猪价格预测的分解-重建-优化框架:集成STL,PCA和BWO优化的BiLSTM
Xiangjuan Liu1,2,3, Yunlong Li1, Fengtong Wang1
1College of Computer and Control Engineering, Qiqihar University, Qiqihar, China.
这项研究开发了一种用于猪价预测的先进混合模型,通过分解,特征工程和优化技术显著提高了80%以上的准确性. 新的框架增强了农业经济时间序列的预测.
科学领域:
- 农业经济学 农业经济学
- 时间序列分析时间序列分析
- 机器学习 机器学习
背景情况:
- 准确的猪价预测对于农业经济的稳定至关重要.
- 传统的时间序列模型经常与农业市场数据的复杂性作斗争.
- 深度学习模型有希望,但需要进一步优化以实现实际应用.
研究的目的:
- 为猪价格时间序列开发一个多阶段混合预测模型.
- 通过整合时间分解,特征工程和智能优化来提高预测准确性.
- 建立一个创新的创新.
主要方法:
- 将七个基准模型 (Prophet,ARIMA,LSTM) 应用于原猪价格数据.
- 使用季节趋势分解使用Loess (STL) 进行序列分解.
- 实施主要组件分析 (PCA) 用于维度缩小和特征选择的斯皮尔曼相关性.
- 开发了一个结合BiLSTM的混合模型,并使用Beluga Whale Optimization (BWO) 进行了优化.
主要成果:
- 深度学习模型在原始数据上表现优于传统方法.
- STL分解使平均绝对误差 (MAE) 降低了22.6%.
- 特性工程 (STL-PCA) 将BiLSTM的MAE降低了83.6% (从1.65降至0.27).
- 优化的STL-PCA-BWO-BiLSTM模型获得了卓越的性能 (RMSE=0.22,MAE=0.16,MAPE=0.99%).
结论:
- 拟议的混合模型显著减少了猪价预测错误 (减少了80%以上).
- STL-PCA功能工程是一个主要贡献者 (67.4%的改进).
- "分解-重建-优化"框架为农业经济时间序列预测提供了一个强大的方法.
更多相关视频
09:12Optimization of Processing of Tiebangchui with Highland Barley Wine Based on the Box-Behnken Design Combined with the Entropy Method
Published on: May 19, 2023
11:53Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm
Published on: December 9, 2012
相关概念视频
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
On...
BIBO stability of continuous and discrete -time systems
To determine the BIBO stability, the convolution integral is utilized when a bounded continuous-time input is applied to a Linear Time-Invariant (LTI) system....
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Statistical Analysis: Overview
One of the most commonly used statistical quantifiers is the mean, which is the ratio between the sum of the numerical values of all results and the...
Extraction: Partition and Distribution Coefficients
For extracting a solute from an aqueous phase into an...
Reconstruction of Signal using Interpolation
