Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “FEATURE”

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 397 records · Page 22

An integrated manifold learning approach for high-dimensional data feature extractions and its applications to online process monitoring of additive manufacturing

As an effective dimension reduction and feature extraction technique, manifold learning has been successfully applied to high-dimensional data analysis. With the rapid development of sensor technology, a large amount of high-dimensional data such as image streams can be easily available. Thus, a promising application of manifold learning is in the field of sensor signal analysis, particular for the applications of online process monitoring and control using high-dimensional data. The objective of this study is to develop a manifold learning-based feature extraction method for process monitoring of Additive Manufacturing (AM) using online sensor data. Due to the non-parametric nature of most existing manifold learning methods, their performance in terms of computational efficiency, as well as noise resistance has yet to be improved. To address this issue, this study proposes an integrated manifold learning approach termed multi-kernel metric learning embedded isometric feature mapping (MKML-ISOMAP) for dimension reduction and feature extraction of online high-dimensional sensor data such as images. Based on the extracted features with the utilization of supervised classification and regression methods, an online process monitoring methodology for AM is implemented to identify the actual process quality status. Finally, in the numerical simulation and real-world case studies, the proposed method demonstrates excellent performance in both prediction accuracy and computational efficiency.

36 MATERIALS SCIENCE↗

An Explainable Machine-Learning Model for Compensatory Reserve Measurement: Methods for Feature Selection and the Effects of Subject Variability

Tracking vital signs accurately is critical for triaging a patient and ensuring timely therapeutic intervention. The patient’s status is often clouded by compensatory mechanisms that can mask injury severity. The compensatory reserve measurement (CRM) is a triaging tool derived from an arterial waveform that has been shown to allow for earlier detection of hemorrhagic shock. However, the deep-learning artificial neural networks developed for its estimation do not explain how specific arterial waveform elements lead to predicting CRM due to the large number of parameters needed to tune these models. Alternatively, we investigate how classical machine-learning models driven by specific features extracted from the arterial waveform can be used to estimate CRM. More than 50 features were extracted from human arterial blood pressure data sets collected during simulated hypovolemic shock resulting from exposure to progressive levels of lower body negative pressure. A bagged decision tree design using the ten most significant features was selected as optimal for CRM estimation. This resulted in an average root mean squared error in all test data of 0.171, similar to the error for a deep-learning CRM algorithm at 0.159. By separating the dataset into sub-groups based on the severity of simulated hypovolemic shock withstood, large subject variability was observed, and the key features identified for these sub-groups differed. This methodology could allow for the identification of unique features and machine-learning models to differentiate individuals with good compensatory mechanisms against hypovolemia from those that might be poor compensators, leading to improved triage of trauma patients and ultimately enhancing military and emergency medicine.

60 APPLIED LIFE SCIENCES↗

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

High-resolution Urban Image Classification Using Extended Features

High-resolution image classification poses several challenges because the typical object size is much larger than the pixel resolution. Any given pixel (spectral features at that location) by itself is not a good indicator of the object it belongs to without looking at the broader spatial footprint. Therefore most modern machine learning approaches that are based on per-pixel spectral features are not very effective in high- resolution urban image classification. One way to overcome this problem is to extract features that exploit spatial contextual information. In this study, we evaluated several features in- cluding edge density, texture, and morphology. Several machine learning schemes were tested on the features extracted from a very high-resolution remote sensing image and results were presented.

99 GENERAL AND MISCELLANEOUS↗

Data-Driven State of Health Estimation for Second-Life Batteries Using Interpolated Synthetic Data and Feature Selection

Accurate estimation of the State of Health (SOH) for second-life batteries (SLBs) is crucial given their increasing use in energy storage applications. Precise SOH prediction is essential for safe operation and robust battery management systems. A major challenge is the limited availability of datasets for building reliable degradation models. To address this, synthetic data generation through linear interpolation is performed to extend the available data, making it more representative of real-world battery operating conditions. By analyzing feature correlation with SOH, the most relevant features are selected for the model. The proposed approach employs a convolutional neural network (CNN) model trained on this interpolated, feature-selected dataset, using time series data of voltage, temperature, and current over a cycle. By focusing on highly correlated features, the model achieves over 95% accuracy, with mean absolute error and root mean squared error up to 2.27% and 2.64%, respectively, in SOH estimation for two battery datasets tested. These results highlight the potential of combining synthetic data generation and feature selection to enhance SOH predictions, showcasing the superior performance of the proposed CNN model for both new batteries and SLBs.

