This paper proposes a novel intelligent estimation algorithm in Wireless Sensor Network nodes location based on Free Search,which converts parameter estimation to on-line optimization of nonlinear function and estimat...This paper proposes a novel intelligent estimation algorithm in Wireless Sensor Network nodes location based on Free Search,which converts parameter estimation to on-line optimization of nonlinear function and estimates the coordinates of senor nodes using the Free Search optimization.Compared to the least-squares estimation algorithms,the localization accuracy has been increased significantly,which has been verified by the simulation results.展开更多
This paper addresses the learning algorithm on the unit sphere.The main purpose is to present an error analysis for regression generated by regularized least square algorithms with spherical harmonics kernel.The exces...This paper addresses the learning algorithm on the unit sphere.The main purpose is to present an error analysis for regression generated by regularized least square algorithms with spherical harmonics kernel.The excess error can be estimated by the sum of sample errors and regularization errors.Our study shows that by introducing a suitable spherical harmonics kernel,the regularization parameter can decrease arbitrarily fast with the sample size.展开更多
基金National Research Foundation for the Doctoral Program of Higher Education of China(No.20060266006)the High-school Natural Science Research Foundation of Jiangsu Province(No.07KJB510095)
文摘This paper proposes a novel intelligent estimation algorithm in Wireless Sensor Network nodes location based on Free Search,which converts parameter estimation to on-line optimization of nonlinear function and estimates the coordinates of senor nodes using the Free Search optimization.Compared to the least-squares estimation algorithms,the localization accuracy has been increased significantly,which has been verified by the simulation results.
基金supported by National Natural Science Foundation of China (Grant Nos. 61272023 and 61075054)
文摘This paper addresses the learning algorithm on the unit sphere.The main purpose is to present an error analysis for regression generated by regularized least square algorithms with spherical harmonics kernel.The excess error can be estimated by the sum of sample errors and regularization errors.Our study shows that by introducing a suitable spherical harmonics kernel,the regularization parameter can decrease arbitrarily fast with the sample size.
