­
­
­
­

Inventi Impact: Distributed Sensor Networks

Articles

  • Inventi:edsn/19776/16
    A Multilayer Improved RBM Network Based Image Compression Method in Wireless Sensor\nNetworks
    01-Jan-1970 Research 2016 : July - September
    Chunling Cheng, Shu Wang, Xingguo Chen, Yanying Yang

    The processing capacity and power of nodes in a Wireless Sensor Network (WSN) are limited. And most image compression\nalgorithms in WSN are subject to random image content changes or have low image qualities after the images are decoded.Therefore,\nan image compression method based on multilayer Restricted Boltzmann Machine (RBM) network is proposed in this paper. The\nalternative iteration algorithm is also applied in RBM to optimize the training process. The proposed image compression method\nis compared with a region of interest (ROI) compression method in simulations. Under the same compression ratio, the qualities\nof reconstructed images are better than that of ROI. When the number of hidden units in top RBM layer is 8, the peak signal-to noise\nratio (PSNR) of the multilayer RBM network compression method is 74.2141, and it is much higher than that of ROI which\nis 60.2093. The multilayer RBM based image compression method has better compression performance and can effectively reduce\nthe energy consumption during image transmission in WSN.

    How to Cite this Article
    CC Compliant Citation: Chunling Cheng, Shu Wang, Xingguo Chen,\nand Yanying Yang, â??A Multilayer Improved RBM Network Based\nImage Compression Method in Wireless Sensor Networks,â?\nInternational Journal of Distributed Sensor Networks, vol. 2016,\nArticle ID 1851829, 11 pages, 2016. doi:10.1155/2016/1851829,\nhttp://creativecommons.org/licenses/by/4.0/.
    Download Full Text