A Network Coding Scheme Transmitting Specific Data and Universal Data Based on Deep Learning
- 8 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 18 (2) , 872-880
Abstract
For a wireless sensor network (WSN), we proposed a network coding scheme that adopts a neural network (NN) instead of methods based on Shannon theory, and this scheme can transmit specific data such as images of specific data sets. In further, it also can transmit universal data with the channel code. In the source, the specific data or the code word is sent out to a network performing network coding, where the universal data are encoded into the code word with Reed Solomon code and Polar code. In the intermediate nodes, the network coding based on Shannon theory is replaced with a multilayer perceptron, convolutional neural networks (CNNs), and recurrent neural networks (RNNs). In the sink, we trained a NN with the received massage as the input and the original data as the label. The trained NN includes the sublayers, which are the subneural networks in every node. We test the new transmission scheme for some datasets and channel code such as Reed Solomon code in a WSN environment, and it is proven to be effective.Keywords
Funding Information
- Natural Science Foundation of Heilongjiang Province (LH2019F052)
This publication has 23 references indexed in Scilit:
- Joint Activity Detection, Channel Estimation, and Data Decoding for Grant-Free Massive Random AccessIEEE Internet of Things Journal, 2023
- Survey on recent advances in IoT application layer protocols and machine learning scope for research directionsDigital Communications and Networks, 2022
- Deep Learning Aided Robust Joint Channel Classification, Channel Estimation, and Signal Detection for Underwater Optical CommunicationIEEE Transactions on Communications, 2020
- How to Distribute Computation in Networks2020
- Linear Network Error Correction Coding Revisited2020
- Soft Maximum Likelihood Decoding using GRAND2020
- Deep Joint Source-channel Coding for Wireless Image Transmission2019
- The Nonlinear Network Coding and Its Application in Error-Correcting CodesWireless Personal Communications, 2017
- An Introduction to Deep Learning for the Physical LayerIEEE Transactions on Cognitive Communications and Networking, 2017
- Combining network coding and compressed sensing for error correction in wireless sensor networksInternational Journal of Communication Systems, 2014