmic time scales. We compress the images using principal component analysis to fit a representation on the quantum hardware. Then, we train RBMs with discriminative and generative algorithms, including contrastive divergence and hybrid generative-discriminative approaches. We compare these methods to Quantum Annealing (QA), Markov Chain Monte Carlo (MCMC) Gibbs Sampling, Simulated Annealing (SA) as well as machine learning algorithms like gradient boosted decision trees. We find that RBMs implemented on D-wave hardware perform well, and that they show some classification performance advantages on small datasets, but they don't offer a broadly strategic advantage for this task. During this exploration, we analyzed the steps required for Boltzmann sampling with the D-Wave 2000Q, including a study of temperature estimation, and examined the impact of qubit noise by comparing and contrasting the original D-Wave 2000Q to the lower-noise version recently made available. While these analyses ultimately had minimal impact on the performance of the RBMs, we include them for reference.

79 ASTRONOMY AND ASTROPHYSICS↗

Desktop Audits: Overview, Case Studies, Guidance

The Energy Independence and Security Act (EISA) of 2007 requires that federal agencies audit 25% of their 3.1 billion square feet of covered facilities each year. Several newer, advanced options such as monitoring-based commissioning, fault detection and diagnostics, and energy management systems can help support data collection and analysis to be used for EISA compliance. The Federal Energy Management Program's (FEMP’s) Audit Decision Tree, Audit Definitions, and FEMP Guidance can be used by Agencies to determine the best approaches to evaluate their facilities. FEMP continues to develop additional resources to support agencies in meeting EISA compliance. This presentation gives an overview of desktop audits, including case studies and guidance.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Case Study: Hybrid Carbon Conversion Using Low-Carbon Energy Sources in Coal-Producing States

The demand for more carbon efficient power sources and a decrease in natural gas prices has decreased the desire for coal power. This decrease in demand has led to massive job losses in coal mining regions over the past decade. The purpose of this project is to develop a hybrid energy system utilizing both a coal power plant and advanced reactor, which is competitive with natural gas by improving on profitability and decreasing carbon emissions. This report details the problem with a summary of the impact on the coal industry and the availability of renewable energy sources in the Appalachian region. Because of the geography of the region, variable renewable energy sources are not available without significant size and siting restrictions. However, biomass in the form of wood waste is abundant and can be used as a carbon neutral energy source. Combining biomass and coal processing, in addition to thermal power plants, can increase system profits and efficiency by providing peaking power and conversion opportunities for secondary markets. The electric load is based on publicly available demand data from Appalachian Power, which services the western Virginia and southern West Virginia in the Appalachian region. The demand information is combined by service, normalized, and scaled to an average demand of 1000 kW, which will be the basis for sizing the hybrid energy system. A traditional screening curve analysis for a coal plant and advanced reactor shows that the least cost design varies significantly based on the assumed discount rate and capital recovery period. An optimization program to size the design in TEAL based on the load curve gives 10 optimal designs, all with a negative resulting net present value (NPV) and a coal plant capacity of less than 15%. Including profits from selling captured carbon at a flat rate results in a positive NPV; however, the coal capacity factor only increases to about 40%. There are limitations with this optimization as well since the price of CO2 is likely to decrease as more is sold to the conversion market. The suggested design will combine coal power, an advanced reactor, and coal and biomass coprocessing to produce a variety of products that can be sold to the conversion market while increasing system efficiency. The analysis of conversion pathways for coal and biomass reveals that multiple options will need to be included in the analysis to produce the optimal system design. Three systems will be optimized and compared to determine the best design based on the figures of merit of total NPV and cost of carbon avoided. The first system will include a coal power plant and an advanced reactor that will sell electricity to the grid to meet demand and sell captured carbon to the conversion market. The second system adds a high-temperature steam electrolysis plant, which will utilize electricity during times of low demand to produce hydrogen and sell it to the conversion market. The third system adds biomass and coal processing with options for hydrocarbon oils, syngas to be produced for the conversion market, and electricity generation to power components within the system or provide peaking power. This analysis will be based on a new approach that combines traditional screening curve methods with a dispatch algorithm that optimizes the system based on the opportunity cost of different production options. The resulting optimization algorithm should provide results with less processing time than HERON’s decision tree method. The results from this analysis will determine an optimal design and reinforce the benefits of coal power when used in a hybrid energy system. The initial results show that the addition of a secondary market for carbon sales could result in a positive NPV and increases the capacity factor of the coal plant as compared to a design with only sales to the electricity market. The addition of more markets and additional coal consumption from biomass coprocessing could increase NPV further, replace carbon in other markets through the sale of biomass-derived hydrocarbons, and demonstrate the value of coal power technology.

01 COAL, LIGNITE, AND PEAT↗

An Intelligent System for Automatic Selection of DC-DC Converter Topology with Optimal Design

In this paper, we present an intelligent system that has the capabilities of automatically selecting topology classes and optimizing circuit parameters of DC-DC power converters for a given design specification. The system, Machine-Learning-enhanced Automated Circuit Configuration and Evaluation of Power Converters (ML-ACCEPT), uses a hybrid of machine learning technologies, decision tree inference, reinforcement learning and deep neural networks. The system gives high accurate recommendations of design topology classes and computationally efficient results in optimizing power efficiencies in power converter design.

Xue, Lincoln↗

Automatic DDoS Attack Detection on SDNs: Preprint

Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks pose a serious threat to computing networks - especially to critical systems within the U.S. electrical grid. As attack mechanisms have increased in complexity and variety, more sophisticated detection mechanisms have become necessary to ensure network security. This paper explores the use of artificial intelligence to automate the process of detection and mitigation of DoS and DDoS attacks within the framework of Software-Defined Networking (SDN), to a high degree. Machine learning algorithms are trained to recognize DoS and DDoS attacks and are deployed in real-time to mitigate malicious network traffic. The results show a well-tuned gradient-boosted decision tree detecting DoS and DDoS attacks, as well as initial successful mitigation of attacks within an SDN framework.

cyber detection↗

Simulation-Based Recovery Action Analysis Using the EMRALD Dynamic Risk Assessment Tool

Recovery human action is defined as the action that prevents deviant conditions from producing unwanted effects. Analyzing recovery actions has been a critical part in human reliability analysis (HRA). However, there are a couple of limitations to treating recovery actions using only the current HRA methods available. Representatively, the existing recovery analysis does not specifically consider recovery actions as they have occurred in actual nuclear power plants (NPPs). To handle the challenges in the existing recovery analyses, this study suggests a way to analyze recovery actions under a dynamic HRA method, the Procedure-based Risk Investigation MEthod-Human Reliability Analysis (PRIME-HRA) method. The PRIME-HRA method suggests a way on how to develop dynamic simulation models using dynamic risk assessment tools such as the Event Modeling Risk Assessment Using Linked Diagram (EMRALD) [1] and the Human Unimodel for Nuclear Technology to Enhance Reliability (HUNTER) [2]. EMRALD and HUNTER are the dynamic probabilistic risk assessment and HRA tools developed at Idaho National Laboratory. In this paper, differences on analyzing recovery actions in the Technique for Human Error-Rate Prediction (THERP), the Cause-Based Decision Tree (CBDT) and the Korean Standard HRA (K-HRA) and challenges of these approaches are introduced. How we have developed the PRIME-HRA is also introduced in this paper. Then, the proposed approach to analyzing recovery human actions in dynamic context is partially discussed with an example.

99 GENERAL AND MISCELLANEOUS↗