feature selection↗

Analysis and Benchmarking of feature reduction for classification under computational constraints

Abstract Machine learning is most often expensive in terms of computational and memory costs due to training with large volumes of data. Current computational limitations of many computing systems motivate us to investigate practical approaches, such as feature selection and reduction, to reduce the time and memory costs while not sacrificing the accuracy of classification algorithms. In this work, we carefully review, analyze, and identify the feature reduction methods that have low costs/overheads in terms of time and memory. Then, we evaluate the identified reduction methods in terms of their impact on the accuracy, precision, time, and memory costs of traditional classification algorithms. Specifically, we focus on the least resource intensive feature reduction methods that are available in Scikit-Learn library. Since our goal is to identify the best performing low-cost reduction methods, we do not consider complex expensive reduction algorithms in this study. In our evaluation, we find that at quadratic-scale feature reduction, the classification algorithms achieve the best trade-off among competitive performance metrics. Results show that the overall training times are reduced 61%, the model sizes are reduced 6×, and accuracy scores increase 25% compared to the baselines on average with quadratic scale reduction.

97 MATHEMATICS AND COMPUTING↗

A New Workflow of X-ray CT Image Processing and Data Analysis of Structural Features in Rock Using Open-Source Software

X-ray computed tomography (CT) images of rock specimens often contain artifacts which must be corrected before scientific analyses are performed. Here, we present a new workflow of automated image processing to utilize poor-quality X-ray CT scan images. The workflow runs on the open-source image analysis software and efficiently separates desired features from low-contrast scanned images. The new workflow is a two-step technique using contrast enhancement and automated feature segmentation to generate noise-free binary images. The results of binary images using the proposed workflow and using a conventional thresholding technique are analyzed to show the quality of the proposed method. The paper also presents a workflow of estimating the structural geometries of features in two and three dimensions. The results of the structural feature analyses and computational time were compared between the open-source (ImageJ) and commercial image analysis software (Bruker Computed Tomography Analyzer). The commercial software was more computationally efficient, but the task-specific macros in open-source software enabled the user-desired automation in image processing and data extraction of desired structural features of comparable quality.

47 OTHER INSTRUMENTATION↗

New scattering features in non-Hermitian space fractional quantum mechanics

Highlights: • Space fraction quantum mechanics (SFQM) has been investigated with complex delta and barrier potentials. • New scattering features due to these potentials are obtained in SFQM. • Spectral Singular (SS) points are blue/red shifted when Levy index is decreased. • The oscillations in scattering coefficients around SS have interesting behaviors in SFQM. • Deeper relations between the scattering properties in standard QM and those of in SFQM are observed. - Abstract: The spectral singularity (SS) and coherent perfect absorption (CPA) have been extensively studied over the last one and half decade for different non-Hermitian potentials in non-Hermitian standard quantum mechanics (SQM) governed by Schrödinger equation. In the present work we explore these scattering features in the domain of non-Hermitian space fractional quantum mechanics (SFQM) governed by fractional Schrödinger equation which is characterized by Levy index α (1<α≤2). We observe that non-Hermitian SFQM systems have more flexibility for SS and CPA and display some new features of scattering. For the delta potential V(x)=iρδ(x−x{sub 0}), ρ>0, the SS energy, E{sub ss}, is blue or red shifted with decreasing α depending on the strength of the potential. For complex rectangular barrier in non-Hermitian SQM, it is known that the reflection and transmission amplitudes are oscillatory near the spectral singular point. It is found that these oscillations eventually develop SS in non-Hermitian SFQM. The similar features are also reported for the case of CPA phenomena from complex rectangular barrier in non-Hermitian SFQM. These observations suggest a deeper relation between scattering features of non-Hermitian SQM and non-Hermitian SFQM.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Protein location prediction using atomic composition and global features of the amino acid sequence

