Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Feature Extraction”

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 793 records · Page 44
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

KG-Hub—building and exchanging biological knowledge graphs

Knowledge graphs (KGs) are a powerful approach for integrating heterogeneous data and making inferences in biology and many other domains, but a coherent solution for constructing, exchanging, and facilitating the downstream use of KGs is lacking. Here we present KG-Hub, a platform that enables standardized construction, exchange, and reuse of KGs. Features include a simple, modular extract–transform–load pattern for producing graphs compliant with Biolink Model (a high-level data model for standardizing biological data), easy integration of any OBO (Open Biological and Biomedical Ontologies) ontology, cached downloads of upstream data sources, versioned and automatically updated builds with stable URLs, web-browsable storage of KG artifacts on cloud infrastructure, and easy reuse of transformed subgraphs across projects. Current KG-Hub projects span use cases including COVID-19 research, drug repurposing, microbial–environmental interactions, and rare disease research. KG-Hub is equipped with tooling to easily analyze and manipulate KGs. KG-Hub is also tightly integrated with graph machine learning (ML) tools which allow automated graph ML, including node embeddings and training of models for link prediction and node classification.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Contrastive learning for robust representations of neutrino data

In neutrino physics, analyses often depend on large simulated datasets, making it essential for models to generalize effectively to real-world detector data. Contrastive learning, a well-established technique in deep learning, offers a promising solution to this challenge. By applying controlled data augmentations to simulated data, contrastive learning enables the extraction of robust and transferable features. This improves the ability of models trained on simulations to adapt to real experimental data distributions. In this paper, we investigate the application of contrastive learning methods in the context of neutrino physics. Through a combination of empirical evaluations and theoretical insights, we demonstrate how contrastive learning enhances model performance and adaptability. Additionally, we compare it to other domain adaptation techniques, highlighting the unique advantages of contrastive learning for this field. Published by the American Physical Society 2025

Wilkinson, Alex (ORCID:0000000253404506)↗
DOE OSTI2021

The effect of longer-range waviness on X-ray reflectivity measurements

A model for calculating the X-ray reflectivity (XRR) of surfaces to extract both roughness and waviness features is presented. Expressions of reflectivity intensity are derived as a function of root-mean-square (RMS) roughness σ, RMS waviness σ L , and the cut-off frequency between the features ω 0 . Experiments were conducted at the Advanced Light Source at Lawrence Berkeley National Laboratory, beamline 8.3.2, on BK7 glass manufactured with a multi-step polishing process to validate the model, and were compared with atomic force microscopy (AFM), Fizeau interferometry and surface profilometry measurements. Here, the parameter results and their deviations for XRR measurements were σ = 2.9 ± 0.2 nm and σ L = 14.6 ± 0.5 nm with a wavelength cut-off of 1/(18 ± 2) µm –1 , while the results from the AFM, Fizeau and profilometry measurements were σ AFM = 3.4 ± 0.4 nm, σ L,Fizeau = 21.6 nm, σ prof = 4.0 ± 0.1 nm, and σ L,prof = 21.4 ± 0.1 nm with cut-offs for the profilometry and Fizeau measurements limited to frequencies of (1/16) µm –1 to (1/4) mm –1 .

42 ENGINEERING↗
DOE OSTI2024

Localized Evaluation for Constructing Discrete Vector Fields

Topological abstractions offer a method to summarize the behavior of vector fields, but computing them robustly can be challenging due to numerical precision issues. One alternative is to represent the vector field using a discrete approach, which constructs a collection of pairs of simplices in the input mesh that satisfies criteria introduced by Forman's discrete Morse theory. While numerous approaches exist to compute pairs in the restricted case of the gradient of a scalar field, state-of-the-art algorithms for the general case of vector fields require expensive optimization procedures. This paper introduces a fast, novel approach for pairing simplices of two-dimensional, triangulated vector fields that do not vary in time. The key insight of our approach is that we can employ a local evaluation, inspired by the approach used to construct a discrete gradient field, where every simplex in a mesh is considered by no more than one of its vertices. Specifically, we observe that for any edge in the input mesh, we can uniquely assign an outward direction of flow. We can further expand this consistent notion of outward flow at each vertex, which corresponds to the concept of a downhill flow in the case of scalar fields. Working with outward flow enables a linear-time algorithm that processes the (outward) neighborhoods of each vertex one-by-one, similar to the approach used for scalar fields. Here, we couple our approach to constructing discrete vector fields with a method to extract, simplify, and visualize topological features. Empirical results on analytic and simulation data demonstrate drastic improvements in running time, produce features similar to the current state-of-the-art, and show the application of simplification to large, complex flows.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Scalable Computation of Topological Abstractions for Scalar Data

