A Study on Principal Component Analysis over Wireless Channel

Authors

  • R. Upadhyay Department of Electronics & Telecommunicati, Institute of Engineering & Technology, Devi Ahilya University, Khandwa Road, Indore 452001, India.
  • A. Soni Department of Electronics & Telecommunicati, Institute of Engineering & Technology, Devi Ahilya University, Khandwa Road, Indore 452001, India
  • P. Panse Department of Electronics & Telecommunicati, Institute of Engineering & Technology, Devi Ahilya University, Khandwa Road, Indore 452001, India
  • U. R. Bhatt Department of Electronics & Telecommunicati, Institute of Engineering & Technology, Devi Ahilya University, Khandwa Road, Indore 452001, India

Keywords:

AWGN, Dimensionality Reduction, Principal Component Analysis, Rician Channel,

Abstract

Applications in many fields such as the internet of things (IoT), stock market, image compression, food adulteration, wireless physical layer key generation, etc. are becoming progressively complex due to a large number of users and increment in their usage. Data obtained by these applications are in huge amount creating a high computational cost. Further, it is difficult to handle and analyze it. To deal with such problems, dimensionality reduction techniques are used and one of the dimensionality reduction techniques is the Principal Component Analysis (PCA). In this paper, PCA is applied over a wireless Rician channel with AWGN at different SNR. It is concluded that the information content is more in less number of principal components with samples at higher SNR. It is also observed that the different combinations of several groups and elements in the sample space provide a different cumulative percentage of information.

Downloads

Published

2019-12-15

How to Cite

Upadhyay, R., Soni, A., Panse, P., & Bhatt, U. R. (2019). A Study on Principal Component Analysis over Wireless Channel. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 11(4), 5–9. Retrieved from https://jtec.utem.edu.my/jtec/article/view/5371