Subcellular location of protein is constructive information in determining its function, screening for drug candidates, vaccine design, annotation of gene products and in selecting relevant proteins for further studies. Computational prediction of subcellular localization deals with predicting the location of a protein from its amino acid sequence. For a computational localization prediction method to be more accurate, it should exploit all possible relevant biological features that contribute to the subcellular localization. In this work, we extracted the biological features from the full length protein sequence to incorporate more biological information. A new biological feature, distribution of atomic composition is effectively used with, multiple physiochemical properties, amino acid composition, three part amino acid composition, and sequence similarity for predicting the subcellular location of the protein. Support Vector Machines are designed for four modules and prediction is made by a weighted voting system. Our system makes prediction with an accuracy of 100, 82.47, 88.81 for self-consistency test, jackknife test and independent data test respectively. Our results provide evidence that the prediction based on the biological features derived from the full length amino acid sequence gives better accuracy than those derived from N-terminal alone. Considering the features as a distribution within the entire sequence will bring out underlying property distribution to a greater detail to enhance the prediction accuracy.

60 APPLIED LIFE SCIENCES↗

Neptune long-lived atmospheric features in 2013–2015 from small (28-cm) to large (10-m) telescopes

Since 2013, observations of Neptune with small telescopes (28–50 cm) have resulted in several detections of long-lived bright atmospheric features that have also been observed by large telescopes such as Keck II or Hubble. The combination of both types of images allows the study of the long-term evolution of major cloud systems in the planet. In 2013 and 2014 two bright features were present on the planet at southern mid-latitudes. These may have merged in late 2014, possibly leading to the formation of a single bright feature observed during 2015 at the same latitude. This cloud system was first observed in January 2015 and nearly continuously from July to December 2015 in observations with telescopes in the 2-10-m class and in images from amateur astronomers. These images show the bright spot as a compact feature at -40.1 ± 1.6° planetographic latitude well resolved from a nearby bright zonal band that extended from -42° to -20°. The size of this system depends on wavelength and varies from a longitudinal extension of 8000 ± 900 km and latitudinal extension of 6500 ± 900 km in Keck II images in H and Ks bands to 5100 ± 1400 km in longitude and 4500 ± 1400 km in latitude in HST images in 657 nm. Over July to September 2015 the structure drifted westward in longitude at a rate of 24.48 ± 0.03°/day or -94 ± 3 m/s. This is about 30 m/s slower than the zonal winds measured at the time of the Voyager 2 flyby. Tracking its motion from July to November 2015 suggests a longitudinal oscillation of 16° in amplitude with a 90-day period, typical of dark spots on Neptune and similar to the Great Red Spot oscillation in Jupiter. The limited time covered by high-resolution observations only covers one full oscillation and other interpretations of the changing motions could be possible. HST images in September 2015 show the presence of a dark spot at short wavelengths located in the southern flank (planetographic latitude -47.0°) of the bright compact cloud observed throughout 2015. The drift rate of the bright cloud and dark spot translates to a zonal speed of -87.0 ± 2.0 m/s, which matches the Voyager 2 zonal speeds at the latitude of the dark spot. Identification of a few other features in 2015 enabled the extraction of some limited wind information over this period. This work demonstrates the need of frequently monitoring Neptune to understand its atmospheric dynamics and shows excellent opportunities for professional and amateur collaborations.

79 ASTRONOMY AND ASTROPHYSICS↗

Evaluating 239 Pu(n,f) cross sections via machine learning using experimental data, covariances, and measurement features

In this paper, the neutron-induced 239 Pu fission cross section, 239 Pu(n,f), is evaluated from 1–20 MeV using experimental data and associated covariances while also considering information on the measurement, termed features here. For instance, methods to determine the background, sample backing material, or impurities in the sample, are explicitly taken into account in the evaluation process. To this end, outliers in the experimental data are identified with a modified version of the Hybrid Robust Support Vector Machine. In a second step, two machine learning methods (logistic regression with elastic net regularization and random forest regression with SHAP feature importance metric) are used to highlight measurement features that are common among many of the outlying data points. Based on this analysis, penalty uncertainties are added to the experimental covariances of outlying data points that have outlier measurement features and are put through the generalized-least-squares evaluation. The resulting evaluated mean values and covariances differ distinctly from those data evaluated without the penalty uncertainties. These results highlight that certain measurement features should be more closely examined.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Identifying critical features of iron phosphate particle for lithium preference

