Search NASA⌕ Search

SEARCH · Search NASA

Results for “support vector machine (SVM)”

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 19 records

A support vector machine (SVM) for predicting preferred treatment position in radiotherapy of patients with breast cancer

Purpose: NYU 05-181 protocol compared the CT simulation in both supine and prone positions for 400 patients with breast cancer (200 left-breast and 200 right-breast) to identify which setup is better at sparing heart and lung involvement in the treatment process. The results demonstrated that all right-breast patients benefited from the prone treatment position, while for left-breast patients, 85% were better treated prone and 15% were better treated supine. Using the clinical data collected from this protocol, the authors aimed at developing an automated tool capable of identifying which of the left-breast cancer patients are better treated supine without obtaining a second CT scan in the supine position. Methods: Prone CT scans from 198 of the 200 left-breast cancer patients enrolled in NYU 05-181 protocol were deidentified and exported to a dedicated research planning workstation. Three-dimensional geometric features of the organs at risk and tumor bed were extracted. A two-stage classifier was used to classify patients into the prone class or the supine class. In the first stage, the authors use simple thresholding to divide the patients into two groups based on their in-field heart volume. For patients with in-field heart volume {<=}0.1 cc, the prone position was chosen as the preferred treatment position. Patients with in-field heart volume >0.1 cc will be further classified in the second stage by a weighted support vector machine (SVM). The weight parameters of the SVM were adjusted to maximize the specificity [true-supine/(true-supine+false-prone)] at the cost of lowering but still maintaining reasonable sensitivity [true-prone/(true-prone+false-supine)]. The authors used K-fold cross validations to test the performance of the SVM classifier. A feature selection algorithm was also used to identify features that give the best classification performance. Results: After the first stage, 49 of the 198 left-breast cancer patients were found to have >0.1 cc of in-field heart volume. The three geometric features of heart orientation, distance between heart and tumor, and in-field lung were selected by the feature selection algorithm in the second stage of the two-stage classifier to give the best predefined weighted accuracy. The overall sensitivity and specificity of the proposed method were found to be 90.4% and 99.3%, respectively. Using two-stage classification, the authors reduced the proportion of prone-treated patients that need a second supine CT scan down to 16.3/170 or 9.6%, as compared to 21/170 or 12.4% when the authors use only the first stage (thresholding) for classification. Conclusions: The authors' study showed that a feature-based classifier is feasible for predicting the preferred treatment position, based on features extracted from prone CT scans. The two-stage classifier achieved very high specificity at an acceptable expense of sensitivity.

60 APPLIED LIFE SCIENCES↗

Using a Support Vector Machine (SVM) to Improve Generalization Ability of Load Model Parameters

Load modeling plays an important role in power system stability analysis and planning studies. The parameters of load models may experience variations in different application situations. Choosing appropriate parameters is critical for dynamic simulation and stability studies in power system. This paper presents a method to select the parameters with good generalization ability based on a given large number of available parameters that have been identified from dynamic simulation data in different scenarios. Principal component analysis is used to extract the major features of the given parameter sets. Reduced feature vectors are obtained by mapping the given parameter sets into principal component space. Then support vectors are found by implementing a classification problem. Load model parameters based on the obtained support vectors are built to reflect the dynamic property of the load. All of the given parameter sets were identified from simulation data based on the New England 10-machine 39-bus system, by taking into account different situations, such as load types, fault locations, fault types, and fault clearing time. The parameters obtained by support vector machine have good generalization capability, and can represent the load more accurately in most situations.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Physics-Informed Machine Learning Models for Predicting the Progress of Reactive-Mixing

