Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “categorical data”

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

Countering Weapons of Mass Destruction Office (CWMD) Data Categorization Study: Chemical, Biological, Radiological, and Nuclear (CBRN) Detection Device Data

Pacific Northwest National Laboratory (PNNL) seeks to address critical questions related to chemical, biological, radiological, and nuclear (CBRN) detection devices. This research aims to enhance the security and understanding of these devices by investigating various aspects of their identification, communication, and functionality. The primary focus is on network security, malware detection, device identification, and intelligence gathering. CBRN data can be categorized in various ways depending on the purpose of CBRN detection devices and the specific context of the applications for analysis. Criteria that can be used to assist in this effort include but are not limited to data type, data protocol, source/destination, application, time, security, and content. This study will inform additional paths for data classification, data profiling, data mapping, and data modeling. This will help the Countering Weapons of Mass Destruction Office (CWMD) better understand their data and make informed decisions based on the insights gained from this study and their application. The CBRN Data Categorization study will include the identification of 5–10 different CBRN detection devices with unique characteristics for assessing and analyzing the data that is being produced by and transmitted from these devices.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Optimal decision trees for categorical data via integer programming

Decision trees have been a very popular class of predictive models for decades due to their interpretability and good performance on categorical features. However, they are not always robust and tend to overfit the data. Additionally, if allowed to grow large, they lose interpretability. In this paper, we present a mixed integer programming formulation to construct optimal decision trees of a prespecified size. We take the special structure of categorical features into account and allow combinatorial decisions (based on subsets of values of features) at each node. Our approach can also handle numerical features via thresholding. Here we show that very good accuracy can be achieved with small trees using moderately-sized training sets. The optimization problems we solve are tractable with modern solvers.

97 MATHEMATICS AND COMPUTING↗

Standardization of Borehole Data to Support Vadose Zone Flow and Transport Modeling

Numerical representation of the geologic framework and its hydrologic and geochemical properties is an integral part of all vadose zone flow and transport modeling. Historically, the geologic framework and the physical distribution of flow and transport properties have been represented by simple homogeneous and horizontally stratified hydrogeologic units. To capture more of the heterogeneity, small-scale variability, and uncertainty within a model, the physical and geochemical parameters may be represented by probability density functions loosely correlated to individual hydrogeologic units. As computer-processing capabilities have become more advanced, there has been more emphasis on improving spatial resolution and quantifying uncertainty in key model parameters. One of the more popular approaches has focused on geostatistical simulation of the flow and transport properties themselves, with little regard to the geologic strata and sedimentary sequences. However, newer approaches are focusing more on geostatistical simulation of the sequence-stratigraphic relations of lithofacies and the geostatistical distributions of flow and transport properties within those facies. These approaches require more rigorous quantitative treatment of geologic data than are normally supported by the mostly qualitative nature of borehole geologic information. Thus at the Hanford Site, efforts are being made to systematize borehole geologic data to be used in a more quantitative way to define the spatial distribution of flow and transport properties in support of vadose flow and transport simulations. New detailed procedures translate qualitative descriptive information into categorical data, and translate inconsistent quantitative and semi-quantitative data into common parametric data sets. A geologic data management system is being developed to manage and integrate these new interpreted categorical data sets with other existing databases to support synergistic analysis and to improve numerical representation of the geologic architecture.

borehole data↗

Carbon Storage Technical Viability Approach (CS TVA) Database

The Carbon Storage Technical Viability Approach (CS TVA) database was developed to support the implementation of the CS TVA Matrix to a national data availability assessment for technically viable carbon storage. This database leverages the efforts of multiple adjacent and overlapping databases by non-redundantly combining the databases into a single database along with additionally providing tags facilitating the CS TVA. The non-redundant aspect of the database permits an accurate assessment of the concentration of available data, aiding in spatial and categorical data gaps analysis relative to the individual CS TVA Matrix Components. Version 2.0 of the database is an expansion of Version 1.0. Version 2.0 was created to include additional data gathered to fill gaps in the existing data set. Downloading the CS TVA v2.0 database will result in two separate databases, the version 1.0 original .gdb, and a second addendum .gdb with the new data gathered, together these two databases make up v2.0. Please see the ReadMe file below for full details, metadata information, use disclaimer, and attributions.

