IMAGE COMPRESSION-WIRELESS SENSOR NETWORKS-VARIATIONAL AUTOENCODER AND RESTRICTED BOLTZMANN MACHINE
DESIGN DETAILS
Wireless Sensor Networks are an exciting technology that can solve a variety of applications. With advanced technology Wireless sensor network (WSNs) plays a key role in networking technologies since, it can be expanded without communication infrastructures. Wireless sensor network face certain limitations in terms of data redundancy, power and requires high bandwidth when used for multimedia data. Image compression method overcome those problems. Most image compression algorithms in WSN are subject to low image qualities after the images are decoded or have random image content changes. As the image contains massive number of redundancies resulting from high correlation between pixels, image compression method is designed. This Matlab design is based on Restricted Boltzmann Machine (RBM) and Variational Autoencoder (VAE) based compression considering Gray (2D) and Color (3D) images for performance evaluation with the number of hidden units i.e., layer is 2,4 and 8. Finally the peak signal-to noise ratio (PSNR) and Signal to Noise Ratio (SNR) are calculated and compared between two methods. variational
REFERENCES
Reference Paper-1: Image Compression in Wireless Sensor Networks Using Autoencoder and RBM Method
Author’s Name: S. Aruna Deepthi, E. Sreenivasa Rao and M. N. Giri Prasad
Source: Innovations in Electronics and Communication Engineering
Year: 2019
Reference Paper-2: A Multilayer Improved RBM Network Based Image Compression
Method in Wireless Sensor Networks
Author’s Name: Chunling Cheng, ShuWang, Xingguo Chen, and Yanying Yang
Source: Hindawi Publishing Corporation
Year: 2016
Reference Paper-3: Autoencoding beyond Pixels using a Learned Similarity Metric
Author’s Name: Anders Boesen Lindbo Larsen, Soren Kaae Sonderby, Hugo Larochelle and, Ole Winther
Source: ICML
Year: 2016
Request source code for academic purpose, fill REQUEST FORM below,
http://www.verilogcourseteam.com/requ...
You may contact +91 7904568456 by WhatsApp Chat, for paid services.
We are available on Telegram and Signal.
Visit Website: http://www.verilogcourseteam.com/
Visit Our Social Media
Like our Facebook Page: / verilogcourseteam
Subscribe: / verilogcourseteamelectricalprojects
Subscribe: / verilogcourseteammatlabproject
Subscribe: / verilogcourseteam