Support vector classifier (SVC) has the superior advantages for small sample learning problems with high dimensions, with especially better generalization ability. However there is some redundancy among the high dim...Support vector classifier (SVC) has the superior advantages for small sample learning problems with high dimensions, with especially better generalization ability. However there is some redundancy among the high dimensions of the original samples and the main features of the samples may be picked up first to improve the performance of SVC. A principal component analysis (PCA) is employed to reduce the feature dimensions of the original samples and the pre-selected main features efficiently, and an SVC is constructed in the selected feature space to improve the learning speed and identification rate of SVC. Furthermore, a heuristic genetic algorithm-based automatic model selection is proposed to determine the hyperparameters of SVC to evaluate the performance of the learning machines. Experiments performed on the Heart and Adult benchmark data sets demonstrate that the proposed PCA-based SVC not only reduces the test time drastically, but also improves the identify rates effectively.展开更多
为了提高超短期风电功率的预测精度,提出了一种基于COOT算法优化的变分模态分解(VMD)、分层主成分分析(hierarchical principal components analysis,HPCA)与门控循环单元神经网络(GRU)的组合预测模型。首先,利用能量差值法确定变分模...为了提高超短期风电功率的预测精度,提出了一种基于COOT算法优化的变分模态分解(VMD)、分层主成分分析(hierarchical principal components analysis,HPCA)与门控循环单元神经网络(GRU)的组合预测模型。首先,利用能量差值法确定变分模态分解子模态数,从而将具有强非线性的原始功率序列分解为一组相对平稳的子模态。其次,利用灰色关联度分析计算高维气象特征与功率序列的关联度值并进行排序分层,利用主成分分析提取各分层特征变量的第一主成分,实现对高维气象特征的降维。最后,引入COOT算法对门控循环单元预测模型的超参数进行优化,加速模型收敛速度,提高模型预测精度。对贵州某风电场的实测数据进行仿真分析,结果表明:相较于传统GRU模型的预测结果,所提方法的均方根误差、平均绝对误差、平均绝对百分误差分别下降了67.41%、72.25%、45.69%,且预测精度高于其他4种组合预测模型,有效提高了超短期风电功率预测精度。展开更多
降维对于数据的可视化和预处理具有重要意义,主成分分析作为最常用的无监督降维算法之一,在实际应用中面临着对噪声和离群点敏感的问题。为了解决这个问题,研究者们提出了多种鲁棒主成分分析算法,通过减小整体样本的重构误差来减小离群...降维对于数据的可视化和预处理具有重要意义,主成分分析作为最常用的无监督降维算法之一,在实际应用中面临着对噪声和离群点敏感的问题。为了解决这个问题,研究者们提出了多种鲁棒主成分分析算法,通过减小整体样本的重构误差来减小离群点的影响。然而,这些算法忽略了数据的固有局部结构,导致数据的本质结构信息丢失,从而影响了对噪声和离群点的准确辨识和移除,进而影响了后续算法的性能。因此,该文提出了基于Soft均值滤波的鲁棒主成分分析(Robust Principal Component Analysis Based on Soft Mean Filtering,RPCA-SMF)算法。RPCA-SMF采用Soft均值滤波的思想,通过两步走的形式,不仅在模型学习前对噪声处理,同时在模型学习后也引入了噪声处理机制。具体而言,RPCA-SMF算法首先引入了均值滤波的相关思想,通过对比样本与其局部近邻这两者和局部均值的偏差对样本进行Soft加权,从而对噪声进行判定。随后,通过第一步获取的关于噪声的“判别知识”处理噪声信息。由于均值滤波能有效保留数据的整体轮廓信息,因此对于被识别为噪声的样本,RPCA-SMF算法强调保留其低频整体轮廓信息,而非高频的噪声信息。这样能够有效地保留数据中的有用信息,提高对数据整体结构特征的保留能力,使得算法具有较强的鲁棒性和较好的泛化性。展开更多
基金the National Natural Science of China (50675167)a Foundation for the Author of National Excellent Doctoral Dissertation of China(200535)
文摘Support vector classifier (SVC) has the superior advantages for small sample learning problems with high dimensions, with especially better generalization ability. However there is some redundancy among the high dimensions of the original samples and the main features of the samples may be picked up first to improve the performance of SVC. A principal component analysis (PCA) is employed to reduce the feature dimensions of the original samples and the pre-selected main features efficiently, and an SVC is constructed in the selected feature space to improve the learning speed and identification rate of SVC. Furthermore, a heuristic genetic algorithm-based automatic model selection is proposed to determine the hyperparameters of SVC to evaluate the performance of the learning machines. Experiments performed on the Heart and Adult benchmark data sets demonstrate that the proposed PCA-based SVC not only reduces the test time drastically, but also improves the identify rates effectively.
文摘为了提高超短期风电功率的预测精度,提出了一种基于COOT算法优化的变分模态分解(VMD)、分层主成分分析(hierarchical principal components analysis,HPCA)与门控循环单元神经网络(GRU)的组合预测模型。首先,利用能量差值法确定变分模态分解子模态数,从而将具有强非线性的原始功率序列分解为一组相对平稳的子模态。其次,利用灰色关联度分析计算高维气象特征与功率序列的关联度值并进行排序分层,利用主成分分析提取各分层特征变量的第一主成分,实现对高维气象特征的降维。最后,引入COOT算法对门控循环单元预测模型的超参数进行优化,加速模型收敛速度,提高模型预测精度。对贵州某风电场的实测数据进行仿真分析,结果表明:相较于传统GRU模型的预测结果,所提方法的均方根误差、平均绝对误差、平均绝对百分误差分别下降了67.41%、72.25%、45.69%,且预测精度高于其他4种组合预测模型,有效提高了超短期风电功率预测精度。
文摘降维对于数据的可视化和预处理具有重要意义,主成分分析作为最常用的无监督降维算法之一,在实际应用中面临着对噪声和离群点敏感的问题。为了解决这个问题,研究者们提出了多种鲁棒主成分分析算法,通过减小整体样本的重构误差来减小离群点的影响。然而,这些算法忽略了数据的固有局部结构,导致数据的本质结构信息丢失,从而影响了对噪声和离群点的准确辨识和移除,进而影响了后续算法的性能。因此,该文提出了基于Soft均值滤波的鲁棒主成分分析(Robust Principal Component Analysis Based on Soft Mean Filtering,RPCA-SMF)算法。RPCA-SMF采用Soft均值滤波的思想,通过两步走的形式,不仅在模型学习前对噪声处理,同时在模型学习后也引入了噪声处理机制。具体而言,RPCA-SMF算法首先引入了均值滤波的相关思想,通过对比样本与其局部近邻这两者和局部均值的偏差对样本进行Soft加权,从而对噪声进行判定。随后,通过第一步获取的关于噪声的“判别知识”处理噪声信息。由于均值滤波能有效保留数据的整体轮廓信息,因此对于被识别为噪声的样本,RPCA-SMF算法强调保留其低频整体轮廓信息,而非高频的噪声信息。这样能够有效地保留数据中的有用信息,提高对数据整体结构特征的保留能力,使得算法具有较强的鲁棒性和较好的泛化性。