Support Vector Machine and Probability Neural Networks in a Device-free Passive Localisation (DfPL) Scenario

Gabriel Deak, K Curran, Joan Condell, Daniel Deak, piotr Mirowski

Research output: Contribution to journalArticle

Abstract

The holy grail of tracking people indoors is being able to locate them when they are not carrying any wireless tracking devices. The aim is to be able to track people just through their physical body interfering with a standard wireless network that would be in most peoples home. The human body contains about 70% water which attenuates the wireless signalreacting as an absorber. The changes in the signal along with prior fingerprinting of a physical location allow identification of a person’s location. This paper is focused on taking the principleof Device-free Passive Localisation (DfPL) and applying it to be able to actually distinguish if there is more than one person in the environment. In order to solve this problem, we tested a Support Vector Machine (SVM) classifier with kernel functions such as Linear, Quadratic, Polynomial, Gaussian Radial Basis Function (RBF) and Multilayer Perceptron (MLP), and a Probabilistic Neural Network (PNN) in order to detect movement based on changes in the wireless signal strength.
LanguageEnglish
Pages9-16
JournalImage Processing and Communications
Volume17
Issue number4
DOIs
Publication statusPublished - 1 Apr 2013

Fingerprint

Support vector machines
Neural networks
Multilayer neural networks
Wireless networks
Classifiers
Polynomials
Water

Cite this

@article{79d4072ed113422e92f63e0a2889b50b,
title = "Support Vector Machine and Probability Neural Networks in a Device-free Passive Localisation (DfPL) Scenario",
abstract = "The holy grail of tracking people indoors is being able to locate them when they are not carrying any wireless tracking devices. The aim is to be able to track people just through their physical body interfering with a standard wireless network that would be in most peoples home. The human body contains about 70{\%} water which attenuates the wireless signalreacting as an absorber. The changes in the signal along with prior fingerprinting of a physical location allow identification of a person’s location. This paper is focused on taking the principleof Device-free Passive Localisation (DfPL) and applying it to be able to actually distinguish if there is more than one person in the environment. In order to solve this problem, we tested a Support Vector Machine (SVM) classifier with kernel functions such as Linear, Quadratic, Polynomial, Gaussian Radial Basis Function (RBF) and Multilayer Perceptron (MLP), and a Probabilistic Neural Network (PNN) in order to detect movement based on changes in the wireless signal strength.",
author = "Gabriel Deak and K Curran and Joan Condell and Daniel Deak and piotr Mirowski",
year = "2013",
month = "4",
day = "1",
doi = "10.2478/v10248-012-0023-1",
language = "English",
volume = "17",
pages = "9--16",
journal = "Image Processing and Communications",
issn = "2300-8709",
number = "4",

}

Support Vector Machine and Probability Neural Networks in a Device-free Passive Localisation (DfPL) Scenario. / Deak, Gabriel; Curran, K; Condell, Joan; Deak, Daniel; Mirowski, piotr.

In: Image Processing and Communications, Vol. 17, No. 4, 01.04.2013, p. 9-16.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Support Vector Machine and Probability Neural Networks in a Device-free Passive Localisation (DfPL) Scenario

AU - Deak, Gabriel

AU - Curran, K

AU - Condell, Joan

AU - Deak, Daniel

AU - Mirowski, piotr

PY - 2013/4/1

Y1 - 2013/4/1

N2 - The holy grail of tracking people indoors is being able to locate them when they are not carrying any wireless tracking devices. The aim is to be able to track people just through their physical body interfering with a standard wireless network that would be in most peoples home. The human body contains about 70% water which attenuates the wireless signalreacting as an absorber. The changes in the signal along with prior fingerprinting of a physical location allow identification of a person’s location. This paper is focused on taking the principleof Device-free Passive Localisation (DfPL) and applying it to be able to actually distinguish if there is more than one person in the environment. In order to solve this problem, we tested a Support Vector Machine (SVM) classifier with kernel functions such as Linear, Quadratic, Polynomial, Gaussian Radial Basis Function (RBF) and Multilayer Perceptron (MLP), and a Probabilistic Neural Network (PNN) in order to detect movement based on changes in the wireless signal strength.

AB - The holy grail of tracking people indoors is being able to locate them when they are not carrying any wireless tracking devices. The aim is to be able to track people just through their physical body interfering with a standard wireless network that would be in most peoples home. The human body contains about 70% water which attenuates the wireless signalreacting as an absorber. The changes in the signal along with prior fingerprinting of a physical location allow identification of a person’s location. This paper is focused on taking the principleof Device-free Passive Localisation (DfPL) and applying it to be able to actually distinguish if there is more than one person in the environment. In order to solve this problem, we tested a Support Vector Machine (SVM) classifier with kernel functions such as Linear, Quadratic, Polynomial, Gaussian Radial Basis Function (RBF) and Multilayer Perceptron (MLP), and a Probabilistic Neural Network (PNN) in order to detect movement based on changes in the wireless signal strength.

U2 - 10.2478/v10248-012-0023-1

DO - 10.2478/v10248-012-0023-1

M3 - Article

VL - 17

SP - 9

EP - 16

JO - Image Processing and Communications

T2 - Image Processing and Communications

JF - Image Processing and Communications

SN - 2300-8709

IS - 4

ER -