Coal↗

Visually Exploring Worldwide Incidents Tracking System Data

This paper presents refinements of an existing analytic tool, Juxter, which was developed for the visualization of multi-dimensional categorical data, and explores its application to support exploration and interaction with open source Worldwide Incidents Tracking System (WITS) data. The volume and complexity of data available on terrorism makes it hard to analyze. Information systems that can efficiently and effectively collect, access, analyze, and report terrorist incidents can help in further studies focused on preventing, detecting, and responding to terrorist attacks. Existing interfaces to the WITS data support advanced search capabilities, and geolocation but lack functionality for identifying patterns and trends. To better support efficient browsing we have refined Juxter’s existing capabilities for filtering, selecting, and sorting elements and categories within the visualization.

99 GENERAL AND MISCELLANEOUS↗

A Reference Based Analysis Framework for Analyzing System Call Traces

Reference based analysis (RBA) is a novel data mining tool for exploring a test data set with respect to a reference data set. The power of RBA lies in it ability to transform any complex data type, such as symbolic sequences and multi-variate categorical data instances, into a multivariate continuous representation. The transformed representation not only allows visualization of the complex data, which cannot be otherwise visualized in its original form, but also allows enhanced anomaly detection in the transformed feature space. We demonstrate the application of the RBA framework in analyzing system call traces and show how the transformation results in improved intrusion detection performance over state of art data mining based intrusion detection methods developed for system call traces.

99 GENERAL AND MISCELLANEOUS↗

Power generation forecasting for solar plants based on Dynamic Bayesian networks by fusing multi-source information

A Dynamic Bayesian network (DBN) model for solar power generation forecasting in solar plants is proposed in this paper. The key idea is to fuse sensor data, operational indicators, meteorological data, lagged output power information, and model errors for more accurate short-term (e.g., hours) and mid-term (e.g., days to weeks) power generation forecasting. The proposed DBN augments automated data-driven structure learning with expert knowledge encoding using continuous and categorical data given constraints to represent causal relationships within a solar inverter system. Additionally, an error compensation mechanism is proposed to capture temporal fluctuation. The effectiveness of the DBN on solar power generation forecasting was evaluated by rolling window analysis with one-year testing data collected from a local solar plant. The proposed DBN is compared with four state-of-art methods including support-vector regression (SVR), k-nearest neighbors (kNN), artificial neural network (ANN), and long short-term memory (LSTM) models. The result show that the proposed DBN achieves better accuracy in general, and it is not as data-hungry as some neural network-based models. The proposed DBN is also shown to have robust and consistent forecasting power with different forecasting horizons. The accuracy is 92% - 95% from one hour to one week ahead forecasting.

14 SOLAR ENERGY↗

Machine Learning–Based Condition Monitoring of a Circulating Water System of a Canadian Nuclear Plant

With the need to maintain long-term reliable energy using nuclear power plants, there is an underlying demand to ensure that the maintenance of plant components and systems is also done in an efficient and cost-effective manner. One way to achieve this is by moving from time-based maintenance to condition-based maintenance. The research presented in this paper focuses on applying statistical and machine-learning-based methods to capture anomalies within data for fault detection to further develop into condition monitoring. This paper focuses on system data for a circulating water system (CWS) of a pressurized heavy-water reactor for detecting anomalies. The different methodologies used for detecting and capturing anomalies in the CWS data are matrix profile, density-based spatial clustering of applications with noise (DBSCAN), and support vector machines (SVMs). Matrix profile and DBSCAN are used to distinguish between normal data and anomalous data. This paper presents a hybrid method using DBSCAN and SVM when a portion of the data is used for DBSCAN to generate clusters. This portion of data is then used to train the SVM along with the clusters generated by DBSCAN as output. SVM is then tested on unseen data as a predictive tool, which can work in real time to categorize data points as either normal or anomalous. This paper presents results that show the high accuracies of DBSCAN and SVM in capturing anomalies within the data for a CWS for fault detection. Thus, the maintenance plan would be focused on component condition rather than a time-based schedule by switching to an automated system to identify and predict faults within a CWS.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Data Mining in Multi-Dimensional Functional Data for Manufacturing Fault Diagnosis

