An Autoencoder-Based Data Collection Scheme for Wireless Sensor Networks
Received date: 2017-08-25
Revised date: 2017-10-05
Online published: 2018-05-31
Data collection is one of the key operations in wireless sensor networks. In this paper, we propose an energy efcient data collection scheme for wireless sensor networks by using an autoencoder. It includes the model training process and the data collection process. In the model training process, historical dataset is utilized to train the autoencoder with the goal of obtaining a measurement matrix and a reconstruction matrix. In the data collection process, the measurement matrix is utilized to compress the sensed data in a distributed manner and the reconstruction matrix is utilized to reconstruct the surveillant data of the whole sensor network. The experiment results show that the proposed scheme presents higher data compression ratio and higher data reconstruction accuracy as well as faster data reconstruction speed than existed data collection schemes.
LI Guo-rui, TIAN Li, CUI Hao, CHEN Hao-bo . An Autoencoder-Based Data Collection Scheme for Wireless Sensor Networks[J]. Journal of Applied Sciences, 2018 , 36(3) : 411 -419 . DOI: 10.3969/j.issn.0255-8297.2018.03.001
[1] Rawat P, Singh K, Chaouchi H, Bonnin J. Wireless sensor networks:a survey on recent developments and potential synergies[J]. The Journal of Supercomputing, 2014, 68(1):1-48.
[2] Campobello G, Segreto A, Serrano S. Data gathering techniques for wireless sensor networks:a comparison[J]. International Journal of Distributed Sensor Networks, 2016, 12(3):1-17.
[3] Monika R, Hemalatha R, Radha S. Energy efcient weighted sampling matrix based CS technique for WSN[C]//Proceedings of the 14th IEEE Sensors Conference, Busan, 2015:1-4.
[4] Lan K C, Wei M Z. A compressibility-based clustering algorithm for hierarchical compressive data gathering[J]. IEEE Sensors Journal, 2017, 17(8):2550-2562.
[5] Wang K, Liu Y, Wang Q, Jing X. Compressed sensing of IR-UWB wireless sensor network data based on two-dimensional measurements[J]. Chinese Journal of Electronics, 2015, 24(3):627-632.
[6] Karakus C, Gurbuz C, Tavli B. Analysis of energy efciency of compressive sensing in wireless sensor networks[J]. IEEE Sensors Journal, 2013, 13(5):1999-2008
[7] Chen W, Rodrigues D, Wassell J. A Frechet mean approach for compressive sensing date acquisition and reconstruction in wireless sensor networks[J]. IEEE Transactions on Wireless Communications, 2012, 11(10):3598-3606.
[8] Tropp J, Gilbert A. Signal recovery from random measurements via orthogonal matching pursuit[J]. IEEE Transactions on Information Theory, 2007, 53(12):4655-4666.
[9] Blumensath T, Davies M. Iterative hard thresholding for compressed sensing[J]. Applied & Computational Harmonic Analysis, 2008, 27(3):265-274.
[10] Rumelhart D, Hinton G, Williams J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088):533-536.
[11] Luo C, Wu F, Sun J, Chen C W. Compressive data gathering for large-scale wireless sensor networks[C]//Proceedings of the 15th Annual International Conference on Mobile Computing and Networking. New York, 2009:145-456.
/
| 〈 |
|
〉 |
