Premium
Data denoising and compression of intelligent transportation system based on two‐dimensional discrete wavelet transform
Author(s) -
Dou Huili,
Wang Guohua
Publication year - 2021
Publication title -
international journal of communication systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.344
H-Index - 49
eISSN - 1099-1131
pISSN - 1074-5351
DOI - 10.1002/dac.4809
Subject(s) - discrete wavelet transform , computer science , wavelet transform , intelligent transportation system , second generation wavelet transform , artificial intelligence , lifting scheme , stationary wavelet transform , wavelet , wavelet packet decomposition , image compression , pattern recognition (psychology) , algorithm , computer vision , image processing , image (mathematics) , civil engineering , engineering
Summary Two‐dimensional discrete wavelet transform is an important tool for digital image analysis. It is widely used in the field of image editing, such as image coding and compression and digital image processing. The realization of effective two‐dimensional discrete wavelet transform has important realities in data or image processing. This paper mainly introduces the research of intelligent transportation system data denoising and compression based on two‐dimensional discrete wavelet transform and intends to provide solutions to the problem of data overload in the process of intelligent transportation system data collection, transmission, and storage. This paper proposes the construction of two‐dimensional discrete wavelet transform, including separation calculation method and non‐separation calculation method, and proposes the construction of time–space data model of intelligent transportation system, including support vector machine (SVM), K nearest neighbor algorithm, and deep neural network algorithm. It is proposed to construct two‐dimensional wavelet transform to denoise and compress data of intelligent transportation systems. The experimental results in this paper show that the signal after denoising by two‐dimensional discrete wavelet transform is smoother, with a maximum difference of 0.57, and the denoising effect is better.