Summary
International Conference on Emerging Technologies for Communications
2021
Session Number:A1
Session:
Number:A1-1
Machine-Learning Approach to Binary Classification of Uplink-Channel States for Secure Body-Coupled Communication
Ai-ichiro Sasaki, Akinori Ban ,
pp.-
Publication Date:2021/12/1
Online ISSN:2188-5079
Summary:
Body-coupled communication (BCC) is a short-range wireless technology that can link communication devices with the human body. The BCC channel is formed by a capacitive coupling between the body, devices, and earth. When another person approaches the BCC system, the person becomes inevitably involved in the system because of the coupling. In this situation, eavesdropping and accidental data transmission can occur. A feasible solution to this security problem is to detect the existence of the undesirable person based on the information of received signals. We emphasize that fiber-optic EO-OE converters are indispensable for correctly evaluating the received signals in BCC uplink channels because they are affected by electronic apparatuses. We demonstrated that an undesirable person can be detected with an accuracy of 96% by using machine learning.