Comparing machine learning classifiers and linear/logistic regression to explore the relationship between hand dimensions and demographic characteristics

O. Miguel-Hurtado, R. Guest, S.V. Stevenage, G.J. Neil, S. Black

Research output: Contribution to journalArticle

Abstract

Understanding the relationship between physiological measurements from human subjects and their demographic data is important within both the biometric and forensic domains. In this paper we explore the relationship between measurements of the human hand and a range of demographic features. We assess the ability of linear regression and machine learning classifiers to predict demographics from hand features, thereby providing evidence on both the strength of relationship and the key features underpinning this relationship. Our results show that we are able to predict sex, height, weight and foot size accurately within various data-range bin sizes, with machine learning classification algorithms out-performing linear regression in most situations. In addition, we identify the features used to provide these relationships applicable across multiple applications.
Original languageEnglish
JournalPLoS One
Volume11
Issue number11
Publication statusPublished - 2016

Fingerprint

sociodemographic characteristics
artificial intelligence
Linear regression
Learning systems
Logistics
Linear Models
hands
Classifiers
demographic statistics
Hand
Logistic Models
Demography
Bins
Biometrics
biometry
Foot
Weights and Measures
gender
Machine Learning

Cite this

@article{5c68c39783644b3dbc84522a7fd4c7cc,
title = "Comparing machine learning classifiers and linear/logistic regression to explore the relationship between hand dimensions and demographic characteristics",
abstract = "Understanding the relationship between physiological measurements from human subjects and their demographic data is important within both the biometric and forensic domains. In this paper we explore the relationship between measurements of the human hand and a range of demographic features. We assess the ability of linear regression and machine learning classifiers to predict demographics from hand features, thereby providing evidence on both the strength of relationship and the key features underpinning this relationship. Our results show that we are able to predict sex, height, weight and foot size accurately within various data-range bin sizes, with machine learning classification algorithms out-performing linear regression in most situations. In addition, we identify the features used to provide these relationships applicable across multiple applications.",
author = "O. Miguel-Hurtado and R. Guest and S.V. Stevenage and G.J. Neil and S. Black",
year = "2016",
language = "English",
volume = "11",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "11",

}

Comparing machine learning classifiers and linear/logistic regression to explore the relationship between hand dimensions and demographic characteristics. / Miguel-Hurtado, O.; Guest, R.; Stevenage, S.V.; Neil, G.J.; Black, S.

In: PLoS One, Vol. 11, No. 11, 2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Comparing machine learning classifiers and linear/logistic regression to explore the relationship between hand dimensions and demographic characteristics

AU - Miguel-Hurtado, O.

AU - Guest, R.

AU - Stevenage, S.V.

AU - Neil, G.J.

AU - Black, S.

PY - 2016

Y1 - 2016

N2 - Understanding the relationship between physiological measurements from human subjects and their demographic data is important within both the biometric and forensic domains. In this paper we explore the relationship between measurements of the human hand and a range of demographic features. We assess the ability of linear regression and machine learning classifiers to predict demographics from hand features, thereby providing evidence on both the strength of relationship and the key features underpinning this relationship. Our results show that we are able to predict sex, height, weight and foot size accurately within various data-range bin sizes, with machine learning classification algorithms out-performing linear regression in most situations. In addition, we identify the features used to provide these relationships applicable across multiple applications.

AB - Understanding the relationship between physiological measurements from human subjects and their demographic data is important within both the biometric and forensic domains. In this paper we explore the relationship between measurements of the human hand and a range of demographic features. We assess the ability of linear regression and machine learning classifiers to predict demographics from hand features, thereby providing evidence on both the strength of relationship and the key features underpinning this relationship. Our results show that we are able to predict sex, height, weight and foot size accurately within various data-range bin sizes, with machine learning classification algorithms out-performing linear regression in most situations. In addition, we identify the features used to provide these relationships applicable across multiple applications.

M3 - Article

VL - 11

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 11

ER -