Multi-dimensional functional data, such as time series data and images from manufacturing processes, have been used for fault detection and quality improvement in many engineering applications such as automobile manufacturing, semiconductor manufacturing, and nano-machining systems. Extracting interesting and useful features from multi-dimensional functional data for manufacturing fault diagnosis is more difficult than extracting the corresponding patterns from traditional numeric and categorical data due to the complexity of functional data types, high correlation, and nonstationary nature of the data. This chapter discusses accomplishments and research issues of multi-dimensional functional data mining in the following areas: dimensionality reduction for functional data, multi-scale fault diagnosis, misalignment prediction of rotating machinery, and agricultural product inspection based on hyperspectral image analysis.

42 ENGINEERING↗

A comparison of building system parameters between affordable and market-rate housing in New York City

Low-income households in the United States experience higher than average energy burdens (defined as the proportion of household income spent on energy utilities), and many of these households struggle to simultaneously pay for rent, energy, and basic household necessities. The analysis presented here in this study examines whether the underlying characteristics of buildings and their energy systems could contribute to this disparity for affordable housing residents in New York City. It combines an energy audit dataset of 7,328 multifamily buildings with a database of properties receiving local, state, or federal housing subsidies. The results of this analysis indicate that the building-level installed equipment in large (greater than 50,000 square feet) affordable housing buildings in New York City is more efficient than that in market-rate buildings, but this trend largely disappears when considering overall building characteristics, such as location, size, or age. Significant differences in the types of systems installed in affordable and market-rate housing are also observed, as well as the types of energy efficiency recommendations made by energy auditors. However, these latter data were not normalized by building system characteristics, as that analysis is much more difficult to interpret for categorical data such as heating system type. These findings indicate that retrofit policies and building performance standards focused on affordable housing will likely need to account for underlying differences in building characteristics between affordable and market-rate housing to achieve intended impacts.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Medical Device Recalls in Radiation Oncology: Analysis of US Food and Drug Administration Data, 2002-2015

Purpose: To analyze all recalls involving radiation oncology devices (RODs) from the US Food and Drug Administration (FDA)'s recall database, comparing these with non–radiation oncology device recalls to identify discipline-specific trends that may inform improvements in device safety. Methods and Materials: Recall data on RODs from 2002 to 2015 were sorted into 4 product categories (external beam, brachytherapy, planning systems, and simulation systems). Outcomes included determined cause of recall, recall class (severity), quantity in commerce, time until recall termination (date FDA determines recall is complete), and time since 510(k) approval. Descriptive statistics were performed with linear regression of time-series data. Results for RODs were compared with those for other devices by Pearson χ{sup 2} test for categorical data and 2-sample Kolmogorov-Smirnov test for distributions. Results: There were 502 ROD recalls and 9534 other class II device recalls during 2002 to 2015. Most recalls were for external beam devices (66.7%) and planning systems (22.9%), and recall events peaked in 2011. Radiation oncology devices differed significantly from other devices in all recall outcomes (P≤.04). Recall cause was commonly software related (49% vs 10% for other devices). Recall severity was more often moderate among RODs (97.6% vs 87.2%) instead of severe (0.2% vs 4.4%; P<.001). Time from 510(k) market approval to recall was shorter among RODs (P<.001) and progressively shortened over time. Radiation oncology devices had fewer recalled devices in commerce than other devices (P<.001). Conclusions: Compared with other class II devices, RODs experience recalls sooner after market approval and are trending sooner still. Most of these recalls were moderate in severity, and software issues are prevalent. Comprehensive analysis of recall data can identify areas for device improvement, such as better system design among RODs.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Adverse Events Involving Radiation Oncology Medical Devices: Comprehensive Analysis of US Food and Drug Administration Data, 1991 to 2015

