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 703 records · Page 39

Data-Driven Cyber-Attack Detection for PV Farms via Time-Frequency Domain Features

The internetworking of grid-connected power electronics converters (PECs) in photovoltaic (PV) farms has inevitably expanded the cyber-attack surfaces. Here this paper presents a comprehensive study on cyber-attack detection and diagnosis for PEC-enabled PV farms via single waveform sensor to distinguish between normal conditions, open-circuit faults, short-circuit faults, and cyber-attacks. To our knowledge, this has not been attempted before. Firstly, we propose frequency-domain magnitude-based residuals to identify short-circuit faults and a time-domain mean current vector-based feature to distinguish open-circuit faults from other threats. These features can fully reflect the specific physical characteristics of PV farms during threat duration. Secondly, unlike micro phasor measurement units (µPMU) and raw electric waveform-based methods, the proposed innovative features can address novel cyber-attacks that are excluded from the training process. Thirdly, an online hardware-in-the-loop (HIL) testbed using the OPAL-RT real-time digital simulator has verified the effectiveness. The monitoring system runs in real-time while using HIL as an operational solar farm and a National Instruments (NI) data acquisition card as the electric waveform sensor at the point of coupling.

42 ENGINEERING↗

FICH: Feature instability cavitation history [Slides]

We seek to improve our ability to predict and understand the Richtmyer-Meshkov (RM) unstable dynamics of explosively shocked isolated features interfaced with vacuum or gases, and an HE products cavity. Explosively shocked features form as 2D or 3D RM phenomena. Liquid cavitation cause cavitation bubbles when shockwaves collide, and cavitation waves from wave interactions with isolated features form that source mass into the RM unstable sheets or spikes, and the cavitation waves may slice through bulk material into the HE products cavity.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

CPGminer: An Interactive Dashboard to Explore the Genomic Features and Taxonomy of Complete Prokaryotic Genomes

Prokaryotes, the earliest forms of life on Earth, play crucial roles in global biogeochemical processes in virtually all ecosystems. The ever-increasing amount of prokaryotic genome sequencing data provides a wealth of information to examine fundamental and applied questions through systematic genome comparison. Genomic features, such as genome size and GC content, and taxonomy-centric genomic features of complete prokaryotic genomes (CPGs) are crucial for various fields of microbial research and education, yet they are often overlooked. Additionally, creating systematically curated datasets that align with research concerns is an essential yet challenging task for wet-lab researchers. In this study, we introduce CPGminer, a user-friendly tool that allows researchers to quickly and easily examine the genomic features and taxonomy of CPGs and curate genome datasets. We also provide several examples to demonstrate its practical utility in addressing descriptive questions.

59 BASIC BIOLOGICAL SCIENCES↗

Graph-based featurization methods for classifying small molecule compounds

For over a decade, drug-induced liver injury (DILI) has posed significant drawbacks in the synthesis and development of drugs and remains a consequential concern. With finite success within the existing preclinical models, DILI is one of the main causes of drug withdrawal or termination from the market. Particularly, this withdrawal occurs during the late stages of drug development (Kullak-Ublick, 2017). Since DILI is difficult to diagnose and treat, it has become an obstacle in the drug production market that in turn affects clinicians, pharmaceutical companies, and consumers. We propose a method for learning features of DILI-positive drugs based on the graphical relationships and patterns they possess within a network of biological databases. We also train various statistical and machine learning models on these learned features in order to classify the drugs as DILI-positive or negative. Our methods include Random Forest, Neural networks, and logistic regression classification. We utilize labeled DILI-positive and DILI-negative datasets, which were developed by the FDA and the National center for toxicological research, as well as additional literature datasets (Thakkar, 2020) in order to validate our results and assess our featurization and model accuracy.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Feature‐shared adaptive‐boost deep learning for invasiveness classification of pulmonary subsolid nodules in CT images

