Manuscript Due

Jan. 25, 2018 (closed)

Description

As wireless communication becomes ubiquitous, an excess of devices ranging from smartphones to medical implants is increasingly competing for use of unlicensed spectrum. As per today's network, these radio devices may interfere with each other by limiting its real-world throughput and capacity. To overcome the hurdles and challenges, these devices must calculate the nature of the environment; define interference limits, and to predict future time samples to cancel unwanted components of a corrupted received signal. If not accounted for, interference can lead to corruption of data that leads to unnecessary retransmission of corrupted packets. Since these results in a degradation of network performance, solving the problem of wireless interference prediction will yield networks with robust performance even while multiple devices contend for limited, shared spectrum. Solving the wireless interference problem is challenging because a wireless signal can be corrupted by a variety of other ambient wireless signals, such as Bluetooth, Wi-Fi, or Long Term Evolution protocol transmissions. The environment, such as walls and obstacles, can further attenuate these signals. The net randomness can make determining wireless interference a challenging endeavour. At the same time, wireless signals may exhibit specific periodic structure and cyclo-stationary features. Modern wireless architectures have not fully realized the potential of utilizing this data to segment and predict wireless interference.

Topics of interest include:
  • Deep Learning methods for Wireless Communication Networks
  • Interference correction by deep machine learning
  • Challenges and hurdles of wireless communication and its solution by machine learning methods
  • Deep Belief Networks and its application in Wireless communications
  • Convolution Neural networks and its applications in wireless communications
  • Deep learning for Adhoc and its strategies.
  • Transcend methods of implementations optimized M2M
  • Machine learning for wireless communication interference, etc.

Lead Guest Editor

  • Nagaraj Balakrishnan, Karpagam College of Engineering, India

Guest Editors

  • Danilo Pelusi, University of Teramo, Italy
  • Chin-Teng Lin, University of Technology, Australia
  • Subramaniam Ganesan, Oakland University, USA
EURASIP Journal on Wireless Communications and Networking