One-dimensional (1D) olivine iron phosphate (FePO 4 ) is widely proposed for electrochemical lithium (Li) extraction from dilute water sources, however, significant variations in Li selectivity were observed for particles with different physical attributes. Understanding how particle features influence Li and sodium (Na) co-intercalation is crucial for system design and enhancing Li selectivity. Here, we investigate a series of FePO 4 particles with various features and revealed the importance of harnessing kinetic and chemo-mechanical barrier difference between lithiation and sodiation to promote selectivity. The thermodynamic preference of FePO 4 provides baseline of selectivity while the particle features are critical to induce different kinetic pathways and barriers, resulting in different Li to Na selectivity from 6.2 × 10 2 to 2.3 × 10 4 . Importantly, we categorize the FePO 4 particles into two groups based on their distinctly paired phase evolutions upon lithiation and sodiation, and generate quantitative correlation maps among Li preference, morphological features, and electrochemical properties. By selecting FePO 4 particles with specific features, we demonstrate fast (636 mA/g) Li extraction from a high Li source (1: 100 Li to Na) with (96.6 ± 0.2)% purity, and high selectivity (2.3 × 10 4 ) from a low Li source (1: 1000 Li to Na) with (95.8 ± 0.3)% purity in a single step.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

The 2175 Å bump features in FeLoBAL quasars: One indicator of MW-like dust in the nuclear region of quasars

To investigate the properties of dust in the nuclear region of quasars, we explored the extinction curves of the iron low-ionisation broad absorption line (FeLoBAL) quasar SDSS J163004.29+311957.6 and its two analogues. The parametrised extinction curves indicated the Milky Way-like 2175 Å bump features in underlying extinction, which are similar to those seen in the Local Group and in a subset of high-redshift star-forming galaxies. Compared to the bump features in the Large Magellanic Cloud (LMC), the detections in this work are much closer to those in the Milky Way (MW). These bump features, as well as those in the high- and low-ionisation broad absorption line (BAL) quasars with 2175 Å bumps, are probably the counterpart of the 2175 Å bump features in the quasar environment. This type of dust grain is generally small, easily disrupted by high-energy photons, and has difficulty surviving in the radiation field of the active galactic nucleus. However, due to the presence of absorption-line outflows, the 2175 Å bump feature in quasars, which should be rare, is seen many times in BAL quasars. The shielding effect of outflow clouds allows the MW-like dust grains to be assembled or extends the survival period in the quasar nuclear region. The process and physical and chemical conditions deserve further observational study and investigation.

79 ASTRONOMY AND ASTROPHYSICS↗

Simultaneous imaging electron- and ion-feature Thomson scattering measurements of radiatively heated Xe

Uniform density and temperature Xe plasmas have been produced over >4 mm scale-lengths using x-rays generated in a cylindrical Pb cavity. The cavity is 750 {mu}m in depth and diameter, and is heated by a 300 J, 2 ns square, 1054 nm laser pulse focused to a spot size of 200 {mu}m at the cavity entrance. The plasma is characterized by simultaneous imaging Thomson scattering measurements from both the electron and ion scattering features. The electron feature measurement determines the spatial electron density and temperature profile, and using these parameters as constraints in the ion feature analysis allows an accurate determination of the charge state of the Xe ions. The Thomson scattering probe beam is 40 J, 200 ps, and 527 nm, and is focused to a 100 {mu}m spot size at the entrance of the Pb cavity. Each system has a spatial resolution of 25 {mu}m, a temporal resolution of 200 ps (as determined by the probe duration), and a spectral resolution of 2 nm for the electron feature system and 0.025 nm for the ion feature system. The experiment is performed in a Xe filled target chamber at a neutral pressure of 3-10 Torr, and the x-rays produced in the Pb ionize and heat the Xe to a charge state of 20{+-}4 at up to 200 eV electron temperatures.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Origin of additional spectral features in modulated reflectance spectra of 2-dimensional semiconductor systems