Topological data analysis has become an important tool for large scale scalar data analysis and visualization, efficiently extracting the inherent structure and features of interest of the data. However, with growing dataset sizes and complexity, it is increasingly becoming infeasible to compute topological abstractions of interest in serial and on single machines. This paper presents the state of the art in the scalable computation of topological abstractions on scalar data, in shared memory parallel on single machines, and in distributed memory parallel on multiple machines. We highlight results for set‐based, graph‐based and complex‐based abstractions and organize the state of the art based on this taxonomy. The paper identifies parallelization and distribution techniques common in topological algorithms and highlights further areas of interest with underdeveloped efforts.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2014

WE-E-17A-03: FDG-PET-Based Radiomics to Predict Local Control and Survival Following Radiotherapy

Purpose: An exploding field in cancer research is “radiomics,” based on the hypothesis that there is statistical (hidden) information in medical images that is prognostic or predictive of outcomes. Our group has developed an efficient pipeline to extract and analyze quantitative image features from medical images as related to outcomes or diagnosis. In this work, we summarize our previous studies with positron emission tomography (PET) images and show the potential of the use of radiomics for outcomes research. Methods: We analyzed two cancer datasets, each consisting of pre-radiotherapy-treatment PET scans: 163 T1-2N0M0 non-small cell lung cancer (NSCLC) patients and 174 head and neck (H and N) cancer patients with stage III–IV. The PET scans were converted to Computational Environment for Radiological Research (CERR) format, and CERR was used to generate 24 shape, texture, and intensity-histogram based image features. Data-mining and logistic regression methods were then used to model local failure (LF) and overall survival (OS). Unbiased estimates of performance were generated using leave-one-out cross-validation (LOOCV). Results: For predicting LF, the models with biologically equivalent dose (BED) and TLG (metabolic tumor volume (MTV) x SUVmean) in NSCLC, and skewness and MTV in H and N, achieved the best performance with AUC=0.818 (p<0.0001) and AUC=0.826 (p=0.0002), respectively. For predicting OS, the models with kurtosis and volume in NSCLC and SUVmax and homogeneity in H and N achieved the best performance with AUC=0.706 (p<0.0001) and AUC=0.656 (p=0.0003), respectively. On LOOCV, all these models retained significant predictive power. Interestingly, MTV was highly correlated with LF in both sites. Conclusion: PET-based imaged features are promising tools for improving treatment management decision making. Much more research is needed to identify optimal radiomics metrics and to correlate imaging phenotype with other clinical or genomic information.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

FAIR to WISE (F2W) v1.0.0

FAIR to WISE (F2W) is an iterative, large-language model (LLM) driven pipeline that turns unstructured research PDFs into structured, queryable knowledge graphs (KGs). Core features include schema-driven extraction to a LinkML model; full provenance capture; ontology-grounded enrichment (e.g., chemical validation and ChEBI lookup); graph construction to JSON-LD with stable IDs; and KG-RAG question answering with evidence-aware retrieval. The system is engineered for reproducibility and accessibility (open-source Ollama models, temperature=0, NVTX/Nsight profiling) with robust QA (relation verification, deduplication, and deterministic outputs). Primary uses are literature-to-KG automation, knowledge-grounded Q&A, and experimental steering support. We demonstrate the approach in organic photovoltaics, where the pipeline ingests papers, builds a domain KG, and evaluates answers against expert competency questions to guide experimental planning and interpretation. Compared with off-the-shelf LLMs and ad-hoc NLP tools, F2W addresses ontology gaps and reduces hallucination risk by grounding responses in extracted evidence and enforcing schema constraints; it also offers deterministic, provenance-linked outputs and open, cost-aware deployment. Evidence-aware ranking further improves answer quality over pure vector search.

