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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Cross-Categorical Transfer Learning based Composite Load Protection Modeling

Protection equipment is used to prevent damage to induction motor loads by isolating them from power systems in the event of severe faults. Modeling the response of induction motor loads and their protection is vital for power system planning and operation, especially in understanding system's dynamic performance and stability after a fault occurs. Induction motors are usually equipped with several types of protection with different operation mechanisms, making it challenging to develop adequate yet not overly complex protection models and determine their parameters for aggregate induction motor models. This paper proposes a novel cross-categorical transfer learning based framework to determine protection model parameters for aggregate induction motor loads in commercial buildings. Introducing a mathematical abstraction, the task of determining a suitable set of parameters for the protection model in composite load models is formulated as a combination of feature extraction using transferable layers, followed by affine operations through non-transferable layers applied on the previous extracted features. Numerical results are provided to illustrate the application of the framework.

transfer learning, Stacked Autoencoder, Composite ↗
DOE OSTI2024

Review of In Situ Sensing for Directed Energy Deposition for Industrial Part Quality Assessment

As the use additive manufacturing (AM) processes continues to grow in critical industries, improved quality assurance methods are becoming increasingly sought after for qualification and certification of AM components. Traditional nondestructive evaluation of printed components is often unable to supply the required confidence in print quality to justify qualification and certification, but the layer-by-layer nature of AM provides unprecedented opportunities for in situ quality inspection. This document summarizes recent developments in process monitoring research specifically related to Directed Energy Deposition (DED). Particular attention is given to three aspects of the highlighted manuscripts: (1) the type of sensors used, (2) features extracted from each sensor modality, and (3) analysis of extracted features for AM quality assessment. Based on the review of the state-of-the-art, several observations have been made. First, none of the reviewed works have applied their trained models to real part geometries, with many of the works relying on single track experiments, thin-walled structures, and cubes. Similarly, there have not been any works demonstrating model generalizability, i.e., a model trained on data from one build allows for fruitful analysis of data from another build. Many works used machine learning techniques to distinguish different process regimes (i.e., normal, keyholing, lack-of-fusion), but very few papers have investigated stochastic variation in an already “optimized” process. Sensor fusion approaches are also limited in the DED sensing literature, but the few works that have employed such techniques have demonstrated the benefits. Finally, registration of in situ data to the build coordinate system is of paramount importance to producing industrially relevant in situ monitoring systems. Data registration allows direct correlations between process anomalies detected in the process monitoring data to localized departures in part quality, but such techniques are generally lacking in the current literature.

36 MATERIALS SCIENCE↗
NASA NTRS1980

Basic cluster compression algorithm

Feature extraction and data compression of LANDSAT data is accomplished by BCCA program which reduces costs associated with transmitting, storing, distributing, and interpreting multispectral image data. Algorithm uses spatially local clustering to extract features from image data to describe spectral characteristics of data set. Approach requires only simple repetitive computations, and parallel processing can be used for very high data rates. Program is written in FORTRAN IV for batch execution and has been implemented on SEL 32/55.

Hilbert, E. E.↗
NASA NTRS1987

Image processing system to analyze droplet distributions in sprays

An image processing system was developed which automatically analyzes the size distributions in fuel spray video images. Images are generated by using pulsed laser light to freeze droplet motion in the spray sample volume under study. This coherent illumination source produces images which contain droplet diffraction patterns representing the droplets degree of focus. The analysis is performed by extracting feature data describing droplet diffraction patterns in the images. This allows the system to select droplets from image anomalies and measure only those droplets considered in focus. Unique features of the system are the totally automated analysis and droplet feature measurement from the grayscale image. The feature extraction and image restoration algorithms used in the system are described. Preliminary performance data is also given for two experiments. One experiment gives a comparison between a synthesized distribution measured manually and automatically. The second experiment compares a real spray distribution measured using current methods against the automatic system.

