TY - GEN
T1 - Machine Learning for Terahertz Communication with Human-Implantable Devices
AU - Sullivan, Kieran
AU - Tolan, Martin
N1 - Funding Information:
ACKNOWLEDGMENT The work in this paper has been facilitated by the CogNet project (671625), which is funded under the European Commission’s H2020 5G-PPP initiative.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/8/20
Y1 - 2018/8/20
N2 - Network communication is now critical for several different sectors, including transport, manufacturing, agriculture, and healthcare. The fifth generation (5G) of networks can support and further enhance this vertical sector work, but new paradigms and technologies are required to meet increasing expectations. Terahertz communication offers potential in this regard, especially given its high transmission rates. A number of issues must be considered, however, including signal attenuation due to the absorption characteristic of the transference medium. In this paper, we examine a healthcare scenario where communication between transmitter and receiver is carried out at terahertz frequencies. Our results show that when combined with a machine learning mechanism, terahertz communications protocols can be established to reduce signal path losses in the system.
AB - Network communication is now critical for several different sectors, including transport, manufacturing, agriculture, and healthcare. The fifth generation (5G) of networks can support and further enhance this vertical sector work, but new paradigms and technologies are required to meet increasing expectations. Terahertz communication offers potential in this regard, especially given its high transmission rates. A number of issues must be considered, however, including signal attenuation due to the absorption characteristic of the transference medium. In this paper, we examine a healthcare scenario where communication between transmitter and receiver is carried out at terahertz frequencies. Our results show that when combined with a machine learning mechanism, terahertz communications protocols can be established to reduce signal path losses in the system.
KW - implantable devices
KW - machine learning
KW - signal path loss
KW - terahertz communication
UR - https://www.scopus.com/pages/publications/85053529218
U2 - 10.1109/EuCNC.2018.8443261
DO - 10.1109/EuCNC.2018.8443261
M3 - Conference contribution
AN - SCOPUS:85053529218
SN - 9781538614785
T3 - 2018 European Conference on Networks and Communications, EuCNC 2018
SP - 293
EP - 297
BT - 2018 European Conference on Networks and Communications, EuCNC 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 European Conference on Networks and Communications, EuCNC 2018
Y2 - 18 June 2018 through 21 June 2018
ER -
