RF-Based Machine Learning Solution for Indoor Person Detection

RF-Based Machine Learning Solution for Indoor Person Detection

Pedro Maia De Santana, Thiago A. Scher, Juliano Joao Bazzo, Alvaro A. M. de Medeiros, Vicente A. de Sousa Jr.
Copyright: © 2021 |Pages: 9
DOI: 10.4018/IJITN.2021040104
OnDemand:
(Individual Articles)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Machine learning techniques applied to radio frequency (RF) signals are used for many applications in addition to data communication. In this paper, the authors propose a machine learning solution for classifying the number of people within an indoor ambient. The main idea is to identify a pattern of received signal characteristics according to the number of people. Experimental measurements are performed using a software-defined radio platform inside a laboratory. The data collected is post-processed by applying a feature mapping technique based on mean, standard deviation, and Shannon information entropy. This feature-space data is then used to train a supervised machine learning network for classifying scenarios with zero, one, two, and three people inside. The proposed solution presents significant accuracy in classification performance.
Article Preview
Top

Measurement Methodology

Experimental Setup

Measurements are carried out with the USRP N210 (Ettus Research, 2016). It is a low-cost software defined radio (SDR) platform designed and sold by Ettus Research (a National Instruments brand since 2010), and suitable for prototyping complete wireless communication systems by software hosted in a personal computer.

At the transmitter side, a CW signal at 2.4~GHz was generated by the Agilent's RF generator N9310A. At the receiver side, a USRP N210 with an attached CBX daughterboard (1.2-6~GHz) collected signal samples to be stored and processed in a laptop. A set of computer-to-usrp scripts were implemented to collect, store and calculate the received power from the signal samples.

Complete Article List

Search this Journal:
Reset
Volume 16: 1 Issue (2024)
Volume 15: 1 Issue (2023)
Volume 14: 1 Issue (2022)
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing