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 703 records · Page 39
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Anomaly Identification of Synchronized Voltage Waveform for Situational Awareness of Low Inertia Systems

Inverter-based resources (IBRs) such as photovoltaics (PVs), wind turbines, and battery energy storage systems (BESSs) are widely deployed in low-carbon power systems. However, these resources typically do not provide the inertia needed for grid stability, resulting in a low-inertia power system. IBRs and lack of inertia have been known to cause anomalies such as waveform distortions and wideband oscillations in power systems due to the limited inertia level, leading to increased generation trips and load shedding. Here, to achieve effective anomaly identification, this paper proposes a synchro-waveform-based algorithm utilizing real-time synchronized voltage waveform measurements from waveform measurement units (WMUs). In the proposed method, different physical characteristics, as well as statistical features, are extracted from synchronized voltage waveform measurements to filter anomalies. Then, the anomaly identification approach based on the random forest is developed and deployed into the FNET/GridEye system considering trade-offs among accuracy, computational burden, and deployment cost. Moreover, four WMUs are specially designed and deployed on Kauai Island to receive instantaneous synchronized voltage waveform measurements. To verify the performance of the proposed algorithm, different experiments are carried out with collected field test data. The result demonstrates that the performance of the proposed synchro-waveform-based anomaly categorization algorithm can accurately identify anomalies 95.35% of the time, which has comparable performance among benchmarking algorithms.

Situational awareness↗
DOE OSTI2023

A Novel Spatial-Temporal Variational Quantum Circuit to Enable Deep Learning on NISQ Devices

Quantum computing presents a promising approach for machine learning with its capability for extremely parallel computation in high-dimension through superposition and entanglement. Despite its potential, existing quantum learning algorithms, such as Variational Quantum Circuits (VQCs), face challenges in handling more complex datasets, particularly those that are not linearly separable. What’s more, it encounters the deployability issue, making the learning models suffer a drastic accuracy drop after deploying them to the actual quantum devices. To overcome these limitations, this paper proposes a novel spatial-temporal design, namely “ST-VQC”, to integrate nonlinearity in quantum learning and improve the robustness of the learning model to noise. Specifically, ST-VQC can extract spatial features via a novel block-based encoding quantum sub-circuit coupled with a layer-wise computation quantum sub-circuit to enable temporal-wise deep learning. Additionally, a SWAP-Free physical circuit design is devised to improve robustness. These designs bring a number of hyperparameters. After a systematic analysis of the design space for each design component, an automated optimization framework is proposed to generate the ST-VQC quantum circuit. The proposed ST-VQC has been evaluated on two IBM quantum processors, ibm-cairo with 27 qubits and ibmq-lima with 7 qubits to assess its effectiveness. The results of the evaluation on the standard dataset for binary classification show that ST-VQC can achieve over 30% accuracy improvement compared with existing VQCs on actual quantum computers. Moreover, on a non-linear synthetic dataset, the STVQC outperforms a linear classifier by 27.9%, while the linear classifier using classical computing outperforms the existing VQC by 15.58%.

Li, Jinyang↗
NASA NTRS1983

Effects of preprocessing Landsat MSS data on derived features

Important to the use of multitemporal Landsat MSS data for earth resources monitoring, such as agricultural inventories, is the ability to minimize the effects of varying atmospheric and satellite viewing conditions, while extracting physically meaningful features from the data. In general, the approaches to the preprocessing problem have been derived from either physical or statistical models. This paper compares three proposed algorithms; XSTAR haze correction, Color Normalization, and Multiple Acquisition Mean Level Adjustment. These techniques represent physical, statistical, and hybrid physical-statistical models, respectively. The comparisons are made in the context of three feature extraction techniques; the Tasseled Cap, the Cate Color Cube. and Normalized Difference.