This paper presents a physics-informed machine learning (ML) framework to construct reduced-order models (ROMs) for reactive-transport quantities of interest (QoIs) based on high-fidelity numerical simu-lations. QoIs include species decay, product yield, and degree of mixing. The ROMs for QoIs are applied to quantify and understand how the chemical species evolve over time. First, high-resolution datasets for constructing ROMs are generated by solving anisotropic reaction-di?usion equations using a non-negative finite element formulation for di?erent input parameters. The reactive-mixing model input parameters are: time-scale associated with flipping of velocity, spatial-scale controlling small/large vortex structures of velocity, perturbation parameter of the vortex-based velocity, anisotropic dispersion strength/contrast, and molecular diffusion. Second, random forests, F-test, and mutual information criterion are used to evaluate the importance of model inputs/features with respect to QoIs. We observed that anisotropic dispersion strength/contrast is the most important feature and time-scale associated with flipping of velocity is the least important feature. Third, Support Vector Machines (SVM) and Support Vector Regression (SVR) are used to construct ROMs based on the model inputs. The constructed SVR-ROMs are then used to predict scaling of QoIs. We also present estimates and inequalities on the QoIs, which inform that the species decay, mix, and produce in an exponential fashion. These inequalities also inform that a radial basis function is the most suitable kernel for the SVM/SVR models for QoIs. It is observed that R2-score for SVR-ROMs on unseen data is greater than 0.9, implying that the SVR-ROMs are able to predict the reaction-diffusion system state reasonably well. Finally, in terms of the computational cost, the proposed SVM-ROMs are O(107) times faster than running a high-fidelity finite element simulation for evaluating QoIs. This makes the proposed ML-based ROMs attractive for reactive-transport sensing and real-time monitoring applications as they are significantly faster yet reasonably accurate.

Mudunuru, Maruti K.↗

A Novel Machine Learning Algorithm for Planetary Boundary Layer Height Estimation Using AERI Measurement Data

Accurately determining the height of the planetary boundary layer (PBL) is important since it can affect the climate, weather, and air quality. Ground-based infrared hyperspectral remote sensing is an effective way to obtain this parameter. Compared with radiosonde measurements, its temporal resolution is much higher. In this study, a method to retrieve the PBL height (PBLH) from the ground-based infrared hyperspectral radiance data is proposed based on machine learning. In this method, the channels that are sensitive to temperature and humidity profiles are selected as the feature vectors, and the PBLHs derived from radiosonde are taken as the true values. The support vector machine (SVM) is applied to train and test the data set, and the parameters are optimized in the process. The data set collected at the Atmospheric Radiation Measurement (ARM) program Southern Great Plains (SGP) from 2012 to 2015 is analyzed. The instruments used in this letter include Atmospheric Emitted Radiance Interferometer (AERI), Vaisala CL31 ceilometer, and radiosonde. It shows that the root mean square error (RMSE) between the PBLHs calculated by the proposed method using AERI data and those from radiosonde data can be within 370 m, and the square correlation coefficient (SCC) is greater than 0.7. Compared with the PBLHs derived from the ceilometer, it can be found that the new method is more stable and less affected by clouds.

54 ENVIRONMENTAL SCIENCES↗

MIC-SVM: Designing A Highly Efficient Support Vector Machine For Advanced Modern Multi-Core and Many-Core Architectures

Support Vector Machine (SVM) has been widely used in data-mining and Big Data applications as modern commercial databases start to attach an increasing importance to the analytic capabilities. In recent years, SVM was adapted to the field of High Performance Computing for power/performance prediction, auto-tuning, and runtime scheduling. However, even at the risk of losing prediction accuracy due to insufficient runtime information, researchers can only afford to apply offline model training to avoid significant runtime training overhead. To address the challenges above, we designed and implemented MICSVM, a highly efficient parallel SVM for x86 based multi-core and many core architectures, such as the Intel Ivy Bridge CPUs and Intel Xeon Phi coprocessor (MIC).

42 ENGINEERING↗

Line Faults Classification Using Machine Learning on Three Phase Voltages Extracted from Large Dataset of PMU Measurements

An end-to-end supervised learning method is developed to classify transmission line faults in a twoyear field-recorded dataset that includes synchronized measurements of three-phase voltages recorded by 38 Phasor Measurement Units (PMU) sparsely located in in the US Western Grid interconnection. Statistical analysis is performed to extract features from this large dataset to train Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) classifiers initially. The training further leverages a simulated dataset from a synthetic grid with 12 PMUs to increase the number of faults of types infrequently seen in the field-recorded dataset. Training the classification models with the combined dataset resulted in a classification accuracy of 97.7%. This is a significant improvement over 89.7% to 92.5% accuracy obtained by relying on the field-recorded dataset alone.