Bertollini, Gary P.↗
NASA NTRS2001

Multi-Sensor Registration of Earth Remotely Sensed Imagery

Assuming that approximate registration is given within a few pixels by a systematic correction system, we develop automatic image registration methods for multi-sensor data with the goal of achieving sub-pixel accuracy. Automatic image registration is usually defined by three steps; feature extraction, feature matching, and data resampling or fusion. Our previous work focused on image correlation methods based on the use of different features. In this paper, we study different feature matching techniques and present five algorithms where the features are either original gray levels or wavelet-like features, and the feature matching is based on gradient descent optimization, statistical robust matching, and mutual information. These algorithms are tested and compared on several multi-sensor datasets covering one of the EOS Core Sites, the Konza Prairie in Kansas, from four different sensors: IKONOS (4m), Landsat-7/ETM+ (30m), MODIS (500m), and SeaWIFS (1000m).

LeMoigne, Jacqueline↗
NASA NTRS2004

Registration and Fusion of Multiple Source Remotely Sensed Image Data

Earth and Space Science often involve the comparison, fusion, and integration of multiple types of remotely sensed data at various temporal, radiometric, and spatial resolutions. Results of this integration may be utilized for global change analysis, global coverage of an area at multiple resolutions, map updating or validation of new instruments, as well as integration of data provided by multiple instruments carried on multiple platforms, e.g. in spacecraft constellations or fleets of planetary rovers. Our focus is on developing methods to perform fast, accurate and automatic image registration and fusion. General methods for automatic image registration are being reviewed and evaluated. Various choices for feature extraction, feature matching and similarity measurements are being compared, including wavelet-based algorithms, mutual information and statistically robust techniques. Our work also involves studies related to image fusion and investigates dimension reduction and co-kriging for application-dependent fusion. All methods are being tested using several multi-sensor datasets, acquired at EOS Core Sites, and including multiple sensors such as IKONOS, Landsat-7/ETM+, EO1/ALI and Hyperion, MODIS, and SeaWIFS instruments. Issues related to the coregistration of data from the same platform (i.e., AIRS and MODIS from Aqua) or from several platforms of the A-train (i.e., MLS, HIRDLS, OMI from Aura with AIRS and MODIS from Terra and Aqua) will also be considered.

LeMoigne, Jacqueline↗
NASA NTRS2010

Speech Acquisition and Automatic Speech Recognition for Integrated Spacesuit Audio Systems

A voice-command human-machine interface system has been developed for spacesuit extravehicular activity (EVA) missions. A multichannel acoustic signal processing method has been created for distant speech acquisition in noisy and reverberant environments. This technology reduces noise by exploiting differences in the statistical nature of signal (i.e., speech) and noise that exists in the spatial and temporal domains. As a result, the automatic speech recognition (ASR) accuracy can be improved to the level at which crewmembers would find the speech interface useful. The developed speech human/machine interface will enable both crewmember usability and operational efficiency. It can enjoy a fast rate of data/text entry, small overall size, and can be lightweight. In addition, this design will free the hands and eyes of a suited crewmember. The system components and steps include beam forming/multi-channel noise reduction, single-channel noise reduction, speech feature extraction, feature transformation and normalization, feature compression, model adaption, ASR HMM (Hidden Markov Model) training, and ASR decoding. A state-of-the-art phoneme recognizer can obtain an accuracy rate of 65 percent when the training and testing data are free of noise. When it is used in spacesuits, the rate drops to about 33 percent. With the developed microphone array speech-processing technologies, the performance is improved and the phoneme recognition accuracy rate rises to 44 percent. The recognizer can be further improved by combining the microphone array and HMM model adaptation techniques and using speech samples collected from inside spacesuits. In addition, arithmetic complexity models for the major HMMbased ASR components were developed. They can help real-time ASR system designers select proper tasks when in the face of constraints in computational resources.

