Abstract | ||
---|---|---|
E-health monitoring signals collected from wireless body area networks (WBANs) usually have some highly correlated structures in a certain transform domain (e.g., discrete cosine transform (DCT)). We exploit these structures and propose a fast recovery algorithm for low-rank and joint-sparse (L&S) structured WBAN signal in the framework of compressed sensing (CS). By using a simultaneously L&S signal model, we employ the number of the bigger singular values and Bayesian learning which incorporates an L&S-inducing prior over the signal and the appropriate hyperpriors over all hyperparameters to recover the signal. Experiments show that the proposed algorithm has a superior performance to state-of-the-art algorithms. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ICCC49849.2020.9238881 | 2020 IEEE/CIC International Conference on Communications in China (ICCC) |
Keywords | DocType | ISSN |
Internet of things,wireless body area network,sparse Bayesian learning,compressed sensing,low-rank and joint-sparse,fast recovery | Conference | 2377-8644 |
ISBN | Citations | PageRank |
978-1-7281-7328-3 | 0 | 0.34 |
References | Authors | |
11 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yanbin Zhang | 1 | 28 | 8.77 |
Longting Huang | 2 | 0 | 0.34 |
Yangqing Li | 3 | 1 | 2.04 |
Kai Zhang | 4 | 0 | 0.34 |
Changchuan Yin | 5 | 548 | 56.53 |