Signal local Reconstruction Algorithm based on Compressed Sensing and Unsupervised Learning
- DOI
- 10.2991/msmee-17.2017.300How to use a DOI?
- Keywords
- Signal Reconstruction; Sparsity; Compressed Sensing; Local Reconstruction; Unsupervised Learning
- Abstract
With the rapid growth of data volume of the Internet and other platforms, the bandwidth needed for data transmission and reception is getting higher and higher, and the requirements for processing speed and sampling frequency of information acquisition are also improved. Based on the Shannon sampling theory, it is found that only when the sampling frequency of the signal is higher than or equal to twice the signal bandwidth, can higher-quality analog signal recovery effect be achieved. In order to efficiently deal with the problem of the fast reconstruction of the unknown sparsity of the compressed signal, a new method with wider adaptability and higher efficiency is proposed. Firstly, use isometric rules to obtain upper and lower bounds of the compressed output signal, and take the closest integer value as estimation value of sparse signal; secondly, by reducing the number of iterative projection support of observation vector to realize complexity reduction of calculation of signal reconstruction, and design evaluation probability system for signal reconstruction to achieve implementation of the validation of the proposed index scheme; finally, based on the experimental verification, the proposed method can obtain and achieve fast reconstruction of sparsity of unknown signal and can obtain higher success rate than backtracking scheme.
- Copyright
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Lingli Tan PY - 2017/05 DA - 2017/05 TI - Signal local Reconstruction Algorithm based on Compressed Sensing and Unsupervised Learning BT - Proceedings of the 2017 2nd International Conference on Materials Science, Machinery and Energy Engineering (MSMEE 2017) PB - Atlantis Press SP - 1657 EP - 1663 SN - 2352-5401 UR - https://doi.org/10.2991/msmee-17.2017.300 DO - 10.2991/msmee-17.2017.300 ID - Tan2017/05 ER -