Firstly,general regression neural network(GRNN) was used for variable selection of key influencing factors of residential load(RL) forecasting.Secondly,the key influencing factors chosen by GRNN were used as the input...Firstly,general regression neural network(GRNN) was used for variable selection of key influencing factors of residential load(RL) forecasting.Secondly,the key influencing factors chosen by GRNN were used as the input and output terminals of urban and rural RL for simulating and learning.In addition,the suitable parameters of final model were obtained through applying the evidence theory to combine the optimization results which were calculated with the PSO method and the Bayes theory.Then,the model of PSO-Bayes least squares support vector machine(PSO-Bayes-LS-SVM) was established.A case study was then provided for the learning and testing.The empirical analysis results show that the mean square errors of urban and rural RL forecast are 0.02% and 0.04%,respectively.At last,taking a specific province RL in China as an example,the forecast results of RL from 2011 to 2015 were obtained.展开更多
We study conformal vector fields on a Finsler manifold whose metric is defined by a Riemannian metric, a 1-form and its norm. We find PDEs characterizing conformal vector fields. Then we obtain the explicit expression...We study conformal vector fields on a Finsler manifold whose metric is defined by a Riemannian metric, a 1-form and its norm. We find PDEs characterizing conformal vector fields. Then we obtain the explicit expressions of conformal vector fields for certain spherically symmetric metrics on R^n.展开更多
Based on the new metric theory of gravitation suggested by the author of this article, it gives a possible theoretical interpretation on the famous experiment done by D.R. Long in 1976, i.e. the distance-dependent eff...Based on the new metric theory of gravitation suggested by the author of this article, it gives a possible theoretical interpretation on the famous experiment done by D.R. Long in 1976, i.e. the distance-dependent effect of the gravitational constant in Newton's theory of gravitation.展开更多
This article suggests a new metric theory of gravitation, in which metric field is determined not only by matter and nongravitational field but also by vector graviton field, and in principle there is no need to intro...This article suggests a new metric theory of gravitation, in which metric field is determined not only by matter and nongravitational field but also by vector graviton field, and in principle there is no need to introduce the Einstein's tensor. In order to satisfy automatically the geodesic postulate, an additional coordinate condition is needed. For the spherically symmetric static field, it leads us to quite different conclusions from those of Einstein's general relativity in the interior region of the surface of infinite redshift. Accurate to the first order of , it obtains the same results about the four experimental tests of general relativity.展开更多
We present three-dimensional(3-D)modeling method of marine controlled-source electromagnetic(CSEM)fields in general anisotropic media using an adaptive finite element approach based on the vector-scalar potential.The ...We present three-dimensional(3-D)modeling method of marine controlled-source electromagnetic(CSEM)fields in general anisotropic media using an adaptive finite element approach based on the vector-scalar potential.The modeling is based on the governing Helmholtz equations in the vector-scalar potential system.Unstructured tetrahedral grids are employed,which can exactly simulate the terrain relief and complex electrical structures.Moreover,based on the gradient recovery technology,the adaptive finite element approach is used to drive the mesh refinement,and make the finite element solutions converge gradually to the exact solutions.The primary-secondary field approach is used to improve the numerical accuracy of CSEM fields near the source point,where the primary field is calculated by using the quasi-analytical formula.The accuracy of this approach is verified by a one-dimensional model.Two 3-D models are used to demonstrate the effectiveness of the adaptive mesh refinement and the influences of dipping anisotropy layer on the marine CSEM responses for both inline and broadside geometries.The complex synthetic model is simulated to show the capability and flexibility of the approach for geometrically complex situations.展开更多
General noise cost functions have been recently proposed for support vector regression(SVR). When applied to tasks whose underlying noise distribution is similar to the one assumed for the cost function, these models ...General noise cost functions have been recently proposed for support vector regression(SVR). When applied to tasks whose underlying noise distribution is similar to the one assumed for the cost function, these models should perform better than classical -SVR. On the other hand, uncertainty estimates for SVR have received a somewhat limited attention in the literature until now and still have unaddressed problems. Keeping this in mind,three main goals are addressed here. First, we propose a framework that uses a combination of general noise SVR models with naive online R minimization algorithm(NORMA) as optimization method, and then gives nonconstant error intervals dependent upon input data aided by the use of clustering techniques. We give theoretical details required to implement this framework for Laplace, Gaussian, Beta, Weibull and Marshall–Olkin generalized exponential distributions. Second, we test the proposed framework in two real-world regression problems using data of two public competitions about solar energy. Results show the validity of our models and an improvement over classical -SVR. Finally, in accordance with the principle of reproducible research, we make sure that data and model implementations used for the experiments are easily and publicly accessible.展开更多
基金Project(07JA790092) supported by the Research Grants from Humanities and Social Science Program of Ministry of Education of ChinaProject(10MR44) supported by the Fundamental Research Funds for the Central Universities in China
文摘Firstly,general regression neural network(GRNN) was used for variable selection of key influencing factors of residential load(RL) forecasting.Secondly,the key influencing factors chosen by GRNN were used as the input and output terminals of urban and rural RL for simulating and learning.In addition,the suitable parameters of final model were obtained through applying the evidence theory to combine the optimization results which were calculated with the PSO method and the Bayes theory.Then,the model of PSO-Bayes least squares support vector machine(PSO-Bayes-LS-SVM) was established.A case study was then provided for the learning and testing.The empirical analysis results show that the mean square errors of urban and rural RL forecast are 0.02% and 0.04%,respectively.At last,taking a specific province RL in China as an example,the forecast results of RL from 2011 to 2015 were obtained.