Abramov, David [Lawrence Berkeley National Laborat↗
DOE OSTI2021

Hardware-Based Emulator with Deep Learning Model for Building Energy Control and Prediction Based on Occupancy Sensors’ Data

Heating, ventilation, and air conditioning (HVAC) is the largest source of residential energy consumption. Occupancy sensors’ data can be used for HVAC control since it indicates the number of people in the building. HVAC and sensors form a typical cyber-physical system (CPS). In this paper, we aim to build a hardware-based emulation platform to study the occupancy data’s features, which can be further extracted by using machine learning models. In particular, we propose two hardware-based emulators to investigate the use of wired/wireless communication interfaces for occupancy sensor-based building CPS control, and the use of deep learning to predict the building energy consumption with the sensor data. We hypothesize is that the building energy consumption may be predicted by using the occupancy data collected by the sensors, and question what type of prediction model should be used to accurately predict the energy load. Another hypothesis is that an in-lab hardware/software platform could be built to emulate the occupancy sensing process. The machine learning algorithms can then be used to analyze the energy load based on the sensing data. To test the emulator, the occupancy data from the sensors is used to predict energy consumption. The synchronization scheme between sensors and the HVAC server will be discussed. We have built two hardware/software emulation platforms to investigate the sensor/HVAC integration strategies, and used an enhanced deep learning model—which has sequence-to-sequence long short-term memory (Seq2Seq LSTM)—with an attention model to predict the building energy consumption with the preservation of the intrinsic patterns. Because the long-range temporal dependencies are captured, the Seq2Seq models may provide a higher accuracy by using LSTM architectures with encoder and decoder. Meanwhile, LSTMs can capture the temporal and spatial patterns of time series data. The attention model can highlight the most relevant input information in the energy prediction by allocating the attention weights. The communication overhead between the sensors and the HVAC control server can also be alleviated via the attention mechanism, which can automatically ignore the irrelevant information and amplify the relevant information during CNN training. Our experiments and performance analysis show that, compared with the traditional LSTM neural network, the performance of the proposed method has a 30% higher prediction accuracy.

Ye, Zhijing↗
DOE OSTI2021

Hierarchical Tactile Sensation Integration from Prosthetic Fingertips Enables Multi-Texture Surface Recognition

Multifunctional flexible tactile sensors could be useful to improve the control of prosthetic hands. To that end, highly stretchable liquid metal tactile sensors (LMS) were designed, manufactured via photolithography, and incorporated into the fingertips of a prosthetic hand. Three novel contributions were made with the LMS. First, individual fingertips were used to distinguish between different speeds of sliding contact with different surfaces. Second, differences in surface textures were reliably detected during sliding contact. Third, the capacity for hierarchical tactile sensor integration was demonstrated by using four LMS signals simultaneously to distinguish between ten complex multi-textured surfaces. Four different machine learning algorithms were compared for their successful classification capabilities: K-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), and neural network (NN). The time-frequency features of the LMSs were extracted to train and test the machine learning algorithms. The NN generally performed the best at the speed and texture detection with a single finger and had a 99.2 ± 0.8% accuracy to distinguish between ten different multi-textured surfaces using four LMSs from four fingers simultaneously. The capability for hierarchical multi-finger tactile sensation integration could be useful to provide a higher level of intelligence for artificial hands.

Abd, Moaed A. (ORCID:0000000284954244)↗
DOE OSTI2022

A dictionary learning algorithm for compression and reconstruction of streaming data in preset order

There has been an emerging interest in developing and applying dictionary learning (DL) to process massive datasets in the last decade. Many of these efforts, however, focus on employing DL to compress and extract a set of important features from data, while considering restoring the original data from this set a secondary goal. On the other hand, although several methods are able to process streaming data by updating the dictionary incrementally as new snapshots pass by, most of those algorithms are designed for the setting where the snapshots are randomly drawn from a probability distribution. In this paper, we present a new DL approach to compress and denoise massive dataset in real time, in which the data are streamed through in a preset order (instances are videos and temporal experimental data), so at any time, we can only observe a biased sample set of the whole data. Here, our approach incrementally builds up the dictionary in a relatively simple manner: if the new snapshot is adequately explained by the current dictionary, we perform a sparse coding to find its sparse representation; otherwise, we add the new snapshot to the dictionary, with a Gram-Schmidt process to maintain the orthogonality. To compress and denoise noisy datasets, we apply the denoising to the snapshot directly before sparse coding, which deviates from traditional dictionary learning approach that achieves denoising via sparse coding. Compared to full-batch matrix decomposition methods, where the whole data is kept in memory, and other mini-batch approaches, where unbiased sampling is often assumed, our approach has minimal requirement in data sampling and storage: i) each snapshot is only seen once then discarded, and ii) the snapshots are drawn in a preset order, so can be highly biased. Through experiments on climate simulations and scanning transmission electron microscopy (STEM) data, we demonstrate that the proposed approach performs competitively to those methods in data reconstruction and denoising.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Methods and systems for detecting cancer