47 OTHER INSTRUMENTATION↗

Benders Cut Classification via Support Vector Machines for Solving Two-Stage Stochastic Programs

In this work, we consider Benders decomposition for solving two-stage stochastic programs with complete recourse based on finite samples of the uncertain parameters. We define the Benders cuts binding at the final optimal solution or the ones significantly improving bounds over iterations as valuable cuts. We propose a learning-enhanced Benders decomposition (LearnBD) algorithm, which adds a cut classification step in each iteration to selectively generate cuts that are more likely to be valuable cuts. The LearnBD algorithm includes two phases: (i) sampling cuts and collecting information from training problems and (ii) solving testing problems with a support vector machine (SVM) cut classifier. We run the LearnBD algorithm on instances of capacitated facility location and multicommodity network design under uncertain demand. Our results show that SVM cut classifier works effectively for identifying valuable cuts, and the LearnBD algorithm reduces the total solving time of all instances for different problems with various sizes and complexities.

97 MATHEMATICS AND COMPUTING↗

Evaluating the Computational Requirements of using SVM software to train Data-Intensive Problems

Support vector machine (SVM) technology is a growing class of computational algorithms for solving classification problems using supervised learning. There are many freely available SVM codes with implementations of varying granularity in the core optimization task. The performance of SVM implementations is related to four key elements; (1) the size and dimension of the data set on which they are operating, (2) the granularity of their core SVM optimization implementation, (3) the kernel transformation applied to the data, and the (4) underlying hardware on which the implementation is running. To assess the performance of different SVM implementations, several freely available codes representing the spectrum of optimization granularity were built on a variety of hardware—two linux clusters, and a shared memory machine. Binary classifiers were trained on datasets of varying size containing anywhere from a few hundred to over 50,000 vectors. Performance of the methods was measured in terms of wall-clock time for training, statistical quality of the resulting classifier, hardware performance (memory footprint, memory bandwidth, floating point unit usage, I/O bandwidth, and instruction stalls), robustness and portability.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Discriminating Tailing Piles using VNIR Imagery and SVMs

This report describes a brief investigation into the use of multispectral satellite imagery and a machine learning technique to discriminate between the soils in two tailing piles in the U1a Complex at the Nevada National Security Site. The south pile dates from the late 1960s and the north pile dates from the early 2000s and is where recent tailings have been dumped. Our approach is to use commercially available satellite imagery of the U1a tailing piles and a Support Vector Machine (SVM) to discriminate between the soils in these piles. Experiments were performed using multispectral pixels selected from around the U1a Complex to train the support vector machine. Pixels in the scene were then classified by the SVM. Classification performance was assessed qualitatively through study of the classification imagery output by the SVM. These qualitative assessments provide the conclusions drawn by the investigation: 1. A SVM can be used to discriminate between different types of materials in satellite imagery. 2. The VNIR imagery used in this investigation does not provide the features needed by the SVM to discriminate between the two tailing piles at the U1a Complex-the soils look too similar in these spectral bands to discriminate. The remainder of the report details the experiments performed to reach these conclusions and the limitations and caveats associated with the conclusions.

97 MATHEMATICS AND COMPUTING↗

A Novel Machine Learning Algorithm for Cloud Detection Using AERI Measurement Data

Infrared hyperspectral remote sensing has been widely used in the field of meteorology. Many scientists have carried out research on inversion methods of meteorological elements such as thermodynamic profile, boundary layer height, cloud base height, etc. In this study, a method based on machine learning for cloud detection using ground-based infrared hyperspectral radiation data is proposed. The features of outliers, the cloudy and cloud-free data of Atmospheric Emitted Radiance Interferometer (AERI) radiation are extracted. The “reference values” of cloudy and cloud-free are determined based on the observation data of Vaisala CL31 ceilometer within the time range of 8 min before the corresponding time of AERI. A support vector machine (SVM) algorithm is used for training. The dataset comes from the Atmospheric Radiation Measurement (ARM) Southern Great Plains (SGP) site and North Slope Alaska (NSA) site from 2015 to 2017, and the ARM West Antarctic Radiation Experiment (AWARE) site in 2016 is also analyzed. The instruments used in this paper include AERI, ceilometer, etc. The experimental results reveal that the agreement of cloud detection results between the proposed algorithm and ceilometer is about 93% at each site. However, for high clouds or optically thin clouds, the agreement will decrease.

