Premium
Estimation of relative exposure levels for cellular phone users using a neural network
Author(s) -
Kim Soo Chan,
Nam Ki Chang,
Kim Deok Won
Publication year - 2006
Publication title -
bioelectromagnetics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.435
H-Index - 81
eISSN - 1521-186X
pISSN - 0197-8462
DOI - 10.1002/bem.20203
Subject(s) - phone , artificial neural network , estimation , computer science , statistics , artificial intelligence , mathematics , engineering , systems engineering , philosophy , linguistics
The wide and growing use of cellular phones has raised questions about the possible health risks associated with radio frequency (RF) electromagnetic fields. It would be helpful for epidemiologists as well as cellular phone users to obtain the relative exposure levels, because the RF exposure level is very difficult to accurately measure and quantify for all individuals. In this study, a neural network model was developed to estimate relative exposure levels on a scale of 0–10 and thus rank the individual risk of exposure using available information. We used parameters such as usage time per day, total usage period, hands‐free usage, extension of antenna, specific absorption rate (SAR) of the cellular phone, and flip or folder type, which are related to RF exposure. Using the relative exposure levels obtained from this model, epidemiologists can divide the subjects into exposed and nonexposed groups in a study investigating the relationship between exposure level and brain cancer in the future, provided that more knowledge between the cellular phone usage pattern and the exposure is available. Bioelectromagnetics 27:440–444, 2006. © 2006 Wiley‐Liss, Inc.