基于多家族波段的特征工程方法用于短期时间序列预测

Kyrylo Yemets¹, Ivan Izonin^2,3, Stergios Aristoteles Mitoulis^3,4

¹Department of Artificial Intelligence, Lviv Polytechnic National University, Kniazia Romana str., 5, Lviv, 79905, Ukraine. kyrylo.v.yemets@lpnu.ua.

Scientific reports

|November 7, 2025

概括

本研究引入了一种使用静止波段变换 (SWT) 和多家族波段的新方法,以改善对自然现象的短期预测. 增强的功能显著提高了预测模型的准确性,如LSTM.

科学领域:

气候科学气候科学
能源管理能源管理
时间序列分析时间序列分析

背景情况:

准确的自然现象短期预测对于气候科学和能源管理至关重要.
传统的预测方法可以通过先进的特征工程,特别是波形变换来增强.

研究的目的:

引入一种新的特征构造方法,用于使用静止波段变换 (SWT) 和多家族波段进行短期时间序列预测.
通过将时间序列数据与详细的波形系数增强来提高预测模型的准确性.

主要方法:

静止波形变换 (SWT) 在多个波形家族 (Daubechies,Symlets,Coiflets,Haar,Meyer) 的应用.
功能工程通过用波形系数补充原始时间序列数据,保持维度.
使用长期短期记忆 (LSTM) 神经网络进行预测任务.

主要成果:

波形增强的LSTM模型在多个数据集中展示了一致的错误减少.
平均绝对误差 (MAE) 减少了13.6%,平均平方误差 (MSE) 减少了17.7%,根平均平方误差 (RMSE) 减少了9.5%,对称平均绝对百分比误差 (SMAPE) 减少了13.9%.
多家族SWT功能在提高气象变量,电力需求和风力发电量预测准确度方面被证明是有效的.

结论:

拟议的多家族SWT特征工程方法提供了一个数据集不可知的方法来提高短期预测的准确性.
这种技术提高了时间序列数据的信息性,从而在关键领域进行更可靠的预测.
来自SWT的特征的集成代表了对自然现象的时间序列预测的重大进步.

关键词:

一个年龄,一个年龄.功能工程的特点工程.功能扩展的功能扩展.功能提取功能提取预测的准确性预测的准确性这是LSTM的LSTM.静止波形变换静止波形变换时间序列预测时间序列预测波段变换的波段变换是什么

相关概念视频

01:20

Discrete-Time Fourier Series

642

The Discrete-Time Fourier Series (DTFS) is a fundamental concept in signal processing, serving as the discrete-time counterpart to the continuous-time Fourier series. It allows for the representation and analysis of discrete-time periodic signals in terms of their frequency components. Unlike its continuous counterpart, which utilizes integrals, the calculation of DTFS expansion coefficients involves summations due to the discrete nature of the signal.
For a discrete-time periodic signal x[n]...

642

01:29

Econometric Views (EViews)

535

Econometric Views, often stylized as EViews, is a package that merges statistical analysis with econometric studies. It is designed to provide tools for time series analysis, forecasting, and econometric model simulation. The software originated from MicroTSP software and has evolved significantly since its inception in 1981. The history of EViews is marked by a continuous effort to enhance its computational speed and user interface. It was initially developed for large computing systems but...

535

01:21

Linear Approximation in Time Domain

330

Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...

330

01:07

Effective Value of a Periodic Waveform

1.1K

The concept of effective value, the root mean square (RMS) value, is crucial in understanding electrical circuits and power delivery. This idea emerges from the necessity to measure the effectiveness of a voltage or current source in supplying power to a resistive load.
The effective value of a periodic current represents the direct current (DC) that conveys the same average power to a resistor as the periodic current itself. This concept is crucial when assessing AC circuits. To determine the...

1.1K

01:11

Continuous -time Fourier Transform

813

The Fourier series is instrumental in representing periodic functions, offering a powerful method to decompose such functions into a sum of sinusoids. This technique, however, necessitates modification when applied to nonperiodic functions. Consider a pulse-train waveform consisting of a series of rectangular pulses. When these pulses have a finite period, they can be accurately represented by a Fourier series. Yet, as the period approaches infinity, resulting in a single, isolated pulse, the...

813

01:15

Discrete Fourier Transform

835

The Discrete Fourier Transform (DFT) is a fundamental tool in signal processing, extending the discrete-time Fourier transform by evaluating discrete signals at uniformly spaced frequency intervals. This transformation converts a finite sequence of time-domain samples into frequency components, each representing complex sinusoids ordered by frequency. The DFT translates these sequences into the frequency domain, effectively indicating the magnitude and phase of each frequency component present...

835