scispace - formally typeset
Search or ask a question
Institution

General Electric

CompanyBoston, Massachusetts, United States
About: General Electric is a company organization based out in Boston, Massachusetts, United States. It is known for research contribution in the topics: Turbine & Rotor (electric). The organization has 76365 authors who have published 110557 publications receiving 1885108 citations. The organization is also known as: General Electric Company & GE.
Topics: Turbine, Rotor (electric), Signal, Combustor, Coating


Papers
More filters
Posted ContentDOI
Spyridon Bakas1, Mauricio Reyes, Andras Jakab2, Stefan Bauer3  +435 moreInstitutions (111)
TL;DR: This study assesses the state-of-the-art machine learning methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018, and investigates the challenge of identifying the best ML algorithms for each of these tasks.
Abstract: Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumoris a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses thestate-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST/RANO criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that underwent gross tota lresection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset.

1,165 citations

Journal ArticleDOI
C. D. Doyle1
TL;DR: The kinetic analysis of the thermogram, by use of either its exact equation or a more convenient approximation formula, is straightforward in cases of volatilization via simple kinetics as mentioned in this paper.
Abstract: Thermogravimetric data are generally more extensive than are comparable isothermal aging data, and therefore afford preliminary kinetic information in greater abundance. The kinetic analysis of the thermogram, by use of either its exact equation or a more convenient approximation formula, is straightforward in cases of volatilization via simple kinetics. Application of the analytical procedure to the thermogram for the zero-order volatilization of octamethylcyclotetrasiloxane yielded an estimate of 11.65 kcal./mole as the average heat of vaporization in the temperature range of 80 to 145°C. The apparent activation energy for the first-order pyrolytic volatilization of 200-mg. samples of pulverized polytetrafluoroethylene was estimated to be 66 to 68 kcal./mole in the temperature range of 520 to 610°C.

1,136 citations

Journal ArticleDOI
TL;DR: Langtry et al. as discussed by the authors developed a new correlation-based transition model based strictly on local variables, which is compatible with modern computational fluid dynamics (CFD) approaches, such as unstructured grids and massive parallel execution.
Abstract: A new correlation-based transition model has been developed, which is based strictly on local variables. As a result, the transition model is compatible with modern computational fluid dynamics (CFD) approaches, such as unstructured grids and massive parallel execution. The model is based on two transport equations, one for intermittency and one for the transition onset criteria in terms of momentum thickness Reynolds number. The proposed transport equations do not attempt to model the physics of the transition process (unlike, e.g., turbulence models) but form a framework for the implementation of correlation-based models into general-purpose CFD methods. Part I (this part) of this paper gives a detailed description of the mathematical formulation of the model and some of the basic test cases used for model validation, including a two-dimensional turbine blade. Part II (Langtry, R. B., Menter, F. R., Likki, S. R., Suzen, Y. B., Huang, P. G., and Volker, S., 2006, ASME J. Turbomach., 128(3), pp. 423–434) of the paper details a significant number of test cases that have been used to validate the transition model for turbomachinery and aerodynamic applications. The authors believe that the current formulation is a significant step forward in engineering transition modeling, as it allows the combination of correlation-based transition models with general purpose CFD codes.

1,131 citations

Proceedings ArticleDOI
14 May 2017
TL;DR: In this article, the authors proposed a simple but strong baseline for time series classification from scratch with deep neural networks, which is pure end-to-end without any heavy preprocessing on the raw data or feature crafting.
Abstract: We propose a simple but strong baseline for time series classification from scratch with deep neural networks. Our proposed baseline models are pure end-to-end without any heavy preprocessing on the raw data or feature crafting. The proposed Fully Convolutional Network (FCN) achieves premium performance to other state-of-the-art approaches and our exploration of the very deep neural networks with the ResNet structure is also competitive. The global average pooling in our convolutional model enables the exploitation of the Class Activation Map (CAM) to find out the contributing region in the raw data for the specific labels. Our models provides a simple choice for the real world application and a good starting point for the future research. An overall analysis is provided to discuss the generalization capability of our models, learned features, network structures and the classification semantics.

1,131 citations

Journal ArticleDOI
R. H. Park1
TL;DR: Starting with the basic assumption of no saturation or hysteresis, and with distribution of armature phase m.
Abstract: Starting with the basic assumption of no saturation or hysteresis, and with distribution of armature phase m. m. f. effectively sinusoidal as far as regards phenomena dependent upon rotor position, general formulas are developed for current, voltage, power, and torque under steady and transient load conditions. Special detailed formulas are also developed which permit the determination of current and torque on three-phase short circuit, during starting, and when only small deviations from an average operating angle are involved. In addition, new and more accurate equivalent circuits are developed for synchronous and asynchronous machines operating in parallel, and the domain of validity of such circuits is established. Throughout, the treatment has been generalized to include salient poles and an arbitrary number of rotor circuits. The analysis is thus adapted to machines equipped with field pole collars, or with amortisseur windings of any arbitrary construction. It is proposed to continue the analysis in a subsequent paper.

1,114 citations


Authors

Showing all 76370 results

NameH-indexPapersCitations
Cornelia M. van Duijn1831030146009
Krzysztof Matyjaszewski1691431128585
Gary H. Glover12948677009
Mark E. Thompson12852777399
Ron Kikinis12668463398
James E. Rothman12535860655
Bo Wang119290584863
Wei Lu111197361911
Harold J. Vinegar10837930430
Peng Wang108167254529
Hans-Joachim Freund10696246693
Carl R. Woese10527256448
William J. Koros10455038676
Thomas A. Lipo10368243110
Gene H. Golub10034257361
Network Information
Related Institutions (5)
Massachusetts Institute of Technology
268K papers, 18.2M citations

86% related

Bell Labs
59.8K papers, 3.1M citations

86% related

Georgia Institute of Technology
119K papers, 4.6M citations

86% related

Argonne National Laboratory
64.3K papers, 2.4M citations

85% related

Oak Ridge National Laboratory
73.7K papers, 2.6M citations

85% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
20231
202216
2021415
20201,027
20191,418
20181,862