47 OTHER INSTRUMENTATION↗

Using support vector machines for anomalous change detonation

We cast anomalous change detection as a binary classification problem, and use a support vector machine (SVM) to build a detector that does not depend on assumptions about the underlying data distribution. To speed up the computation, our SVM is implemented, in part, on a graphical processing unit. Results on real and simulated anomalous changes are used to compare performance to algorithms which effectively assume a Gaussian distribution. In this paper, we investigate the use of support vector machines (SVMs) with radial basis kernels for finding anomalous changes. Compared to typical applications of SVMs, we are operating in a regime of very low false alarm rate. This means that even for relatively large training sets, the data are quite meager in the regime of operational interest. This drives us to use larger training sets, which in turn places more of a computational burden on the SVM. We initially considered three different approaches to to address the need to work in the very low false alarm rate regime. The first is a standard SVM which is trained at one threshold (where more reliable estimates of false alarm rates are possible) and then re-thresholded for the low false alarm rate regime. The second uses the same thresholding approach, but employs a so-called least squares SVM; here a quadratic (instead of a hinge-based) loss function is employed, and for this model, there are good theoretical arguments in favor of adjusting the threshold in a straightforward manner. The third approach employs a weighted support vector machine, where the weights for the two types of errors (false alarm and missed detection) are automatically adjusted to achieve the desired false alarm rate. We have found in previous experiments (not shown here) that the first two types can in some cases work well, while in other cases they do not. This renders both approaches unreliable for automated change detection. By contrast, the third approach reliably produces good results, but at the cost of larger computational requirements caused by the need to estimate very small false alarm rates. To address these computational requirements, we employ a recently developed in-house solver for SVMs that is significantly faster than freely available standard solvers. But these computational issues are secondary to the larger question: do kernelized solutions provide better performance, in terms of detection rates and false alarm rates, than more traditional methods for change detection that effectively assume Gaussian data distributions? To this end, we will compare ROC curves obtained from the SVM with those from chronochrome, covariance equalization, and hyperbolic anomalous change detection.

97 MATHEMATICS AND COMPUTING↗

Protecting Customer Privacy Through Distributed Energy Resource Anonymization

Due to their stochastic nature, the increase of Renewable Energy Resources (RERs) as a primary source of energy for power grids creates challenges regarding the reliability and resilience of the system. In order to combat these obstacles, expansion of Distributed Energy Resources (DERs) and their participation in Demand Response (DR) programs is necessary. Widespread participation requires prioritizing customer privacy and addressing concerns that may arise regarding communication between DERs and the Grid Service Provider (GSP). This paper discusses the use of flow reservation resources to split the operating cycles of DER load profiles into unique phases. The splitting of phases increases anonymization of the DERs by making it more difficult to determine the individual characteristics of the device. We discuss an example of this using simulated DER load profile data and examine the resulting effectiveness by using a machine learning algorithm for classification, called Support Vector Machine (SVM).

Distributed Energy Resource, Anonymization, Renewa↗

Randomized Sampling for Large Data Applications of SVM

A trend in machine learning is the application of existing algorithms to ever-larger datasets. Support Vector Machines (SVM) have been shown to be very effective, but have been difficult to scale to large-data problems. Some approaches have sought to scale SVM training by approximating and parallelizing the underlying quadratic optimization problem. This paper pursues a different approach. Our algorithm, which we call Sampled SVM, uses an existing SVM training algorithm to create a new SVM training algorithm. It uses randomized data sampling to better extend SVMs to large data applications. Experiments on several datasets show that our method is faster than and comparably accurate to both the original SVM algorithm it is based on and the Cascade SVM, the leading data organization approach for SVMs in the literature. Further, we show that our approach is more amenable to parallelization than Cascade SVM.

large data↗

SVM-Based Parameter Identification for Composite ZIP and Electronic Load Modeling

This paper proposes a parameter identification technique for composite ZIP and electronic loads by leveraging the support vector machine (SVM) approach. Since the active power and the reactive power of electronic loads are piecewise functions of the voltage magnitude, the operating modes of electronic loads are determined by the voltage magnitude. To improve the accuracy of parameter identification, two filters (Hampel and Savitzky–Golay) are employed to preprocess measurements to reduce noise. The data after noise reduction serve as training data for the regression model that is solved by the SVM approach. Numerical results show that the SVM approach with filters can identify the parameters of the composite ZIP and electronic load model with high accuracy

Electronic load↗

SU-F-J-207: Non-Small Cell Lung Cancer Patient Survival Prediction with Quantitative Tumor Textures Analysis in Baseline CT