Purpose In clinical practice, invasiveness is an important reference indicator for differentiating the malignant degree of subsolid pulmonary nodules. These nodules can be classified as atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IAC). The automatic determination of a nodule's invasiveness based on chest CT scans can guide treatment planning. However, it is challenging, owing to the insufficiency of training data and their interclass similarity and intraclass variation. To address these challenges, we propose a two‐stage deep learning strategy for this task: prior‐feature learning followed by adaptive‐boost deep learning. Methods The adaptive‐boost deep learning is proposed to train a strong classifier for invasiveness classification of subsolid nodules in chest CT images, using multiple 3D convolutional neural network (CNN)‐based weak classifiers. Because ensembles of multiple deep 3D CNN models have a huge number of parameters and require large computing resources along with more training and testing time, the prior‐feature learning is proposed to reduce the computations by sharing the CNN layers between all weak classifiers. Using this strategy, all weak classifiers can be integrated into a single network. Results Tenfold cross validation of binary classification was conducted on a total of 1357 nodules, including 765 noninvasive (AAH and AIS) and 592 invasive nodules (MIA and IAC). Ablation experimental results indicated that the proposed binary classifier achieved an accuracy of with an AUC of 81.3 . These results are superior compared to those achieved by three experienced chest imaging specialists who achieved an accuracy of , , and , respectively. About 200 additional nodules were also collected. These nodules covered 50 cases for each category (AAH, AIS, MIA, and IAC, respectively). Both binary and multiple classifications were performed on these data and the results demonstrated that the proposed method definitely achieves better performance than the performance achieved by nonensemble deep learning methods. Conclusions It can be concluded that the proposed adaptive‐boost deep learning can significantly improve the performance of invasiveness classification of pulmonary subsolid nodules in CT images, while the prior‐feature learning can significantly reduce the total size of deep models. The promising results on clinical data show that the trained models can be used as an effective lung cancer screening tool in hospitals. Moreover, the proposed strategy can be easily extended to other similar classification tasks in 3D medical images.

Wang, Jun↗

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↗

Image feature based GPS trace filtering for road network generation and road segmentation

We propose a new method to infer road networks from GPS trace data and accurately segment road regions in high-resolution aerial images. Unlike previous efforts that rely on GPS traces alone, we exploit image features to infer road networks from noisy trace data. The inferred road network is used to guide road segmentation. We show that the number of image segments spanned by the traces and the trace orientation validated with image features are important attributes for identifying GPS traces on road regions. Based on filtered traces , we construct road networks and integrate them with image features to segment road regions. Lastly, our experiments show that the proposed method produces more accurate road networks than the leading method that uses GPS traces alone, and also achieves high accuracy in segmenting road regions even with very noisy GPS data.

58 GEOSCIENCES↗

Differentiation of pancreatic neuroendocrine tumors from pancreas renal cell carcinoma metastases on CT using qualitative and quantitative features

Purpose: To assess qualitative and quantitative imaging features on enhanced CT that may differentiate pancreatic neuroendocrine tumors (PNETs) from pancreatic renal cell carcinoma (RCC) metastases. Methods: This IRB-approved multi-center retrospective case–control study compared 43 resected PNETs and 28 resected RCC metastases with pre-operative enhanced CT identified consecutively between 2003 and 2017. Two blinded radiologists (R1/R2) independently assessed tumor location, attenuation (relative to pancreas), composition (solid/cystic/mixed), homogeneity (homogeneous/heterogeneous), calcification, multiplicity, and for main pancreatic duct (MPD) dilation. Tumors were segmented for quantitative texture analysis. Data were analyzed with Chi square, logistic regression, and receiver operating characteristic (ROC). Inter-observer agreement was assessed (Cohen’s kappa). Results: There was no difference in age, gender, location, attenuation, or composition (P > 0.05) between groups. PNETs were larger than RCC metastases (37 ± 23 mm vs. 26 ± 21 mm, P = 0.038), more frequently solitary (P < 0.001), subjectively more heterogeneous (P = 0.033/0.144, R1/R2), and associated with calcification (P = 0.002/0.004) and MPD dilation (P = 0.025/0.006). Agreement for subjective features was moderate-to-almost perfect (K = 0.4879–0.9481). Quantitative texture analysis showed higher entropy in PNETs (6.32 ± 0.49 versus 5.96 ± 0.53; P = 0.004) with no difference in other features studied (P > 0.05). Entropy had ROC area under the curve for diagnosis of PNET of 0.77 ± 0.06, with optimal sensitivity/specificity of 71.4/79.1%. Conclusions: Compared to pancreatic RCC metastases, PNETs are larger, more frequently solitary, contain calcification, show MPD dilation, and are subjectively and quantitatively more heterogeneous tumors.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Reader agreement and accuracy of ultrasound features for hepatic steatosis

