51CTO博客已为您找到关于PSO-GPR的相关内容,包含IT学习相关文档代码介绍、相关教程视频课程,以及PSO-GPR问答内容。更多PSO-GPR相关解答可以来51CTO博客参与分享和学习,帮助广大IT技术人实现成长和进步。
Subsequently, a PSO-GPR is proposed to estimate the state of the battery. Experiments were conducted on battery cells with different charging and discharging rates. The root mean square error (RMSE) and mean absolute error (MAE) of the SOC estimation results were obtained to be less than 3.65...
(3) 支持向量机回归(SVR)算法; (4) 高斯过程回归(GPR)算法; 3. 比较不同机器学习算法对GaN模型的建模效果,研究最适合GaN器件的机器学习建模方法。在机器学习算法的基础上开发出更高精度的GaN基器件的模型,实现基于物理结构模型所达不...
摘要 传统对含缺陷管道失效应力的预测方法存在误差偏大的问题。针对该问题,利用MATLAB软件建立基于PSO–GPR(particle swarm optimization–Gaussian process regression...展开更多 The traditional prediction method of failure stress of pipeline with defects has the problem of large error.Aiming at this problem,the...
基于PSO-GPR的短时高速公路交通量预测 作者:田甜; 田永宏粒子优化群算法高斯过程回归短时交通量预测 摘要:本文通过分析常用交通量预测算法的不足与缺陷,引入粒子群优化算法和高斯过程回归,重点研究了采用粒子群优化算法自动搜寻泛化性能最好的高斯过程回归超参数算法模型解决方案。通过建立交通量预测模型对某高速公路短时...
利用粒子群算法改进传统高斯过程模型参数优化的不足,构建预测模型.以重构序列作为预测模型的训练集和测试集,实现短时交通流预测.采用北京市东四环快速路检测器实测数据对比分析模型预测效果.结果表明,基于PSR和PSO-GPR的短时交通流预测模型评价指标均优于对比模型,其中绝对误差平均降低4.88,绝对百分比误差平均降低3.97%,均...
(PSO-LSSVR), and subsequently predicted the tunnel surrounding rock deformation using the constructed Gaussian Process Regression model (PSO-GPR).The research results indicate that the average relative error of the PSO-LSSVR reconstruction model is 1.21 %, lower than the 4.82 % of the LSSVR ...
This item pack contains costumes inspired by the new Retem region in PSO2 New Genesis, and useful in-game items. ・The core game is Free-to-Play, but there is certain paid content that can be purchased.
基于粒子群算法(PSO)优化高斯过程回归(PSO-GPR)的数据回归预测,matlab代码,多变量输入模型。 1453 -- 0:19 App 基于麻雀算法(SSA)优化卷积神经网络-长短期记忆网络(CNN-LSTM)回归预测,SSA-CNN-LSTM多输入单输出模型。 1233 -- 0:13 App 麻雀优化算法SSA-灰狼优化算法GWO-粒子群优化算法PSO-鲸鱼优化算法WOA-遗...
In view of the shortcomings of existing artificial neural network (ANN) and support vector regression (SVR) in the application of three-dimensional displacement back analysis, Gaussian process regression (GPR) algorithm is introduced to make up for the shortcomings of existing intelligent inversion meth...