Parris, T. M.↗
DOE OSTI2016

SU-F-R-30: Interscanner Variability of Radiomics Features in Computed Tomography (CT) Using a Standard ACR Phantom

Purpose: A simple approach to investigate Interscanner variability of Radiomics features in computed tomography (CT) using a standard ACR phantom. Methods: The standard ACR phantom was scanned on CT scanners from three different manufacturers. Scanning parameters of 120 KVp, 200 mA were used while slice thickness of 3.0 mm on two scanners and 3.27 mm on third scanner was used. Three spherical regions of interest (ROI) from water, medium density and high density inserts were contoured. Ninety four Radiomics features were extracted using an in-house program. These features include shape (11), intensity (22), GLCM (26), GLZSM (11), RLM (11), and NGTDM (5) and 8 fractal dimensions features. To evaluate the Interscanner variability across three scanners, a coefficient of variation (COV) is calculated for each feature group. Each group is further classified according to the COV- by calculating the percentage of features in each of the following categories: COV less than 2%, between 2 and 10% and greater than 10%. Results: For all feature groups, similar trend was observed for three different inserts. Shape features were the most robust for all scanners as expected. 70% of the shape features had COV <2%. For intensity feature group, 2% COV varied from 9 to 32% for three scanners. All features in four groups GLCM, GLZSM, RLM and NGTDM were found to have Interscanner variability ≥2%. The fractal dimensions dependence for medium and high density inserts were similar while it was different for water inserts. Conclusion: We concluded that even for similar scanning conditions, Interscanner variability across different scanners was significant. The texture features based on GLCM, GLZSM, RLM and NGTDM are highly scanner dependent. Since the inserts of the ACR Phantom are not heterogeneous in HU values suggests that matrix based 2nd order features are highly affected by variation in noise. Research partly funded by NIH/NCI R01CA190105-01.

60 APPLIED LIFE SCIENCES↗
NASA NTRS1991

An evaluation of techniques for the extraction of mineral absorption features from high spectral resolution remote sensing data

Airborne Visible/Infrared Imaging Spectrometer data covering the wavelength range between 2000 and 2400 nm are examined for their ability to display the diagnostic mineral absorption features of certain alteration minerals, employing various data processing techniques. The techniques may be separated into two broad categories: scene based techniques that use parameters derived from the data themselves, and correction techniques utilizing external information such as solar/atmospheric models. Results indicate that the data corrected utilizing the LOWTRAN 7 atmospheric transfer code constrained with local weather station data are the most effective at showing the diagnostic absorption features of the regions of known mineralogy and introduce the least number of artifacts into the data.

Rast, Michael↗
NASA NTRS2005

Noise, Edge Extraction and Visibility of Features

Noise, whether due to the image-gathering device or some other reason, reduces the visibility of fine features in an image. Several techniques attempt to mitigate the impact of noise by performing a low-pass filtering operation on the acquired data. This is based on the assumption that the uncorrelated noise has high-frequency content and thus will be suppressed by low-pass filtering. A result of this operation is that edges in a noisy image also tend to get blurred, and, in some cases, may get completely lost due to the low-pass filtering. In this paper, we quantitatively assess the impact of noise on fine feature visibility by using computer-generated targets of known spatial detail. Additionally, we develop a new scheme for noise-reduction based on the connectivity of edge-features. The overall impact of this scheme is to reduce overall noise, yet retain the high frequency content that make edge-features sharp.

Rahman, Zia-ur↗
NASA NTRS1985

Maximum likelihood classification of synthetic aperture radar imagery

Classification of synthetic aperture radar (SAR) images has important applications in geology, agriculture, and the military. A statistical model for SAR images is reviewed and a maximum likelihood classification algorithm developed for the classification of agricultural fields based on the model. It is first assumed that the target feature information is known a priori. The performance of the algorithm is then evaluated in terms of the probability of incorrect classification. A technique is also presented to extract the needed feature information from a SAR image; then both the feature extraction and the maximum likelihood classification algorithms are tested on a SEASAT-A SAR image.