Purpose: The purpose of the study is to assess the reader agreement and accuracy of eight ultrasound imaging features for classifying hepatic steatosis in adults with known or suspected hepatic steatosis. Methods: This was an IRB-approved, HIPAA-compliant prospective study of adult patients with known or suspected hepatic steatosis. All patients signed written informed consent. Ultrasound images (Siemens S3000, 6C1HD, and 4C1 transducers) were acquired by experienced sonographers following a standard protocol. Eight readers independently graded eight features and their overall impression of hepatic steatosis on ordinal scales using an electronic case report form. Duplicated images from the 6C1HD transducer were read twice to assess intra-reader agreement. Intra-reader, inter-transducer, and inter-reader agreement were assessed using intraclass correlation coefficients (ICC). Features with the highest intra-reader agreement were selected as predictors for dichotomized histological steatosis using Classification and Regression Tree (CART) analysis, and the accuracy of the decision rule was compared to the accuracy of the radiologists’ overall impression. Results: 45 patients (18 males, 27 females; mean age 56 ± 12 years) scanned from September 2015 to July 2016 were included. Mean intra-reader ICCs ranged from 0.430 to 0.777, inter-transducer ICCs ranged from 0.228 to 0.640, and inter-reader ICCs ranged from 0.014 to 0.561. The CART decision rule selected only large hepatic vein blurring and achieved similar accuracy to the overall impression (74% to 75% and 68% to 72%, respectively). Conclusions: Large hepatic vein blurring, liver–kidney contrast, and overall impression provided the highest reader agreement. Large hepatic vein blurring may provide the highest classification accuracy for dichotomized grading of hepatic steatosis.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Pancreatic neuroendocrine tumors: MR imaging features preoperatively predict lymph node metastasis

Purposes: Predictive factors of lymph node metastasis (LNM) in pancreatic neuroendocrine tumors (pNETs) are not well established. We sought to identify the value of MR imaging features in preoperatively predicting the lymph node metastasis of pNETs. Materials and methods: In this study, we enrolled 108 consecutive patients with pNETs between January 2009 and June 2018. MR morphologic features and quantitative data were evaluated. Predictors of LNM were evaluated using univariate and multivariate logistic regression models. Results: A total of 108 patients with pNETs were finally enrolled, including 82 LNM-negative and 26 LNM-positive patients. Features significantly related to the LNM of pNETs at univariate analysis were tumor size > 2 cm (P = 0.003), Ki-67 > 5% (P = 0.002), non-enhancement pattern (P < 0.001), apparent diffusion coefficient value (P < 0.001), main pancreatic duct dilation (P < 0.001) and pancreatic atrophy (P = 0.032) and extrapancreatic tumor spread (P = 0.001), CNRs during arterial, portal and delay phase (P = 0.005, 0.047, and 0.045, respectively), and histological classification (P = 0.006). At multivariate analysis, non-enhancement pattern (P = 0.019; odds ratio, 6.652; 95% CI 1.369, 32.321) and main pancreatic duct dilation (P = 0.018; odds ratio, 6.745; 95% CI 1.379, 32.991) were independent risk factors for predicting the LNM of pNETs. Conclusion: The non-enhancement characteristic and main pancreatic duct dilation appear to be linked with LNM in pNETs. These radiological predictors can be easily obtained preoperatively, and may help to avoid missing pNETs with a high risk of LNM.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Frequency and imaging features of abdominal immune-related adverse events in metastatic lung cancer patients treated with PD-1 inhibitor