文摘We study conformal vector fields on a Finsler manifold whose metric is defined by a Riemannian metric, a 1-form and its norm. We find PDEs characterizing conformal vector fields. Then we obtain the explicit expressions of conformal vector fields for certain spherically symmetric metrics on R^n.
文摘Based on the new metric theory of gravitation suggested by the author of this article, it gives a possible theoretical interpretation on the famous experiment done by D.R. Long in 1976, i.e. the distance-dependent effect of the gravitational constant in Newton's theory of gravitation.
文摘This article suggests a new metric theory of gravitation, in which metric field is determined not only by matter and nongravitational field but also by vector graviton field, and in principle there is no need to introduce the Einstein's tensor. In order to satisfy automatically the geodesic postulate, an additional coordinate condition is needed. For the spherically symmetric static field, it leads us to quite different conclusions from those of Einstein's general relativity in the interior region of the surface of infinite redshift. Accurate to the first order of , it obtains the same results about the four experimental tests of general relativity.
基金support from the Natural Science Foundation of Jiangxi Province,China(Nos.20202ACBL211006,20202BAB213017)the National Natural Science Foundation of China(Nos.41774078,41904075).
文摘We present three-dimensional(3-D)modeling method of marine controlled-source electromagnetic(CSEM)fields in general anisotropic media using an adaptive finite element approach based on the vector-scalar potential.The modeling is based on the governing Helmholtz equations in the vector-scalar potential system.Unstructured tetrahedral grids are employed,which can exactly simulate the terrain relief and complex electrical structures.Moreover,based on the gradient recovery technology,the adaptive finite element approach is used to drive the mesh refinement,and make the finite element solutions converge gradually to the exact solutions.The primary-secondary field approach is used to improve the numerical accuracy of CSEM fields near the source point,where the primary field is calculated by using the quasi-analytical formula.The accuracy of this approach is verified by a one-dimensional model.Two 3-D models are used to demonstrate the effectiveness of the adaptive mesh refinement and the influences of dipping anisotropy layer on the marine CSEM responses for both inline and broadside geometries.The complex synthetic model is simulated to show the capability and flexibility of the approach for geometrically complex situations.
基金With partial support from Spain’s grants TIN2013-42351-P, TIN2016-76406-P, TIN2015-70308-REDT, as well as S2013/ICE-2845 CASI-CAM-CMsupported also by project FACIL–Ayudas Fundación BBVA a Equipos de Investigación Científica 2016
文摘General noise cost functions have been recently proposed for support vector regression(SVR). When applied to tasks whose underlying noise distribution is similar to the one assumed for the cost function, these models should perform better than classical -SVR. On the other hand, uncertainty estimates for SVR have received a somewhat limited attention in the literature until now and still have unaddressed problems. Keeping this in mind,three main goals are addressed here. First, we propose a framework that uses a combination of general noise SVR models with naive online R minimization algorithm(NORMA) as optimization method, and then gives nonconstant error intervals dependent upon input data aided by the use of clustering techniques. We give theoretical details required to implement this framework for Laplace, Gaussian, Beta, Weibull and Marshall–Olkin generalized exponential distributions. Second, we test the proposed framework in two real-world regression problems using data of two public competitions about solar energy. Results show the validity of our models and an improvement over classical -SVR. Finally, in accordance with the principle of reproducible research, we make sure that data and model implementations used for the experiments are easily and publicly accessible.
