基于特征相关分析修正的GPSO-LSTM 短期负荷预测

郭傅傲, 刘大明, 张振中, 唐飞 - 电测与仪表, 2021 - emijournal.net
… Due to the random initialization of LSTM network weights, the … The improved particle swarm
optimization algorithm is used … neural network (BPNN) and recursive neural network (Elman), …

[PDF][PDF] 基于混合全局局部自适应粒子群算法的人脸认证支持向量机模型

SA Hussein, AA Mahmood, MI Dohan - 西南交通大学学报, 2020 - researchgate.net
… global local adaptive particle swarm optimization-based … purpose, such as neural networks
and machine learning methods [3]… Begin Initialize particle swarm randomly While (the number …

基于SOM 和PSO 的非监督地震相分析技术

郑晓东, 李劲松, 路交通, 曹成寅, 隋京坤 - 地球物理学报, 2015 - geophy.cn
… the weight trends to stabilization, the training is finished, otherwise, … using the global
optimization of the PSO, which is initialized … Another "best" value that is tracked by the particle

[HTML][HTML] 基于动态因子和共享适应度的改进粒子群算法

谭熠峰, 孙婷婷, 徐新民 - 浙江大学学报(理学版), 2016 - fx361.com
method of wind turbine gearbox based on BP neural network … rate of particle swarm
optimization, an improved particle swarm … The chosen particles will be re-initialized as a new

基于神经网络的炭气凝胶孔结构的预测与优化模型研究

杨榛, 乔文明, 梁晓怿 - 新型炭材料, 2017 - xxtcl.sxicc.ac.cn
using an artificial neural network (ANN) algorithm. The ANN model has been optimized based
on an improved genetic algorithm from six typical training … randomly initialized between 0 …

一种基于充电模式识别的电动汽车充电时间预测方法

李春喜, 傅莹颖, 崔向科, 葛泉波 - 信息与电子工程前沿(英文), 2023 - fitee.zjujournals.com
… This method improves the training efficiency, but it has limited ability to … Initialize the
particle swarm … We propose a new improved simplified particle swarm optimization (ISPSO) …

基于人工神经网络的高分五号高光谱影像悬浮泥沙浓度反演方法

刘一鸣, 张磊, 周梅, 梁建, 王妍, 孙力… - 红外与毫米波 …, 2021 - journal.sitp.ac.cn
… In this study,the neural network calibrator(NNC)based on ANN was … parameterized through
the particle swarm optimization algorithm for … The weights in ANN are initialized by simu⁃ …

基于改进粒子群算法的LSTM 股票预测模型

黄建华, 钟敏, 胡庆春 - 华东理工大学学报(自然科学版), 2022 - journal.ecust.edu.cn
Initialize the number of particles Train LSTM, calculate particle fitness value … Aiming at the
above problems, this paper proposes an improved particle swarm algorithm to optimize the key …

[HTML][HTML] 基于广义化自适应的NAG 方法非负张量分解模型

陶名康 - Advances in Applied Mathematics, 2022 - hanspub.org
… is integrated into the SLF-NMU algorithm, and the generalized NAG method is obtained. On
… adaptive NAG method is proposed. During the training process, particle swarm optimization …

[HTML][HTML] 灰色粒子群自适应卫星钟差预报方法

李源, 战兴群, 梅浩, 刘宝玉 - 哈尔滨工业大学学报, 2018 - hit.alljournals.cn
Particle swarm adaptive satellite clock error prediction model … model using the latest
measurement for initialization is … Application of neural network in satellite clock bias short-term …