Purpose: To investigate the frequency and imaging features of radiographically evident abdominal immune-related adverse events (irAEs) in patients with metastatic non-small-cell lung cancer (NSCLC) treated with PD-1 inhibitors. Methods: This retrospective study included 137 patients with metastatic NSCLC treated with PD-1 inhibitor nivolumab monotherapy (75 women; median age: 65 years), who had a baseline CT and at least one follow-up abdomen CT during therapy. Baseline and all follow-up abdominal CTs performed for monitoring of nivolumab therapy were reviewed to identify the organ-specific abdominal irAEs including colitis/enteritis, hepatitis, biliary toxicity, pancreatitis, nephritis, sarcoid-like reaction, and pancreatic and adrenal atrophy. Their frequency and imaging features were described. Results: Eighteen (13%) patients had radiologically identified abdominal irAEs (median 2.1 months after starting nivolumab; interquartile range 1.17–5.83 months); 16 patients developed enteritis/colitis (12 pancolitis, two segmental colitis, one enterocolitis, one enteritis), two hepatitis, one adrenalitis. One patient with hepatitis also developed colitis/enteritis. Radiographic abdominal irAE occurred after nivolumab therapy was discontinued in six patients before any subsequent therapy was started. IrAEs prompted nivolumab interruption and treatment with steroids in four patients (three colitis/enteritis, one hepatitis). Most common CT features of colitis/enteritis included mesenteric hyperemia (n = 15), bowel wall thickening (n = 13), mucosal hyperenhancement (n = 10), and fluid-filled colon (n = 9). Conclusion: Abdominal irAEs were detected on CT in 13% of NSCLC patients treated with nivolumab, and colitis, in the pancolitis form, was the most common irAE. Given the expanding role of immunotherapy, radiologists should be aware of the frequency and imaging manifestations of abdominal irAEs and the impact on patient management.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Liver metastases of neuroendocrine tumors: is it possible to diagnose different histologic subtypes depending on multiphasic CT features?

Purpose: To assess and compare the multiphasic computed tomography (CT) features of neuroendocrine tumor (NET) liver metastases and to investigate the possibility to predict the histologic subtype of the primary tumor. Materials and methods: Between January 2013 and December 2017 patients with biopsy proven NET with at least one liver metastasis who underwent multiphasic CT were enrolled in this study. All cases were acquired using a standardized multiphasic liver CT protocol, arterial, portal, and hepatic venous phases were obtained. Images were retrospectively analyzed in consensus by two abdominal radiologists blinded to clinical data and histologic subtype. The size, number, and location of lesions were noted. Enhancement patterns of each lesion on arterial, portal, and hepatic venous phases were assessed. For quantitative analysis, CT attenuation of tumors, liver parenchyma, and aorta were measured using a circular region of interest (ROI) on arterial, portal, and hepatic venous phases for reflecting the blood supply of the tumor. Tumor-to-aorta and tumor-to-liver ratio were calculated in all three phases. Differences between subtypes of NET liver metastases were studied using ROC analysis of clustered data. Results: A total of 255 neuroendocrine tumor liver metastases divided into 101 (39.6%) pancreatic, 60 (23.5%) gastroenteric and 94 (36.8%) lung NET liver metastases were analyzed. Contrast enhancement of lesions was homogeneous in 78% of patients (n = 199), which was significantly more frequent in patients with pancreatic group than in those with gastroenteric origin (n = 90, 89.1% vs. n = 28, 46.7%; p < 0.001). Gastroenteric NET metastases frequently showed heterogeneous enhancement, which was significantly higher than in the other two groups (50% vs. 3% and 2%). With respect to the location of the primary tumor, the difference in enhancement patterns of the liver lesions was statistically significant (p < 0.001). Pancreatic NET metastases were mostly hyperdense on arterial images and isodense on portal and hepatic venous phase images (79.2%, n = 80). Gastroenteric NET metastases were mostly hyperdense on arterial phase images and hypodense on portal and hepatic venous phase images (n = 28, 46.7%). The most frequent pattern for lung NET metastases was hypoattenuation on all three phase images (n = 44, 46.8%). ROC analysis of clustered data revealed statistically significant differences between pancreatic NET liver metastases, gastroenteric NET liver metastases, and lung NET liver metastases in terms of tumor-to-aorta (T–A) ratio and tumor-to-liver (T–L) ratio (p < 0.001). Conclusion: We observed statistically significant differences in multiphasic CT features (enhancement pattern, T–A ratio, and T–L ratio) between histologic subtypes of NET liver metastases. As the difference in histological subtypes of NET liver metastases results in a different prognosis and different management strategy, these CT features might help to identify the primary tumor when it is not known to ensure accurate tumor staging and to provide optimal treatment.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Clinicopathological findings and imaging features of intraductal papillary neoplasm of the bile duct: comparison between contrast-enhanced ultrasound and contrast-enhanced computed tomography