Frost, V. S.↗
DOE OSTI2019

Cross-source sensing data fusion for building occupancy prediction with adaptive lasso feature filtering

Fusing various sensing data sources can significantly improve the accuracy and reliability of building occupancy detection. Fusing environmental sensors and wireless network signals are seldom studied for its computational and technical complexity. Here, this study aims to propose an integrated adaptive lasso model that is able to extract critical data features for environmental and Wi-Fi probe dual sensing sources. Through rapid feature extraction and process simplification, the proposed method aims to improve the computational efficiency of occupancy detecting models. To validate the proposed model, an onsite experiment was conducted to examine two occupancy data resolutions, (real-time and four-level occupancy resolutions). The results suggested that, among all twelve features, eight features are most relevant. The mean absolute error of the real-time occupancy can be reduced to 2.18 and F1_accuracy is about 84.36% for the four-level occupancy.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2015

TU-CD-BRB-10: 18F-FDG PET Image-Derived Tumor Features Highlight Altered Pathways Identified by Trancriptomic Analysis in Head and Neck Cancer

Purpose: Several quantitative features can be extracted from 18F-FDG PET images, such as standardized uptake values (SUVs), metabolic tumor volume (MTV), shape characterization (SC) or intra-tumor radiotracer heterogeneity quantification (HQ). Some of these features calculated from baseline 18F-FDG PET images have shown a prognostic and predictive clinical value. It has been hypothesized that these features highlight underlying tumor patho-physiological processes at smaller scales. The objective of this study was to investigate the ability of recovering alterations of signaling pathways from FDG PET image-derived features. Methods: 52 patients were prospectively recruited from two medical centers (Brest and Poitiers). All patients underwent an FDG PET scan for staging and biopsies of both healthy and primary tumor tissues. Biopsies went through a transcriptomic analysis performed in four spates on 4×44k chips (Agilent™). Primary tumors were delineated in the PET images using the Fuzzy Locally Adaptive Bayesian algorithm and characterized using 10 features including SUVs, SC and HQ. A module network algorithm followed by functional annotation was exploited in order to link PET features with signaling pathways alterations. Results: Several PET-derived features were found to discriminate differentially expressed genes between tumor and healthy tissue (fold-change >2, p<0.01) into 30 co-regulated groups (p<0.05). Functional annotations applied to these groups of genes highlighted associations with well-known pathways involved in cancer processes, such as cell proliferation and apoptosis, as well as with more specific ones such as unsaturated fatty acids. Conclusion: Quantitative features extracted from baseline 18F-FDG PET images usually exploited only for diagnosis and staging, were identified in this work as being related to specific altered pathways and may show promise as tools for personalizing treatment decisions.

60 APPLIED LIFE SCIENCES↗
NASA NTRS2018

Advances in Hyperspectral Image Classification Methods for Vegetation and Agricultural Cropland Studies

