A “parallel” combined Transformer-CNN model using secondary decomposition for crude oil forecasting

首页 > 成果 > 详情

认领

导出

Link by DOI

反馈

作者信息关键词期刊信息基础信息归属信息摘要

成果类型：

期刊论文

作者：

Zhifeng Dai*;Huali Huang;Qinnan Jiang;Yaling Chen

通讯作者：

Zhifeng Dai

作者机构：

[Huali Huang; Qinnan Jiang] College of Mathematics and Statistics, Changsha University of Science and Technology, Hunan, China

Beijing Huairou Laboratory, Bejing, 101499, Peoples R China

[Yaling Chen] School of Humanity and Management, Hunan University of Chinese Medicine, Changsha, Hunan, China

State Key Laboratory of Disaster Prevention & Reduction for Power Grid, Changsha University of Science & Technology, Changsha 410114, China

[Zhifeng Dai] College of Mathematics and Statistics, Changsha University of Science and Technology, Hunan, China<&wdkj&>Beijing Huairou Laboratory, Bejing, 101499, Peoples R China<&wdkj&>State Key Laboratory of Disaster Prevention & Reduction for Power Grid, Changsha University of Science & Technology, Changsha 410114, China

通讯机构：

[Zhifeng Dai] C

College of Mathematics and Statistics, Changsha University of Science and Technology, Hunan, China<&wdkj&>Beijing Huairou Laboratory, Bejing, 101499, Peoples R China<&wdkj&>State Key Laboratory of Disaster Prevention & Reduction for Power Grid, Changsha University of Science & Technology, Changsha 410114, China

语种：

英文

期刊：

Expert Systems with Applications

ISSN：

0957-4174

年：

2026

卷：

299

页码：

129968

DOI：

10.1016/j.eswa.2025.129968

机构署名：

本校为第一且通讯机构

院系归属：

数学与统计学院

摘要：

In order to better apply the advantages of deep learning models in crude oil price prediction, this paper proposes a novel deep learning combined model. It has a “decomposition and construction, dual-model parallel feature and extraction fully connected fusion” architecture, which combines the Transformer model with self-attention mechanism, the convolutional neural network (CNN) with local feature extraction in “parallel” and a fully connected neural network (FCN) to realize feature fusion. Firstly, the original price sequence is decompose...

反馈

产权有误：本人成果被他人认领

数据有误：数据基本信息有误

归属有误：成果的院系归属、机构署名归属有误

其他原因：

验证码：

看不清楚，换一个

确定

取消

成果认领

标题：

用户	作者	通讯作者	--
	请选择	请选择	--

确定

取消

A “parallel” combined Transformer-CNN model using secondary decomposition for crude oil forecasting

反馈

成果认领

提示

该栏目需要登录且有访问权限才可以访问