Purpose: Intraductal papillary neoplasms of the bile duct (IPNBs) are a group of rare lesions with uncertain clinical findings and imaging features. We aim to investigate the clinicopathological features and imaging findings of IPNBs on contrast-enhanced ultrasound (CEUS) and contrast-enhanced computed tomography (CECT). Methods: From February 2005 to March 2018, 30 patients with pathologically confirmed IPNBs were retrospectively identified in our hospital. Demographic, clinical, and pathological data, CEUS and CECT features and surgical strategies were analyzed. Results: The most common clinical manifestations were abdominal pain (53.3%), jaundice (23.3%), and acute cholangitis (10.0%). Among all lesions, 5/30 (16.7%) lesions presented as dilated bile ducts only, while 13/30 (43.3%) lesions presented as dilated bile ducts with intraductal papillary masses, and 12/30 (40.0%) presented as solid masses with dilated bile ducts. For the 20 patients who underwent both CEUS and CECT, 18 lesions were hyperenhanced on CEUS, and 17 lesions were hyperenhanced on CECT in the arterial phase. In total, 16 and 18 lesions showed washout in the portal and late phases on CEUS, while the corresponding number of lesions that showed washout in the portal and late phases on CECT were 11 and 13. Twelve lesions (40.0%) showed atypical hyperplasia, while 16/30 (53.3%) lesions underwent malignant transformations. Conclusions: There are 3 major forms of IPNBs on grayscale ultrasound, including diffusely dilated bile ducts without visible mass; focal dilated bile duct with intraductal papillary masses; and solid mass surrounded by dilated bile ducts. The enhancement patterns of IPNBs on CEUS and on CECT were consistent. IPNB has a high malignant potential, and patients should be treated with surgical resection after the diagnosis is established.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Microvascular invasion and grading in hepatocellular carcinoma: correlation with major and ancillary features according to LIRADS

