Conference Proceeding Article
Compressive sensing has been successfully used for optimized operations in wireless sensor networks. However, raw data collected by sensors may be neither originally sparse nor easily transformed into a sparse data representation. This paper addresses the problem of transforming source data collected by sensor nodes into sparse representation with a few nonzero elements. Our contributions that address three major issues include: 1) an effective method that extracts population sparsity of the data, 2) a sparsity ratio guarantee scheme, and 3) a customized leaerning algorithm of the sparsifying dictionary. We introduce an unsupervised neural network to extract an intrinsic sparse coding of the data. The sparse codes are generated at the activation of the hidden layer using a sparsity nomination constraint and a shrinking mechanism. Our analysis using real data samples shows that the proposed method outperforms conventional sparsity-inducing methods.
Sparse coding, compressive sensing, sparse autoencoders, wireless sensor newtworks.
OS and Networks | Software Engineering
Software and Cyber-Physical Systems
2015 IEEE 40th Conference on Local Computer Networks (LCN), Clearwater, Florida, USA, 2015, October 26
City or Country
Florida, Clearwater, USA
MOHAMMAD, Abu Alsheik; LIN, Shaowei; TAN, Hwee-Pink; and NIYATO, Dusit.
Towards a robust sparse data representation in wireless sensor networks. (2015). 2015 IEEE 40th Conference on Local Computer Networks (LCN), Clearwater, Florida, USA, 2015, October 26. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3738
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.