A technique for classifying lesions as malignant or benign is disclosed. The technique can include: cooling an area of skin including a lesion of a patient to initiate a warm-up process; receiving a temporal sequence of thermal images of the area of skin representing a thermal recovery of the area of skin, the temporal sequence of thermal images generated by an infrared camera; generating a temporal profile of the thermal recovery based on the temporal sequence of thermal images; analyzing temporal statistical properties of the temporal profile; determining a malignancy probability that the lesion is malignant based on an analysis of the temporal profile, wherein the determining includes extracting one or more statistical features based on continuous-time stochastic signals in the sequence of thermal images; and classifying the lesion based on the malignancy probability.

47 OTHER INSTRUMENTATION↗
DOE OSTI2016

Neutronics and computational fluid dynamics analyses for a natural circulation loop of molten fuel salt

A conceptual reactor system of molten fuel salt loop designed for Mo-99 production was analyzed by coupling TRITON neutronics and Fluent computational fluid dynamics (CFD) simulations. The loop system operated in 1 MW thermal power features natural circulation and potential extraction of non-soluble fission products (FP) in fuel salt. The behavior of natural circulation was studied and the power and temperature distributions in equilibrium were obtained. A long-term fuel depletion analysis of the system considering fuel circulation and reprocessing was then performed using an approximate stepwise sequence of simulations. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2015

Internal respiratory surrogate in multislice 4D CT using a combination of Fourier transform and anatomical features

Purpose: The purpose of this study was to develop a novel algorithm to create a robust internal respiratory signal (IRS) for retrospective sorting of four-dimensional (4D) computed tomography (CT) images. Methods: The proposed algorithm combines information from the Fourier transform of the CT images and from internal anatomical features to form the IRS. The algorithm first extracts potential respiratory signals from low-frequency components in the Fourier space and selected anatomical features in the image space. A clustering algorithm then constructs groups of potential respiratory signals with similar temporal oscillation patterns. The clustered group with the largest number of similar signals is chosen to form the final IRS. To evaluate the performance of the proposed algorithm, the IRS was computed and compared with the external respiratory signal from the real-time position management (RPM) system on 80 patients. Results: In 72 (90%) of the 4D CT data sets tested, the IRS computed by the authors’ proposed algorithm matched with the RPM signal based on their normalized cross correlation. For these data sets with matching respiratory signals, the average difference between the end inspiration times (Δt{sub ins}) in the IRS and RPM signal was 0.11 s, and only 2.1% of Δt{sub ins} were more than 0.5 s apart. In the eight (10%) 4D CT data sets in which the IRS and the RPM signal did not match, the average Δt{sub ins} was 0.73 s in the nonmatching couch positions, and 35.4% of them had a Δt{sub ins} greater than 0.5 s. At couch positions in which IRS did not match the RPM signal, a correlation-based metric indicated poorer matching of neighboring couch positions in the RPM-sorted images. This implied that, when IRS did not match the RPM signal, the images sorted using the IRS showed fewer artifacts than the clinical images sorted using the RPM signal. Conclusions: The authors’ proposed algorithm can generate robust IRSs that can be used for retrospective sorting of 4D CT data. The algorithm is completely automatic and requires very little processing time. The algorithm is cost efficient and can be easily adopted for everyday clinical use.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Structure–Function Insights into Thermoresponsive Copolymers as Lanthanide Precipitants

The synthetic toolbox for stimuli-responsive polymers has broadened to include many tunable variables, making these materials applicable in diverse technologies. However, unraveling the key composition–structure–function relationships to facilitate ground-up design remains a challenge due to the inherent dispersity in sequence and conformations for synthetic polymers. We here present a systematic study of these relationships using a model system of copolymers with a thermoresponsive (N-isopropylacrylamide) backbone in addition to metal-chelating (acrylic acid) and hydrophobic structural comonomers and evaluate their efficiency at isolating technologically critical lanthanide ions. The efficiency of lanthanide ion extraction by precipitation was quantitated with a metallochromic dye to reveal trends relating copolymer hydrophobicity to improved separations. Further, we examined the role of different hydrophobic comonomers in dictating the solution-phase conformation of the polymer in the presence and absence of lanthanide ions, and we correlated key features of the hydrophobic comonomer to extraction efficiency. Lastly, we identified how the local proximity of thermoresponsive, chelating, and hydrophobic subunits facilitates metal extraction by manipulating the copolymer sequence with multiblock polymerization. Through mechanistic analysis, we propose a binding-then-assembly process through which metal ions are coprecipitated with macromolecular chelators.