Hyperspectral data are becoming more widely available via sensors on airborne and unmanned aerial vehicle (UAV) platforms, as well as proximal platforms. While space-based hyperspectral data continue to be limited in availability, multiple spaceborne Earth-observing missions on traditional platforms are scheduled for launch, and companies are experimenting with small satellites for constellations to observe the Earth, as well as for planetary missions. Land cover mapping via classification is one of the most important applications of hyperspectral remote sensing and will increase in significance as time series of imagery are more readily available. However, while the narrow bands of hyperspectral data provide new opportunities for chemistry-based modeling and mapping, challenges remain. Hyperspectral data are high dimensional, and many bands are highly correlated or irrelevant for a given classification problem. For supervised classification methods, the quantity of training data is typically limited relative to the dimension of the input space. The resulting Hughes phenomenon, often referred to as the curse of dimensionality, increases potential for unstable parameter estimates, overfitting, and poor generalization of classifiers. This is particularly problematic for parametric approaches such as Gaussian maximum likelihood–based classifiers that have been the backbone of pixel-based multispectral classification methods. This issue has motivated investigation of alternatives, including regularization of the class covariance matrices, ensembles of weak classifiers, development of feature selection and extraction methods, adoption of nonparametric classifiers, and exploration of methods to exploit unlabeled samples via semi-supervised and active learning. Data sets are also quite large, motivating computationally efficient algorithms and implementations. This chapter provides an overview of the recent advances in classification methods for mapping vegetation using hyperspectral data. Three data sets that are used in the hyperspectral classification literature (e.g., Botswana Hyperion satellite data and AVIRIS airborne data over both Kennedy Space Center and Indian Pines) are described in Section 3.2 and used to illustrate methods described in the chapter. An additional high-resolution hyperspectral data set acquired by a SpecTIR sensor on an airborne platform over the Indian Pines area is included to exemplify the use of new deep learning approaches, and a multiplatform example of airborne hyperspectral data is provided to demonstrate transfer learning in hyperspectral image classification. Classical approaches for supervised and unsupervised feature selection and extraction are reviewed in Section 3.3. In particular, nonlinearities exhibited in hyperspectral imagery have motivated development of nonlinear feature extraction methods in manifold learning, which are outlined in Section 3.3.1.4. Spatial context is also important in classification of both natural vegetation with complex textural patterns and large agricultural fields with significant local variability within fields. Approaches to exploit spatial features at both the pixel level (e.g., co-occurrence–based texture and extended morphological attribute profiles [EMAPs]) and integration of segmentation approaches (e.g., HSeg) are discussed in this context in Section 3.3.2. Recently, classification methods that leverage nonparametric methods originating in the machine learning community have grown in popularity. An overview of both widely used and newly emerging approaches, including support vector machines (SVMs), Gaussian mixture models, and deep learning based on convolutional neural networks is provided in Section 3.4. Strategies to exploit unlabeled samples, including active learning and metric learning, which combine feature extraction and augmentation of the pool of training samples in an active learning framework, are outlined in Section 3.5. Integration of image segmentation with classification to accommodate spatial coherence typically observed in vegetation is also explored, including as an integrated active learning system. Exploitation of multisensor strategies for augmenting the pool of training samples is investigated via a transfer learning framework in Section 3.5.1.2. Finally, we look to the future, considering opportunities soon to be provided by new paradigms, as hyperspectral sensing is becoming common at multiple scales from ground-based and airborne autonomous vehicles to manned aircraft and space-based platforms.

Pasolli, Edoardo↗
DOE OSTI2015

SU-E-J-256: Predicting Metastasis-Free Survival of Rectal Cancer Patients Treated with Neoadjuvant Chemo-Radiotherapy by Data-Mining of CT Texture Features of Primary Lesions

Purpose: The purpose of this study is to investigate the relationship between computed tomographic (CT) texture features of primary lesions and metastasis-free survival for rectal cancer patients; and to develop a datamining prediction model using texture features. Methods: A total of 220 rectal cancer patients treated with neoadjuvant chemo-radiotherapy (CRT) were enrolled in this study. All patients underwent CT scans before CRT. The primary lesions on the CT images were delineated by two experienced oncologists. The CT images were filtered by Laplacian of Gaussian (LoG) filters with different filter values (1.0–2.5: from fine to coarse). Both filtered and unfiltered images were analyzed using Gray-level Co-occurrence Matrix (GLCM) texture analysis with different directions (transversal, sagittal, and coronal). Totally, 270 texture features with different species, directions and filter values were extracted. Texture features were examined with Student’s t-test for selecting predictive features. Principal Component Analysis (PCA) was performed upon the selected features to reduce the feature collinearity. Artificial neural network (ANN) and logistic regression were applied to establish metastasis prediction models. Results: Forty-six of 220 patients developed metastasis with a follow-up time of more than 2 years. Sixtyseven texture features were significantly different in t-test (p<0.05) between patients with and without metastasis, and 12 of them were extremely significant (p<0.001). The Area-under-the-curve (AUC) of ANN was 0.72, and the concordance index (CI) of logistic regression was 0.71. The predictability of ANN was slightly better than logistic regression. Conclusion: CT texture features of primary lesions are related to metastasisfree survival of rectal cancer patients. Both ANN and logistic regression based models can be developed for prediction.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2015

