A method for fast 1-fold cross validation is proposed for the regularized extreme learning machine （RELM）. The computational time of fast l-fold cross validation increases as the fold number decreases, which is oppo...A method for fast 1-fold cross validation is proposed for the regularized extreme learning machine （RELM）. The computational time of fast l-fold cross validation increases as the fold number decreases, which is opposite to that of naive 1-fold cross validation. As opposed to naive l-fold cross validation, fast l-fold cross validation takes the advantage in terms of computational time, especially for the large fold number such as l 〉 20. To corroborate the efficacy and feasibility of fast l-fold cross validation, experiments on five benchmark regression data sets are evaluated.展开更多
为解决交替方向乘子法(alternating direction method of multipliers,ADMM)正则化极限学习机(regularized extreme learning machine,RELM)迭代收敛速度慢和迭代后期误差衰减停滞的问题,提出一种基于动态步长ADMM的正则化极限学习机,记...为解决交替方向乘子法(alternating direction method of multipliers,ADMM)正则化极限学习机(regularized extreme learning machine,RELM)迭代收敛速度慢和迭代后期误差衰减停滞的问题,提出一种基于动态步长ADMM的正则化极限学习机,记为VAR-ADMM-RELM.该算法在ADMM算法的基础上采用动态衰减步长进行迭代,并同时使用L1和L2正则化对模型复杂度进行约束,解得具有稀疏性和鲁棒性的极限学习机输出权重.在UCI和MedMNIST数据集中对VAR-ADMM-RELM、极限学习机(extreme learning machine,ELM)、正则化极限学习机(regularized ELM,RELM)和基于ADMM的L1正则化ELM(ADMMRELM)进行拟合、分类和回归对比实验.结果表明,VAR-ADMM-RELM算法的平均分类准确率和平均回归预测精度分别比ELM算法提升了1.94%和2.49%,较标准ADMM算法可以取得3~5倍的速度提升,且对异常值干扰具有更好的鲁棒性和泛化能力,在高维度多样本的场景下建模效率逼近标准极限学习机.该方法有效提升了ADMM算法的收敛速度,取得了比主流ELM算法更加优秀的性能表现.展开更多
基金supported by the National Natural Science Foundation of China(51006052)the NUST Outstanding Scholar Supporting Program
文摘A method for fast 1-fold cross validation is proposed for the regularized extreme learning machine （RELM）. The computational time of fast l-fold cross validation increases as the fold number decreases, which is opposite to that of naive 1-fold cross validation. As opposed to naive l-fold cross validation, fast l-fold cross validation takes the advantage in terms of computational time, especially for the large fold number such as l 〉 20. To corroborate the efficacy and feasibility of fast l-fold cross validation, experiments on five benchmark regression data sets are evaluated.
文摘养殖水体中溶解氧浓度一直是最重要的水质参数之一。为了精准地对水体溶解氧进行调控,提高养殖生产效率,降低养殖风险,该研究考虑外部天气条件对溶解氧的影响以及溶解氧自身的昼夜变化特征,提出一种基于正则化极限学习机(principal component analysis and clustering method optimized regularized extreme learning machine,PC-RELM)的养殖水体溶解氧数据流预测模型。首先,采用主成分分析法判断影响溶解氧浓度的强重要性因子,降低预测模型的数据维度;其次,利用熵权法计算各时刻点的天气环境指数,并利用快速动态时间规整算法(fast dynamic time warping,FastDTW)完成时间序列数据流在不同天气环境下的相似度度量;然后使用k-means算法对时间序列的相似度进行聚类分簇,并基于分簇结果完成正则化极限学习机预测模型的构建,实现溶解氧浓度的估算。最后将PC-RELM模型应用到无锡南泉试验基地养殖池塘的溶解氧预测调控过程中。试验结果表明:PC-RELM的预测均方根误差值(root mean square error,RMSE)为0.9619,与PLS-ELM(partial least squares optimized ELM)、最小二乘支持向量机(least square support vector machine,LSSVM)以及BP神经网络模型进行对比,其RMSE值分别降低了41.54%、54.58%和67.16%。该预测模型可以有效地捕捉不同天气条件下溶解氧的变化特点,具有较高的预测精度和效率。