Purpose: Chemo-radiation therapy (CRT) is widely used in treating patients with locally advanced non-small cell lung cancer (NSCLC). Determination of the likelihood of patient response to treatment and optimization of treatment regime is of clinical significance. Up to date, no imaging biomarker has reliably correlated to NSCLC patient survival rate. This pilot study is to extract CT texture information from tumor regions for patient survival prediction. Methods: Thirteen patients with stage II-III NSCLC were treated using CRT with a median dose of 6210 cGy. Non-contrast-enhanced CT images were acquired for treatment planning and retrospectively collected for this study. Texture analysis was applied in segmented tumor regions using the Local Binary Pattern method (LBP). By comparing its HU with neighboring voxels, the LBPs of a voxel were measured in multiple scales with different group radiuses and numbers of neighbors. The LBP histograms formed a multi-dimensional texture vector for each patient, which was then used to establish and test a Support Vector Machine (SVM) model to predict patients’ one year survival. The leave-one-out cross validation strategy was used recursively to enlarge the training set and derive a reliable predictor. The predictions were compared with the true clinical outcomes. Results: A 10-dimensional LBP histogram was extracted from 3D segmented tumor region for each of the 13 patients. Using the SVM model with the leave-one-out strategy, only 1 out of 13 patients was misclassified. The experiments showed an accuracy of 93%, sensitivity of 100%, and specificity of 86%. Conclusion: Within the framework of a Support Vector Machine based model, the Local Binary Pattern method is able to extract a quantitative imaging biomarker in the prediction of NSCLC patient survival. More patients are to be included in the study.

60 APPLIED LIFE SCIENCES↗

TU-FG-209-12: Treatment Site and View Recognition in X-Ray Images with Hierarchical Multiclass Recognition Models

Purpose: To investigate an approach of automatically recognizing anatomical sites and imaging views (the orientation of the image acquisition) in 2D X-ray images. Methods: A hierarchical (binary tree) multiclass recognition model was developed to recognize the treatment sites and views in x-ray images. From top to bottom of the tree, the treatment sites are grouped hierarchically from more general to more specific. Each node in the hierarchical model was designed to assign images to one of two categories of anatomical sites. The binary image classification function of each node in the hierarchical model is implemented by using a PCA transformation and a support vector machine (SVM) model. The optimal PCA transformation matrices and SVM models are obtained by learning from a set of sample images. Alternatives of the hierarchical model were developed to support three scenarios of site recognition that may happen in radiotherapy clinics, including two or one X-ray images with or without view information. The performance of the approach was tested with images of 120 patients from six treatment sites – brain, head-neck, breast, lung, abdomen and pelvis – with 20 patients per site and two views (AP and RT) per patient. Results: Given two images in known orthogonal views (AP and RT), the hierarchical model achieved a 99% average F1 score to recognize the six sites. Site specific view recognition models have 100 percent accuracy. The computation time to process a new patient case (preprocessing, site and view recognition) is 0.02 seconds. Conclusion: The proposed hierarchical model of site and view recognition is effective and computationally efficient. It could be useful to automatically and independently confirm the treatment sites and views in daily setup x-ray 2D images. It could also be applied to guide subsequent image processing tasks, e.g. site and view dependent contrast enhancement and image registration. The senior author received research grants from ViewRay Inc. and Varian Medical System.

60 APPLIED LIFE SCIENCES↗

MapReduce SVM Game

Despite technological advances making computing devices faster, smaller, and more prevalent in today's age, data generation and collection has outpaced data processing capabilities. Simply having more compute platforms does not provide a means of addressing challenging problems in the big data era. Rather, alternative processing approaches are needed and the application of machine learning to big data is hugely important. The MapReduce programming paradigm is an alternative to conventional supercomputing approaches, and requires less stringent data passing constrained problem decompositions. Rather, MapReduce relies upon defining a means of partitioning the desired problem so that subsets may be computed independently and recom- bined to yield the net desired result. However, not all machine learning algorithms are amenable to such an approach. Game-theoretic algorithms are often innately distributed, consisting of local interactions between players without requiring a central authority and are iterative by nature rather than requiring extensive retraining. Effectively, a game-theoretic approach to machine learning is well suited for the MapReduce paradigm and provides a novel, alternative new perspective to addressing the big data problem. In this paper we present a variant of our Support Vector Machine (SVM) Game classifier which may be used in a distributed manner, and show an illustrative example of applying this algorithm.

97 MATHEMATICS AND COMPUTING↗