Copolymers↗
DOE OSTI2023

Model-based image change quantification

A system is provided for identifying and quantizing a change in a scene having objects based on comparison of features representing a target object derived from a first image and a second image that includes the target object. The system segments, based on a scene model of the scene, a second image that includes the target object to identify a second area representing the target object within the second image. The system extracts, from the second image, second features for the target object based on the second area. The system determines a second effectiveness of the second features indicating effectiveness of the second features in representing the target object. The system detects a change based on a difference between first features and the second features factoring in a first effectiveness and the second effectiveness.

Roberts, Randy S.↗
DOE OSTI2019

Multi-Formalism Modeling for Disaster Resilience, Forecasting, and Response

Disaster response preparedness, risk mitigation, and effective post-event response are critical for national security, public health, and economic integrity. For areas impacted by extreme events, timely and accurate impact assessments of lifeline infrastructures are critical. Traditional disaster management and situational awareness platforms are not capable of handling the massive influx of available information from traditional and non-traditional sources. Next-generation analytic assessment approaches, where use of dynamically sourced, heterogeneous data with near real-time availability are integrated into a continually-updated analytics framework. The objective of this research was to develop a foundational multi-formalism modeling platform to integrate novel data sources for use in improving situational awareness after a disaster event. Specifically, to 1) provide an architecture for machine-learning based data fusion various multi-sensor datasets; 2) classify, geolocate, and temporally bin novel data sources for use in spatially-enabled machine-learning based data fusion; and 3) derive confidence-based observation data with machine-learning based prediction to fill spatial and temporal observation gaps. This project developed a reusable cloud-based pipeline architecture for ingesting, storing, and analyzing relevant data, executing a range of deep-learning models, and visualize the information geographically. The pipeline development was informed by previous PNNL investments (StreamKit) and built upon leading-edge technologies consisting of: 1) a raw datastore; 2) a data enrichment pipeline with custom and third-party analytics; 3) enriched data storage; and 4) a custom UI to display the enriched data. Machine learning/deep learning models were selected and tested to classify social media images for relevancy and presence of flood waters. Our custom trained relevance models were run on a validation dataset and the overall accuracy of the relevance classifiers ranged from 65% to 90%. We found that convolutional neural network (CNN) models were both faster and more accurate than more traditional machine learning models. We applied the relevance classifier to remove non-relevant images and then undertook a limited training of CNN models to detect flood on ~1,800 labeled images. The testing accuracy of the flood detection models were ~88%. To improve the geographic location of both social media and oblique aerial images we tested a multi-step workflow built on a pre-trained deep-learning model. To identify similarity features from test and reference scenes, we applied the Xception and Faiss models to a set of test images with inaccurate spatial locations, as well and precisely-located reference scenes from the general area. Matching reference scenes to the test scenes with the closest similarity index had limited success in improving the precision of test scene location and additional methods have been identified for testing. Data fusion between authoritative geographic data (satellite imaging) and non-authoritative crowdsourced data is an underlying theme throughout this research and methods are tested bring these data to a common geographic form through feature matching and transformations. The automated extraction of supporting information for disaster response from oblique aerial images or ground-level social media images is accomplished through semantic image segmentation and transformation. The non-authoritative data are used to validate the authoritative data collections and processing and optionally, t+0 flood models. In addition, the common form geographic data are combined with other static landscape features to develop spatially-explicit training vectors used in deep generative statistical inference models to develop complex non-linear relationships in static and dynamic data and ultimately derive a spatially continuous and probabilistic assessment of flood damage with the event domain.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2017

Geometry and Gesture-Based Features from Saccadic Eye-Movement as a Biometric in Radiology

In this study, we present a novel application of sketch gesture recognition on eye-movement for biometric identification and estimating task expertise.The study was performed for the task of mammographic screening with simultaneous viewing of four coordinated breast views as typically done in clinical practice. Eye-tracking data and diagnostic decisions collected for 100 mammographic cases (25 normal, 25 benign, 50 malignant) and 10 readers (three board certified radiologists and seven radiology residents), formed the corpus for this study.Sketch gesture recognition techniques were employed to extract geometric and gesture-based features from saccadic eye-movements.Our results show that saccadic eye-movement, characterized using sketch-based features, result in more accurate models for predicting individual identity and level of expertise than more traditional eye-tracking features.

Alamudun, Folami↗