River flow sequence feature extraction and prediction using an enhanced sparse autoencoder

Qian Lipeng; Li Junfeng; Liu Changzheng; Tao Junhong; Chen Fulong

首页> 外文期刊>Journal of Hydroinformatics >River flow sequence feature extraction and prediction using an enhanced sparse autoencoder

【24h】

River flow sequence feature extraction and prediction using an enhanced sparse autoencoder

机译：河流序列采用增强稀疏自动系列的提取和预测

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

For the prediction of river flow sequence, owing to the non-stationariness and randomness of the sequence, the prediction accuracy of extreme river flow is not enough. In this study, the sparse factor of the loss function in a sparse autoencoder was enhanced using the inverse method of simulated annealing (ESA), and the river flow of the Kenswat Station in the Manas River Basin in northern Xinjiang, China, at 9:00, 15:00, and 20:00 daily during June, July, and August in 1998-2000 was considered as the study sequence. When the initial values of the sparse factor beta(0)are 5, 10, 15, 20, and 25, the experiment is designed with 60, 70, 80, 90, and 100 neurons, respectively, in the hidden layer to explore the relationship between the output characteristics of the hidden layer, and the original river flow sequence after the network is trained with various sparse factors and different numbers of neurons in the hidden layer. Meanwhile, the orthogonal experimental groups ESA1, ESA2, ESA3, ESA4, and ESA5 were designed to predict the daily average river flow in September 2000 and compared with the prediction results of the support vector machine (SVM) and the feedforward neural network (FFNN). The results indicate that after the ESA training, the output of the hidden layer consists of a large number of features of the original river flow sequence, and the boundaries of these features can reflect the river flow series with large changes. The upper bound of the features can reflect the characteristics of the river flow during the flood. Meanwhile, the prediction results of the orthogonal experiment groups indicate that when the number of neurons in the hidden layer is 90 and beta(0)= 15, the ESA has the best prediction effect on the sequence. In particular, the fitting effect on the day of 'swelling up' of the river flow is more satisfactory than that of SVM and FFNN. The results are significant, as they provide a guide for exploring the evolution of the river flow under drought and flood as well as for optimally dispatching and managing water resources.

机译：对于河流序列的预测，由于序列的非公平性和随机性，极端河流流动的预测精度是不够的。在这项研究中，利用模拟退火（ESA）的逆方法，增强了稀疏自身额位中损失功能的稀疏因素，以及新疆北部玛纳斯河流域的Kenswat站的河流流动，9： 00，00,15:00和20:00每日，7月，1998 - 2000年8月被认为是研究序列。当稀疏因子β（0）的初始值是5,10,15,20和25时，实验分别设计有60,70,80,90和100神经元，其中在隐藏层中以探索隐藏层的输出特性与网络后的原始河流流动序列之间的关系，在隐藏层中具有各种稀疏因子和不同数量的神经元。同时，设计正交实验组ESA1，ESA2，ESA3，ESA4和ESA5，旨在预测2000年9月的日常普通河流，并与支持向量机（SVM）和前馈神经网络（FFNN）的预测结果相比。结果表明，在ESA训练之后，隐藏层的输出包括原始河流流量序列的大量特征，这些功能的边界可以反映河流系列大的变化。特征的上限可以反映洪水期间河流流动的特征。同时，正交实验组的预测结果表明，当隐藏层中的神经元数为90且β（0）= 15时，ESA对序列具有最佳的预测效果。特别是，河流流动“膨胀”日的拟合效果比SVM和FFNN更令人满意。结果是重要的，因为它们提供了探索干旱和洪水下河流进化的指南，以及最佳地调度和管理水资源。

著录项

来源
《Journal of Hydroinformatics》 |2020年第6期|1391-1409|共19页
作者
Qian Lipeng; Li Junfeng; Liu Changzheng; Tao Junhong; Chen Fulong;
展开▼
作者单位

Shihezi Univ Coll Water Conservancy & Architectural Engn Shihezi 832000 Xinjiang Peoples R China;

Shihezi Univ Coll Water Conservancy & Architectural Engn Shihezi 832000 Xinjiang Peoples R China|Xinjiang Prod & Construct Grp Key Lab Modern Water Saving Irrigat Shihezi 832000 Xinjiang Peoples R China;