TU-AB-BRA-06: Texture Feature Reproducibility Between PET/CT and PET/MR Imaging Modalities

Purpose: Radiomics involves the extraction of texture features from different imaging modalities with the purpose of developing models to predict patient treatment outcomes. The purpose of this study is to investigate texture feature reproducibility across [18F]FDG PET/CT and [18F]FDG PET/MR imaging in patients with primary malignancies. Methods: Twenty five prospective patients with solid tumors underwent clinical [18F]FDG PET/CT scan followed by [18F]FDG PET/MR scans. In all patients the lesions were identified using nuclear medicine reports. The images were co-registered and segmented using an in-house auto-segmentation method. Fifty features, based on the intensity histogram, second and high order matrices, were extracted from the segmented regions from both image data sets. One-way random-effects ANOVA model of the intra-class correlation coefficient (ICC) was used to establish texture feature correlations between both data sets. Results: Fifty features were classified based on their ICC values, which were found in the range from 0.1 to 0.86, in three categories: high, intermediate, and low. Ten features extracted from second and high-order matrices showed large ICC ≥ 0.70. Seventeen features presented intermediate 0.5 ≤ ICC ≤ 0.65 and the remaining twenty three presented low ICC ≤ 0.45. Conclusion: Features with large ICC values could be reliable candidates for quantification as they lead to similar results from both imaging modalities. Features with small ICC indicates a lack of correlation. Therefore, the use of these features as a quantitative measure will lead to different assessments of the same lesion depending on the imaging modality from where they are extracted. This study shows the importance of the need for further investigation and standardization of features across multiple imaging modalities.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2014

TU-A-12A-10: Robust Radiomics Feature Quantification Using Semiautomatic Volumetric Segmentation

Purpose: Recent advances in medical imaging technologies provide opportunities to quantify the tumor phenotype throughout the course of treatment non-invasively. The emerging field of Radiomics addresses this by converting medical images into minable data by applying a large number of quantitative imaging algorithms. Accurate tumor segmentation is one of the main challenges of Radiomics. It has been shown that semiautomatic segmentation approaches efficiently reduce inter-observer variability as compared to the time consuming manual delineations. In this study, a semiautomatic volumetric segmentation algorithm, implemented in the free and publicly available 3D-Slicer platform, was investigated in terms of its robustness for Radiomics features quantification. Methods: Fifty-six 3D-Radiomics features, quantifying phenotypic differences based on the tumor intensity, shape and texture, were extracted from the computed tomography images of twenty lung cancer patients. These Radiomics features were derived from the 3D-tumor volumes defined by three independent observers twice using 3D-Slicer, and compared to manual slice-by-slice delineations of five independent physicians in terms of intra-class correlation coefficient (ICC) and feature range. Results: Radiomics features extracted from 3D-Slicer segmentations had significantly higher reproducibility (ICC= 0.85 0.15, p=0.0009) compared to the features extracted from the manual segmentations (ICC= 0.77 0.17). Furthermore, the features extracted from 3D-Slicer based segmentations, spread over significantly smaller range across observers as compared to those of the manual delineations (p= 3.819e-07). Moreover, the features derived from 3D-Slicer segmentations overlapped in range with those of the manual delineations, as the lower(higher) limit(s) being significantly higher(lower) for the 3D-Slicer features (p= 0.007, p= 5.863e-06). Conclusion: 3D-Slicer based semiautomatic segmentation significantly improves the robustness of radiomics features and thus could serve as a potential alternative to the time consuming manual segmentation process. So 3D-Slicer can have a large application in Radiomics, and be employed for high-throughput data mining research of medical imaging in clinical oncology.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