Huang, Yiteng↗
NASA NTRS2015

Automatic Speech Acquisition and Recognition for Spacesuit Audio Systems

NASA has a widely recognized but unmet need for novel human-machine interface technologies that can facilitate communication during astronaut extravehicular activities (EVAs), when loud noises and strong reverberations inside spacesuits make communication challenging. WeVoice, Inc., has developed a multichannel signal-processing method for speech acquisition in noisy and reverberant environments that enables automatic speech recognition (ASR) technology inside spacesuits. The technology reduces noise by exploiting differences between the statistical nature of signals (i.e., speech) and noise that exists in the spatial and temporal domains. As a result, ASR accuracy can be improved to the level at which crewmembers will find the speech interface useful. System components and features include beam forming/multichannel noise reduction, single-channel noise reduction, speech feature extraction, feature transformation and normalization, feature compression, and ASR decoding. Arithmetic complexity models were developed and will help designers of real-time ASR systems select proper tasks when confronted with constraints in computational resources. In Phase I of the project, WeVoice validated the technology. The company further refined the technology in Phase II and developed a prototype for testing and use by suited astronauts.

Ye, Sherry↗
DOE OSTI2014

Using computer-extracted image features for modeling of error-making patterns in detection of mammographic masses among radiology residents

Purpose: Mammography is the most widely accepted and utilized screening modality for early breast cancer detection. Providing high quality mammography education to radiology trainees is essential, since excellent interpretation skills are needed to ensure the highest benefit of screening mammography for patients. The authors have previously proposed a computer-aided education system based on trainee models. Those models relate human-assessed image characteristics to trainee error. In this study, the authors propose to build trainee models that utilize features automatically extracted from images using computer vision algorithms to predict likelihood of missing each mass by the trainee. This computer vision-based approach to trainee modeling will allow for automatically searching large databases of mammograms in order to identify challenging cases for each trainee. Methods: The authors’ algorithm for predicting the likelihood of missing a mass consists of three steps. First, a mammogram is segmented into air, pectoral muscle, fatty tissue, dense tissue, and mass using automated segmentation algorithms. Second, 43 features are extracted using computer vision algorithms for each abnormality identified by experts. Third, error-making models (classifiers) are applied to predict the likelihood of trainees missing the abnormality based on the extracted features. The models are developed individually for each trainee using his/her previous reading data. The authors evaluated the predictive performance of the proposed algorithm using data from a reader study in which 10 subjects (7 residents and 3 novices) and 3 experts read 100 mammographic cases. Receiver operating characteristic (ROC) methodology was applied for the evaluation. Results: The average area under the ROC curve (AUC) of the error-making models for the task of predicting which masses will be detected and which will be missed was 0.607 (95% CI,0.564-0.650). This value was statistically significantly different from 0.5 (p < 0.0001). For the 7 residents only, the AUC performance of the models was 0.590 (95% CI,0.537-0.642) and was also significantly higher than 0.5 (p = 0.0009). Therefore, generally the authors’ models were able to predict which masses were detected and which were missed better than chance. Conclusions: The authors proposed an algorithm that was able to predict which masses will be detected and which will be missed by each individual trainee. This confirms existence of error-making patterns in the detection of masses among radiology trainees. Furthermore, the proposed methodology will allow for the optimized selection of difficult cases for the trainees in an automatic and efficient manner.

60 APPLIED LIFE SCIENCES↗
NASA NTRS2009

Automatic Extraction of Planetary Image Features

With the launch of several Lunar missions such as the Lunar Reconnaissance Orbiter (LRO) and Chandrayaan-1, a large amount of Lunar images will be acquired and will need to be analyzed. Although many automatic feature extraction methods have been proposed and utilized for Earth remote sensing images, these methods are not always applicable to Lunar data that often present low contrast and uneven illumination characteristics. In this paper, we propose a new method for the extraction of Lunar features (that can be generalized to other planetary images), based on the combination of several image processing techniques, a watershed segmentation and the generalized Hough Transform. This feature extraction has many applications, among which image registration.

Troglio, G.↗
DOE OSTI2014

Binary classification of items of interest in a repeatable process

A system includes host and learning machines in electrical communication with sensors positioned with respect to an item of interest, e.g., a weld, and memory. The host executes instructions from memory to predict a binary quality status of the item. The learning machine receives signals from the sensor(s), identifies candidate features, and extracts features from the candidates that are more predictive of the binary quality status relative to other candidate features. The learning machine maps the extracted features to a dimensional space that includes most of the items from a passing binary class and excludes all or most of the items from a failing binary class. The host also compares the received signals for a subsequent item of interest to the dimensional space to thereby predict, in real time, the binary quality status of the subsequent item of interest.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