High resolution photoreflectance (PR) spectroscopy study on a single GaAs/AlGaAs quantum well representing a two-dimensional (2D) system, shows additional distinct spectral features on the high energy side of the first confined heavy-hole and light-hole exciton transitions. The PR experiments involved a special dual detection technique which significantly improved the measurement sensitivity. Photoluminescence excitation spectroscopy data on the sample showed broadened step-like features around these energies. A detailed lineshape analysis, including first principles simulations, was performed to understand the origins of these additional PR spectral features. They are shown to arise primarily from inhomogeneously broadened first excited state transition of the excitons, rather than from a change in the joint density of states at the exciton continuum edge. The analysis suggests that such features are more likely in the case of 2D excitons as compared to 3D excitons in bulk material. Apart from its significance for post-growth characterization, identification of these additional PR features enables direct estimation of the exciton binding energy.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Polarization controlled deep sub-wavelength periodic features written by femtosecond laser on nanodiamond thin film surface

Deep sub-wavelength (Λ/λ = ∼0.22) periodic features are induced uniformly on a nanodiamond (ND) thin film surface using femtosecond (fs) laser irradiation (pulse duration = ∼110 fs and central wavelength of ∼800 nm). The topography of the surface features is controlled by the laser polarization. Orientation of features is perpendicular to laser polarization. Periodicity (spatial periodicity of < λ/4) of the surface features is less than the laser wavelength. This work gives an experimental proof of polarization controlled surface plasmon-fs laser coupling mechanism prompting the interaction between fs laser and solid matter (here ND thin film) which in turn is resulting in the periodic surface features. Scanning electron microscopy in conjunction with micro Raman scattering, X-ray diffraction, and atomic force microscopy are carried out to extract surface morphology and phase information of the laser irradiated regions. This work demonstrates an easy and efficient surface fabrication technique.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

A data-driven approach to construct a quantitative relationship between microstructural features of fatigue cracks and contact acoustic nonlinearity

This study demonstrates the feasibility of a data-driven approach to construct a quantitative relationship between nonlinear acoustic parameters and microstructural features of contact interfaces. The near-surface nonlinearity is measured using dynamic acousto-elastic testing (DAET) with a surface wave probe, while the microstructural features are extracted from scanning electron microscopy (SEM) images of fatigue cracks. Four aluminum alloy samples, each having a fatigue crack are prepared. Six local nonlinearity parameters are measured at different locations along the crack propagation direction. A total of 40 local measurements are acquired. A principal component analysis (PCA) reveals that all six nonlinearity parameters are correlated and hence can be replaced by one principal component (PC). Fifteen crack micro-geometrical features at each measurement point were extracted from the SEM images. Regression analysis is used to relate the PC of the nonlinearity parameters to the microstructural features at the crack interface. We compare three regression models that take variable selection into account: stepwise multiple linear regression (MLR), stepwise principal component regression (PCR), and least absolute shrinkage and selection operator (LASSO). Despite having different principles, the three predictive models identify two features as the most significant in predicting the interface nonlinearity: the crack aperture (opening) distribution and the distance to the crack tip. The differences between the three models and the physical interpretation of the data-driven predictions are discussed.

36 MATERIALS SCIENCE↗

The impact of seasonality on multi-scale feature extraction techniques

A key component in constructing a broad-scale, gridded population dataset is fine resolution geospatial data accurately depicting the extent of human activity. Analogous datasets are often developed using a wide range of methods and classification techniques, including the use of spatial features, spectral features, or the coupling of both to identify the presence of man-made structures from high-resolution satellite imagery. By using spatial and textural-based descriptors to generate high-resolution settlement layers for two dissimilar regions at the peak of seasonal disparity, this study attempts to quantify the influence of seasonality on the accuracy of a supervised, multi-scale, feature extraction framework for automated delineation of human settlement. Results generated by numerous models are evaluated against a reference dataset allowing for assessment of seasonal and feature differences in the context of accuracy. Global or regional mapping of human settlement requires the assemblage of high-resolution satellite images with variegated acquisition characteristics (season, sun elevation, off-nadir, etc.) to produce a cloud-free composite image from which features are extracted. Results of this study suggest an emphasis on imagery criteria, in particular acquisition date, could improve classification accuracy when mapping human settlement at scale.

58 GEOSCIENCES↗