Purpose: Radiation oncology relies on rapidly evolving technology and highly complex processes. The US Food and Drug Administration collects reports of adverse events related to medical devices. We sought to characterize all events involving radiation oncology devices (RODs) from the US Food and Drug Administration's postmarket surveillance Manufacturer and User Facility Device Experience (MAUDE) database, comparing these with non–radiation oncology devices. Methods and Materials: MAUDE data on RODs from 1991 to 2015 were sorted into 4 product categories (external beam, brachytherapy, planning systems, and simulation systems) and 5 device problem categories (software, mechanical, electrical, user error, and dose delivery impact). Outcomes included whether the device was evaluated by the manufacturer, adverse event type, remedial action, problem code, device age, and time since 510(k) approval. Descriptive statistics were performed with linear regression of time-series data. Results for RODs were compared with those for other devices by the Pearson χ{sup 2} test for categorical data and 2-sample Kolmogorov-Smirnov test for distributions. Results: There were 4234 ROD and 4,985,698 other device adverse event reports. Adverse event reports increased over time, and events involving RODs peaked in 2011. Most ROD reports involved external beam therapy (50.8%), followed by brachytherapy (24.9%) and treatment planning systems (21.6%). The top problem types were software (30.4%), mechanical (20.9%), and user error (20.4%). RODs differed significantly from other devices in each outcome (P<.001). RODs were more likely to be evaluated by the manufacturer after an event (46.9% vs 33.0%) but less likely to be recalled (10.5% vs 37.9%) (P<.001). Device age and time since 510(k) approval were shorter among RODs (P<.001). Conclusions: Compared with other devices, RODs may experience adverse events sooner after manufacture and market approval. Close postmarket surveillance, improved software design, and manufacturer–user training may help mitigate these events.

07 ISOTOPE AND RADIATION SOURCES↗

Early Experience with Out-of-Core Applications on the Cray XMT

This paper describes early experience with a preproduction Cray XMT system that implements a scalable shared memory architecture with hardware support for multithreading. Unlike its predecessor, the Cray MTA-2 that had very limited I/O capability, the Cray XMT offers Lustre, a scalable high-performance parallel filesystem. Therefore it enables development of out-of-core applications that can deal with very large data sets that otherwise would not fit the system main memory. Our application performs statistically-based anomaly detection for categorical data that can be used for Internet traffic analysis. Our results indicate that the preproduction version of the machine is able to achieve good performance and scalability for the in-and out-of-core versions of the example application.

97 MATHEMATICS AND COMPUTING↗

CTGAN-TVAE

SAND2026-18914O CTGAN-TVAE (Conditional Tabular Generative Adversarial Networks-Tabular Variational Autoencoders) generates extensive sets of variable generation data through a hybrid framework. It enhances latent space representation by combining TVAE's robust feature-embedding with CTGAN's ability to condition categorical variables such as time. CTGAN-TVAE employs a fully connected neural network within a conditional generative adversarial network framework to manage continuous and categorical data effectively, capturing complex feature interactions without needing sequential modeling. This was developed as part of NNSA-MSIPP: Minority Serving Institution Partnership Program, Grant Number DE-NA0004016. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy's National Nuclear Security Administration under contract DE-NA0003525.

Newlun, Cody [Sandia National Lab. (SNL-CA), Liver↗

Enhancing Privacy in Participatory Sensing Applications with Multidimensional Data

Participatory sensing applications rely on individuals to share personal data to produce aggregated models and knowledge. In this setting, privacy concerns can discourage widespread adoption of new applications. We present a privacy-preserving participatory sensing scheme based on negative surveys for both continuous and multivariate categorical data. Without relying on encryption, our algorithms enhance the privacy of sensed data in an energy and computation efficient manner. Simulations and implementation on Android smart phones illustrate how multidimensional data can be aggregated in a useful and privacy-enhancing manner.

Forrest, Stephanie↗

Search for an eV-Scale Sterile Neutrino Using Improved High-Energy νμ Event Reconstruction in IceCube

This Letter presents the result of a 3+1 sterile neutrino search using 10.7 yr of IceCube data. We analyze atmospheric muon neutrinos that traverse the Earth with energies ranging from 0.5 to 100 TeV, incorporating significant improvements in modeling neutrino flux and detector response compared to earlier studies. Notably, for the first time, we categorize data into starting and throughgoing events, distinguishing neutrino interactions with vertices inside or outside the instrumented volume, to improve energy resolution. The best-fit point for a 3+1 model is found to be at sin^{2}(2θ_{24})=0.16 and Δm_{41}^{2}=3.5 eV^{2}, which agrees with previous iterations of this Letter. The result is consistent with the null hypothesis of no sterile neutrinos with a p value of 3.1%.

Neutrino detection↗