DARHT Multi-intelligence Seismic and Acoustic Data Analysis

The purpose of this report is to document the analysis of seismic and acoustic data collected at the Dual-Axis Radiographic Hydrodynamic Test (DARHT) facility at Los Alamos National Laboratory for robust, multi-intelligence decision making. The data utilized herein is obtained from two tri-axial seismic sensors and three acoustic sensors, resulting in a total of nine data channels. The goal of this analysis is to develop a generalized, automated framework to determine internal operations at DARHT using informative features extracted from measurements collected external of the facility. Our framework involves four components: (1) feature extraction, (2) data fusion, (3) classification, and finally (4) robustness analysis. Two approaches are taken for extracting features from the data. The first of these, generic feature extraction, involves extraction of statistical features from the nine data channels. The second approach, event detection, identifies specific events relevant to traffic entering and leaving the facility as well as explosive activities at DARHT and nearby explosive testing sites. Event detection is completed using a two stage method, first utilizing signatures in the frequency domain to identify outliers and second extracting short duration events of interest among these outliers by evaluating residuals of an autoregressive exogenous time series model. Features extracted from each data set are then fused to perform analysis with a multi-intelligence paradigm, where information from multiple data sets are combined to generate more information than available through analysis of each independently. The fused feature set is used to train a statistical classifier and predict the state of operations to inform a decision maker. We demonstrate this classification using both generic statistical features and event detection and provide a comparison of the two methods. Finally, the concept of decision robustness is presented through a preliminary analysis where uncertainty is added to the system through noise in the measurements.

58 GEOSCIENCES↗
NASA NTRS2012

Composite Wavelet Filters for Enhanced Automated Target Recognition

Automated Target Recognition (ATR) systems aim to automate target detection, recognition, and tracking. The current project applies a JPL ATR system to low-resolution sonar and camera videos taken from unmanned vehicles. These sonar images are inherently noisy and difficult to interpret, and pictures taken underwater are unreliable due to murkiness and inconsistent lighting. The ATR system breaks target recognition into three stages: 1) Videos of both sonar and camera footage are broken into frames and preprocessed to enhance images and detect Regions of Interest (ROIs). 2) Features are extracted from these ROIs in preparation for classification. 3) ROIs are classified as true or false positives using a standard Neural Network based on the extracted features. Several preprocessing, feature extraction, and training methods are tested and discussed in this paper.

automated target recognition↗
NASA NTRS2011

Testing of a Composite Wavelet Filter to Enhance Automated Target Recognition in SONAR

Automated Target Recognition (ATR) systems aim to automate target detection, recognition, and tracking. The current project applies a JPL ATR system to low resolution SONAR and camera videos taken from Unmanned Underwater Vehicles (UUVs). These SONAR images are inherently noisy and difficult to interpret, and pictures taken underwater are unreliable due to murkiness and inconsistent lighting. The ATR system breaks target recognition into three stages: 1) Videos of both SONAR and camera footage are broken into frames and preprocessed to enhance images and detect Regions of Interest (ROIs). 2) Features are extracted from these ROIs in preparation for classification. 3) ROIs are classified as true or false positives using a standard Neural Network based on the extracted features. Several preprocessing, feature extraction, and training methods are tested and discussed in this report.

image processing↗
NASA NTRS2005

Automated Extraction of Secondary Flow Features

The use of Computational Fluid Dynamics (CFD) has become standard practice in the design and development of the major components used for air and space propulsion. To aid in the post-processing and analysis phase of CFD many researchers now use automated feature extraction utilities. These tools can be used to detect the existence of such features as shocks, vortex cores and separation and re-attachment lines. The existence of secondary flow is another feature of significant importance to CFD engineers. Although the concept of secondary flow is relatively understood there is no commonly accepted mathematical definition for secondary flow. This paper will present a definition for secondary flow and one approach for automatically detecting and visualizing secondary flow.