SU-D-204-01: A Methodology Based On Machine Learning and Quantum Clustering to Predict Lung SBRT Dosimetric Endpoints From Patient Specific Anatomic Features

Purpose: To develop a data-mining methodology based on quantum clustering and machine learning to predict expected dosimetric endpoints for lung SBRT applications based on patient-specific anatomic features. Methods: Ninety-three patients who received lung SBRT at our clinic from 2011–2013 were retrospectively identified. Planning information was acquired for each patient, from which various features were extracted using in-house semi-automatic software. Anatomic features included tumor-to-OAR distances, tumor location, total-lung-volume, GTV and ITV. Dosimetric endpoints were adopted from RTOG-0195 recommendations, and consisted of various OAR-specific partial-volume doses and maximum point-doses. First, PCA analysis and unsupervised quantum-clustering was used to explore the feature-space to identify potentially strong classifiers. Secondly, a multi-class logistic regression algorithm was developed and trained to predict dose-volume endpoints based on patient-specific anatomic features. Classes were defined by discretizing the dose-volume data, and the feature-space was zero-mean normalized. Fitting parameters were determined by minimizing a regularized cost function, and optimization was performed via gradient descent. As a pilot study, the model was tested on two esophageal dosimetric planning endpoints (maximum point-dose, dose-to-5cc), and its generalizability was evaluated with leave-one-out cross-validation. Results: Quantum-Clustering demonstrated a strong separation of feature-space at 15Gy across the first-and-second Principle Components of the data when the dosimetric endpoints were retrospectively identified. Maximum point dose prediction to the esophagus demonstrated a cross-validation accuracy of 87%, and the maximum dose to 5cc demonstrated a respective value of 79%. The largest optimized weighting factor was placed on GTV-to-esophagus distance (a factor of 10 greater than the second largest weighting factor), indicating an intuitively strong correlation between this feature and both endpoints. Conclusion: This pilot study shows that it is feasible to predict dose-volume endpoints based on patient-specific anatomic features. The developed methodology can potentially help to identify patients at risk for higher OAR doses, thus improving the efficiency of treatment planning. R01-184173.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Assessment of Machine Learning for Ultrasonic Nondestructive Evaluation of Alkali–Silica Reaction in Concrete

Alkali–silica reaction (ASR) is a type of material degradation in concrete structures that leads to concrete cracking and rebar corrosion, thereby reducing the material’s structural integrity and the overall structure’s lifetime and raising safety concerns. Ultrasonic nondestructive evaluation (NDE) has been proven to be a valuable technique for assessing concrete properties and monitoring ASR progression in concrete. However, the deployment and analysis of ultrasonic NDE and its data requires specialized expertise, often relying on the engineer’s subjective interpretation. With the surge in computational power, artificial intelligence (AI) and machine learning (ML) algorithms have become popular in automating NDE data analysis. Various industrial sectors are increasingly adopting ML algorithms for NDE data analysis with a growing emphasis on AI–assisted automation. Regulatory agencies are also preparing for this technological shift, anticipating corresponding revisions in standards. Thus, there is an urgent need to identify the capabilities and limitations of current ML technologies for the evaluation of concrete material properties and damage status. Furthermore, the effects of various factors on ML model performance must be thoroughly investigated. The study summarized herein evaluated the effectiveness of two ML models (i.e., support vector regression (SVR) and deep neural network (DNN)) in predicting concrete material damage induced by ASR based on the long-term ultrasonic monitoring data. Four distinct concrete specimens were cast with artificially induced ASR, and over a period exceeding 500 days, ultrasonic signals and expansion data were continuously collected. For the SVR model, wave velocity and 12 other wave features were extracted from the ultrasonic signals, with 6 out of 13 features selected as input for the model. Different combinations of training and testing datasets were designed to explore factors influencing prediction performance, including the range of data within training and testing sets, in addition to various signal preprocessing methodologies. These findings suggest the importance of using a training dataset with a broader data range compared with testing datasets for improved model performance alongside consistent signal preprocessing across datasets.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Phasor-Measurement-Unit-Based Data Analytics Using Digital Twin and PhasorAnalytics Software

