多分辨率分析
离散小波变换
小波
计算机科学
阈值
小波变换
MATLAB语言
时间序列
系列(地层学)
数据挖掘
希尔伯特-黄变换
财务
人工智能
模式识别(心理学)
计量经济学
数学
机器学习
白噪声
经济
电信
古生物学
图像(数学)
生物
操作系统
作者
Hana Rabbouch,Bochra Rabbouch,Foued Saâdaoui
标识
DOI:10.1007/978-3-031-36570-6_5
摘要
In this chapter, we explore the use of multiresolution analysis techniques, including wavelet transforms such as the discrete wavelet transform (DWT), stationary wavelet transform (SWT), and empirical mode decomposition (EMD), for analyzing financial time series data in Matlab. These techniques allow for the decomposition of financial time series data into different frequency bands and the identification of trends and patterns at different scales, which can be useful for forecasting and trading strategies. We also explore the use of denoising techniques, such as wavelet thresholding, for improving the accuracy of financial time series data. Our results show that multiresolution analysis can provide valuable insights into financial time series data and can improve the performance of trading strategies.
科研通智能强力驱动
Strongly Powered by AbleSci AI