Purpose: To assess major and ancillary parameters that could be correlated with Microvascular Invasion (MIV) and with histologic grade of HCC. Materials and methods: In this retrospective study, we assessed 62 patients (14 women–48 men; mean age, 63 years; range 38–80 years) that underwent hepatic resection for HCC. All patients were subject to Multidetector computed tomography (MDCT); 40 to Magnetic Resonance (MR) study. The radiologist assessed major and ancillary features according to LIRADS (v. 2018) and reported any radiological accessory findings if detected. Results: No major feature showed statistically significant differences and correlation with grading. Mean ADC value was correlated with grading and with MIV status. No major feature was correlated to MIV; progressive contrast enhancement and satellite nodules showed statistically different percentages with respect to the presence of MIV, so as at the monovariate correlation analysis, satellite nodules were correlated with the presence of MIV. At multivariate regression analysis, no factor proved to be strong predictors of grading while progressive contrast enhancement and satellite nodules were significantly associated with the MIV. Conclusion: Mean ADC value is correlated to HCC grading and MIV status. Progressive contrast enhancement and the presence of satellite nodules are correlated to MIV status.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Microscale Confinement features in microfluidic devices can affect biofilm

Biofilms are aggregations of microbes that are encased by extra-cellular polymeric substances (EPS) and adhere to surfaces and interfaces. Biofilm development on abiotic surfaces is a dynamic process, which typically proceeds through an initial phase of adhesion of plankntonic microbes to the substrate, followed by events such as growth, maturation and EPS secretion. However, the coupling of hydrodynamics, microbial adhesion and biofilm growth remain poorly understood. Here, we investigate the effect of semiconfined features on biofilm formation. Using a microfluidic device and fluorescent time-lapse microscopy, we establish that confinement features can significantly affect biofilm formation. Biofilm dynamics change not only as a function of confinement features, but also of the total fluid flow rate, and our combination of experimental results and numerical simulations reveal insights into the link between hydrodynamics and biofilm formation.

biofilm↗

Features of resilience

The National Academy of Sciences (NAS) definition of resilience is used here to organize common concepts and synthesize a set of key features of resilience that can be used across diverse application domains. The features in common include critical functions (services), thresholds, cross-scale (both space and time) interactions, and memory and adaptive management. We propose a framework for linking these features to the planning, absorbing, recovering, and adapting phases identified in the NAS definition. As a result, the proposed delineation of resilience can be important in understanding and communicating resilience concepts.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Parametric reduced-order modeling for component-oriented treatment and localized nonlinear feature inclusion

Abstract We propose coupling a physics-based reduction framework with a suited response decomposition technique to derive a component-oriented reduction (COR) approach, which is suitable for assembly systems featuring localized nonlinearities. Dependencies on influencing parameters are injected into the reduced-order model (ROM), thus ensuring robustness and validity over a domain of parametric inputs, while capturing nonlinear effects. The implemented approach employs individual component modes to capture localized features while additionally relying on reduced modes of a global nature to approximate the system’s dynamics accurately. The global modes are derived from a linear monolithic system, defined as a result of a coordinate separation scheme, which permits the proposed COR-ROM to naturally couple the response between linear and nonlinear subdomains. The derived low-order representation utilizes a proper orthogonal decomposition projection and is additionally reinforced with the inclusion of a hyper-reduction technique to capture the underlying high-fidelity model response while providing accelerated computations. The resulting approach is exemplified in the synthetic case studies of a four-story shear frame with multiple nonlinear regions driven by hysteresis and a large-scale kingpin connection featuring plasticity.

Vlachas, Konstantinos (ORCID:000000029124219X)↗

A multi-backend autotuning study of feature selection on GPUs

Abstract Feature selection is an important step in machine learning that can benefit from GPU acceleration. As the number of GPU vendors increases, it is imperative to adapt algorithms such as the minimum Redundancy Maximum Relevance (mRMR) feature selection method to different backends that support several GPU architectures. This work presents a multi-backend implementation of mRMR across CUDA, HIP, and SYCL, and studies its performance when combined with Bayesian optimization and transfer learning to automatically tune execution parameters for different platforms and datasets. Our experimental results show that when tuned, CUDA and HIP achieve comparable performance on NVIDIA architectures, while SYCL exhibits a moderate performance gap. Overall, this work highlights the impact of backend choice and autotuning on GPU-accelerated feature selection and provides insights into deploying mRMR across heterogeneous environments.

Beceiro, Bieito (ORCID:0000000333014890)↗