A major objective of this project was to apply GE’s commercial machine learning and data analytics toolsets to large-scale, real-world, anonymized Phasor Measurement Unit (PMU) datasets in order to extract signatures, correlated and/or causal factors, and precursor patterns associated with significant power system phenomena. The project had a particular emphasis on extraction of insights relevant to asset health monitoring, real-time load modeling and cybersecurity monitoring. Additionally, the team was directed to undertake a comprehensive data quality analysis for the provided datasets and encouraged to estimate the ‘machine-learning readiness’ of the datasets by documenting any major obstacles to the application of commercial machine learning algorithms. To accomplish the aforementioned objectives, the project team’s work centered around the identification of key event signatures and application of the identified event signatures for event detection and event classification. The industry-validated, semi-supervised machine learning strategy employed for event signature identification involved several major tasks, including data-preprocessing, generation of an overabundance of features, normal data identification, normality modeling, and event signature identification through a methodical, quantitative ranking of features in order of relevance to each studied event type. Throughout the project, data quality issues and mitigation techniques were investigated. In this report, insights are provided regarding the readiness of the provided synchrophasor datasets for application of machine learning and data analytics. The methodologies employed for this technical strategy are summarized in this report. With regards to data preprocessing and feature generation, the provided Training and Test Datasets were ingested into GE’s big data environment. Subsequently, the team applied bad data cleansing and data imputation scripts, event detection scripts, and application programming interfaces (APIs) to the datasets for convenient data access. The project team completed development and validation of dozens of physics-based, statistics-based and transformation-based feature functions used for the extraction of over 60 synchrophasor features. Using a new parallel feature generation technology developed on this project, over 60 features have been rapidly generated for the full two years’ worth of Training and Test Dataset data associated with both the Eastern and Western interconnects. Even accommodating for temporal down-sampling inherent to the feature extraction procedure, this parallel feature generation activity resulted in a massive feature set with a storage requirement approximately equal to that of the raw training dataset itself. With regards to normal data identification and normality modeling, a normality model was built using the feature data extracted from the Training Dataset and iteratively refined subsequent to incremental adjustments and expansions of the Training Dataset feature data. With respect to event characterization and signature identification, an event signature identification pipeline was developed and used in conjunction with the normality model to identify over 15 event signatures for key event categories within the Training Dataset. The identified event signatures were used to characterize hundreds of key events in terms of relative severity, duration, and location of the event. An investigation was undertaken to identify correlated and causal factors involved in transformer events. A separate investigation into temporal trends in ring-down analysis results was undertaken to determine possible associations between system dynamics and various other factors such as loading, season or year. To validate the identified event signatures, additional work was undertaken to develop signature-based anomaly detection and classification tools suitable for convenient application to the synchrophasor datasets. The anomaly detection and classification tools, suitable for online application, were then applied to the entirety of the Eastern Interconnect Training and Test Datasets. Performance of the event detection and classification tools was evaluated upon receipt of the Test Dataset event logs (i.e., the labels for events contained in the Test Dataset), and promising results were obtained despite several challenges (documented herein) associated with application of supervised or semi-supervised machine learning methods to large-scale, anonymized datasets. Finally, the detection and classification tools were used to detect, classify, and characterize thousands of new events not included in the original event logs provided by the DOE within both the Training and Test Datasets.

24 POWER TRANSMISSION AND DISTRIBUTION↗