Shihezi Univ Coll Water Conservancy & Architectural Engn Shihezi 832000 Xinjiang Peoples R China;

Shihezi Univ Coll Water Conservancy & Architectural Engn Shihezi 832000 Xinjiang Peoples R China;

Shihezi Univ Coll Water Conservancy & Architectural Engn Shihezi 832000 Xinjiang Peoples R China|Xinjiang Prod & Construct Grp Key Lab Modern Water Saving Irrigat Shihezi 832000 Xinjiang Peoples R China;

展开▼
收录信息美国《科学引文索引》(SCI);
原文格式 PDF
正文语种 eng
中图分类
关键词
extreme flow; river flow characteristics; simulated annealing; sparse autoencoder;

机译：极端流动;河流流动特性;模拟退火;稀疏的autoencoder;

相似文献

外文文献
中文文献
专利

1. An Abnormal Network Flow Feature Sequence Prediction Approach for DDoS Attacks Detection in Big Data Environment [J] . Jieren Cheng, Ruomeng Xu, Xiangyan Tang, 计算机、材料和连续体(英文) . 2018,第004期
2. A novel sparse feature extraction method based on sparse signal via dual-channel self-adaptive TQWT [J] . Junlin LI, Huaqing WANG, Liuyang SONG 中国航空学报（英文版） . 2021,第007期
3. Pulse-to-pulse periodic signal sorting features and feature extraction in radar emitter pulse sequences [J] . Qiang Guo, Zhenshen Qu, Changhong Wang 系统工程与电子技术：英文版 . 2010,第003期
4. Prediction of aptamer-protein interacting pairs based on sparse autoencoder feature extraction and an ensemble classifier [J] . Yang Qing, Jia Cangzhi, Li Taoying Mathematical Biosciences: An International Journal . 2019,第期

机译：基于稀疏AutoEncoder特征提取的Aptamer-蛋白相互作用对的预测和集合分类器
5. An Enhanced Design of Sparse Autoencoder for Latent Features Extraction Based on Trigonometric Simplexes for Network Intrusion Detection Systems [J] . Progress in Artificial Intelligence . 2020,第2期

机译：基于三角单纯X的网络入侵检测系统采用增强型稀疏自动化器设计
6. Prediction of Protein-Protein Interactions from Protein Sequences by Combining MatPCA Feature Extraction Algorithms and Weighted Sparse Representation Models [J] . Zheng Wang, Yang Li, Zhu-Hong You, Mathematical Problems in Engineering: Theory, Methods and Applications . 2020,第1期

机译：通过组合MATPCA特征提取算法和加权稀疏表示模型预测蛋白质 - 蛋白质与蛋白质序列相互作用
7. Network Intrusion Detection System using Feature Extraction based on Deep Sparse Autoencoder [C] . Joohwa Lee, JuGeon Pak, Myungsuk Lee International Conference on Information and Communication Technology Convergence . 2020

机译：基于深稀疏自动探测器的特征提取网络入侵检测系统
8. Feature fusion models via stacked autoencoders: Applications to vehicular traffic flow prediction and Alzheimer's disease stage detection [D] . Moussavi-Khalkhali, Arezou. 2016

机译：通过堆叠式自动编码器的特征融合模型：在交通流量预测和阿尔茨海默氏病阶段检测中的应用
9. Defect-Repairable Latent Feature Extraction of Driving Behavior via a Deep Sparse Autoencoder [O] . Hailong Liu, Tadahiro Taniguchi, Kazuhito Takenaka, 2018

机译：通过深度稀疏自动编码器提取驾驶行为的可修复潜在特征
10. River flow sequence feature extraction and prediction using an enhanced sparse autoencoder [O] . Lipeng Qian, Junfeng Li, Changzheng Liu, 2020

机译：河流序列功能提取和预测使用增强稀疏的自动化器
11. Sparse Representation and Dictionary Learning as Feature Extraction in Vessel Imagery. [R] . Rainey, K., Ascencio, A. 2014

机译：稀疏表示与字典学习作为船舶图像特征提取。

River flow sequence feature extraction and prediction using an enhanced sparse autoencoder

摘要

著录项

相似文献

相关主题

期刊订阅