Dorney, Suzanne M.↗
DOE OSTI2014

Electronic nose with a new feature reduction method and a multi-linear classifier for Chinese liquor classification

An electronic nose (e-nose) was designed to classify Chinese liquors of the same aroma style. A new method of feature reduction which combined feature selection with feature extraction was proposed. Feature selection method used 8 feature-selection algorithms based on information theory and reduced the dimension of the feature space to 41. Kernel entropy component analysis was introduced into the e-nose system as a feature extraction method and the dimension of feature space was reduced to 12. Classification of Chinese liquors was performed by using back propagation artificial neural network (BP-ANN), linear discrimination analysis (LDA), and a multi-linear classifier. The classification rate of the multi-linear classifier was 97.22%, which was higher than LDA and BP-ANN. Finally the classification of Chinese liquors according to their raw materials and geographical origins was performed using the proposed multi-linear classifier and classification rate was 98.75% and 100%, respectively.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS2004

An X-Band Radar Terrain Feature Detection Method for Low-Altitude SVS Operations and Calibration Using LiDAR

To enable safe use of Synthetic Vision Systems at low altitudes, real-time range-to-terrain measurements may be required to ensure the integrity of terrain models stored in the system. This paper reviews and extends previous work describing the application of x-band radar to terrain model integrity monitoring. A method of terrain feature extraction and a transformation of the features to a common reference domain are proposed. Expected error distributions for the extracted features are required to establish appropriate thresholds whereby a consistency-checking function can trigger an alert. A calibration-based approach is presented that can be used to obtain these distributions. To verify the approach, NASA's DC-8 airborne science platform was used to collect data from two mapping sensors. An Airborne Laser Terrain Mapping (ALTM) sensor was installed in the cargo bay of the DC-8. After processing, the ALTM produced a reference terrain model with a vertical accuracy of less than one meter. Also installed was a commercial-off-the-shelf x-band radar in the nose radome of the DC-8. Although primarily designed to measure precipitation, the radar also provides estimates of terrain reflectivity at low altitudes. Using the ALTM data as the reference, errors in features extracted from the radar are estimated. A method to estimate errors in features extracted from the terrain model is also presented.

Young, Steve↗
DOE OSTI2016

TU-D-207B-03: Early Assessment of Response to Chemoradiotherapy Based On Textural Analysis of Pre and Mid-Treatment FDG-PET Image in Locally Advanced Head and Neck Cancer

Purpose: To evaluate whether tumor textural features extracted from both pre- and mid-treatment FDG-PET images predict early response to chemoradiotherapy in locally advanced head and neck cancer, and investigate whether they provide complementary value to conventional volume-based measurements. Methods: Ninety-four patients with locally advanced head and neck cancers were retrospectively studied. All patients received definitive chemoradiotherapy and underwent FDG-PET planning scans both before and during treatment. Within the primary tumor we extracted 6 textural features based on gray-level co-occurrence matrices (GLCM): entropy, dissimilarity, contrast, correlation, energy, and homogeneity. These image features were evaluated for their predictive power of treatment response to chemoradiotherapy in terms of local recurrence free survival (LRFS) and progression free survival (PFS). Logrank test were used to assess the statistical significance of the stratification between low- and high-risk groups. P-values were adjusted for multiple comparisons by the false discovery rate (FDR) method. Results: All six textural features extracted from pre-treatment PET images significantly differentiated low- and high-risk patient groups for LRFS (P=0.011–0.038) and PFS (P=0.029–0.034). On the other hand, none of the textural features on mid-treatment PET images was statistically significant in stratifying LRFS (P=0.212–0.445) or PFS (P=0.168–0.299). An imaging signature that combines textural feature (GLCM homogeneity) and metabolic tumor volume showed an improved performance for predicting LRFS (hazard ratio: 22.8, P<0.0001) and PFS (hazard ratio: 13.9, P=0.0005) in leave-one-out cross validation. Intra-tumor heterogeneity measured by textural features was significantly lower in mid-treatment PET images than in pre-treatment PET images (T-test: P<1.4e-6). Conclusion: Tumor textural features on pretreatment FDG-PET images are predictive for response to chemoradiotherapy in locally advanced head and neck cancer. The complementary information offered by textural features improves patient stratification and may potentially aid in personalized risk-adaptive therapy.

60 APPLIED LIFE SCIENCES↗