Short-term load forecasting is a basis of power system dispatching and operation. In order to improve the short term power load precision, a novel approach for short-term load forecasting is presented based on local m...Short-term load forecasting is a basis of power system dispatching and operation. In order to improve the short term power load precision, a novel approach for short-term load forecasting is presented based on local mean decomposition (LMD) and the radial basis function neural network method (RBFNN). Firstly, the decomposition of LMD method based on characteristics of load data then the decomposed data are respectively predicted by using the RBF network model and predicted by using the BBO-RBF network model. The simulation results show that the RBF network model optimized by using BBO algorithm is optimized in error performance index, and the prediction accuracy is higher and more effective.展开更多
Hemodynamic response during motor imagery （MI） is studied extensively by functional magnetic resonance imaging （fMRI） technologies. To further understand the human brain functions under MI, a more precise classifi...Hemodynamic response during motor imagery （MI） is studied extensively by functional magnetic resonance imaging （fMRI） technologies. To further understand the human brain functions under MI, a more precise classification of the brain regions corresponding to each brain function is desired. In this study, a Bayesian trained radial basis function （RBF） neural network, which determines the weights and regularization parameters automatically by Bayesian learning, is applied to make a precise classification of the hemodynamic response to the tasks during the MI experiment. To illustrate the proposed method, data with MI task performance from 1 subject was used. The results demonstrate that this approach splits the hemodynamic response to different tasks successfully.展开更多
文摘Short-term load forecasting is a basis of power system dispatching and operation. In order to improve the short term power load precision, a novel approach for short-term load forecasting is presented based on local mean decomposition (LMD) and the radial basis function neural network method (RBFNN). Firstly, the decomposition of LMD method based on characteristics of load data then the decomposed data are respectively predicted by using the RBF network model and predicted by using the BBO-RBF network model. The simulation results show that the RBF network model optimized by using BBO algorithm is optimized in error performance index, and the prediction accuracy is higher and more effective.
基金supported by the National Natural Science Foundation of China under Grant No. 9082006 and 30770590Key Research Project of Science and Technology of MOE under Grant No. 107097863 Program under Grant No. 2008AA02Z4080
文摘Hemodynamic response during motor imagery （MI） is studied extensively by functional magnetic resonance imaging （fMRI） technologies. To further understand the human brain functions under MI, a more precise classification of the brain regions corresponding to each brain function is desired. In this study, a Bayesian trained radial basis function （RBF） neural network, which determines the weights and regularization parameters automatically by Bayesian learning, is applied to make a precise classification of the hemodynamic response to the tasks during the MI experiment. To illustrate the proposed method, data with MI task performance from 1 subject was used. The results demonstrate that this approach splits the hemodynamic response to different tasks successfully.
文摘为了解决单个神经网络预测的局限性和时间序列的波动性,提出了一种奇异谱分析(singular spectrum analysis,SSA)和Stacking框架相结合的短期负荷预测方法。利用随机森林筛选出与历史负荷相关性强烈的特征因素,采用SSA为负荷数据降噪,简化模型计算过程;基于Stacking框架,结合长短期记忆(long and short-term memory,LSTM)-自注意力机制(self-attention mechanism,SA)、径向基(radial base functions,RBF)神经网络和线性回归方法集成新的组合模型,同时利用交叉验证方法避免模型过拟合;选取PJM和澳大利亚电力负荷数据集进行验证。仿真结果表明,与其他模型比较,所提模型预测精度高。
