One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial Sensor
A number of previous works have shown that information about a subject is encoded in sparse kinematic information, such as the one revealed by so-called point light walkers. With the work at hand, we extend these results to classifications of soft biometrics from inertial sensor recordings at a sing...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2015-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/15/12/29907 |
_version_ | 1811303798351593472 |
---|---|
author | Qaiser Riaz Anna Vögele Björn Krüger Andreas Weber |
author_facet | Qaiser Riaz Anna Vögele Björn Krüger Andreas Weber |
author_sort | Qaiser Riaz |
collection | DOAJ |
description | A number of previous works have shown that information about a subject is encoded in sparse kinematic information, such as the one revealed by so-called point light walkers. With the work at hand, we extend these results to classifications of soft biometrics from inertial sensor recordings at a single body location from a single step. We recorded accelerations and angular velocities of 26 subjects using integrated measurement units (IMUs) attached at four locations (chest, lower back, right wrist and left ankle) when performing standardized gait tasks. The collected data were segmented into individual walking steps. We trained random forest classifiers in order to estimate soft biometrics (gender, age and height). We applied two different validation methods to the process, 10-fold cross-validation and subject-wise cross-validation. For all three classification tasks, we achieve high accuracy values for all four sensor locations. From these results, we can conclude that the data of a single walking step (6D: accelerations and angular velocities) allow for a robust estimation of the gender, height and age of a person. |
first_indexed | 2024-04-13T07:54:35Z |
format | Article |
id | doaj.art-35f463a5aa3a4235a394a00c781aba64 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-13T07:54:35Z |
publishDate | 2015-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-35f463a5aa3a4235a394a00c781aba642022-12-22T02:55:26ZengMDPI AGSensors1424-82202015-12-011512319993201910.3390/s151229907s151229907One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial SensorQaiser Riaz0Anna Vögele1Björn Krüger2Andreas Weber3Department of Computer Science II, Universität Bonn, Bonn 53113, GermanyDepartment of Computer Science II, Universität Bonn, Bonn 53113, GermanyGokhale Method Institute, Stanford, CA 94305, USADepartment of Computer Science II, Universität Bonn, Bonn 53113, GermanyA number of previous works have shown that information about a subject is encoded in sparse kinematic information, such as the one revealed by so-called point light walkers. With the work at hand, we extend these results to classifications of soft biometrics from inertial sensor recordings at a single body location from a single step. We recorded accelerations and angular velocities of 26 subjects using integrated measurement units (IMUs) attached at four locations (chest, lower back, right wrist and left ankle) when performing standardized gait tasks. The collected data were segmented into individual walking steps. We trained random forest classifiers in order to estimate soft biometrics (gender, age and height). We applied two different validation methods to the process, 10-fold cross-validation and subject-wise cross-validation. For all three classification tasks, we achieve high accuracy values for all four sensor locations. From these results, we can conclude that the data of a single walking step (6D: accelerations and angular velocities) allow for a robust estimation of the gender, height and age of a person.http://www.mdpi.com/1424-8220/15/12/29907estimation of soft biometricsgender, age and height estimation from inertial datagait analysisinertial sensors to estimate gender, age and heightaccelerometers |
spellingShingle | Qaiser Riaz Anna Vögele Björn Krüger Andreas Weber One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial Sensor Sensors estimation of soft biometrics gender, age and height estimation from inertial data gait analysis inertial sensors to estimate gender, age and height accelerometers |
title | One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial Sensor |
title_full | One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial Sensor |
title_fullStr | One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial Sensor |
title_full_unstemmed | One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial Sensor |
title_short | One Small Step for a Man: Estimation of Gender, Age and Height from Recordings of One Step by a Single Inertial Sensor |
title_sort | one small step for a man estimation of gender age and height from recordings of one step by a single inertial sensor |
topic | estimation of soft biometrics gender, age and height estimation from inertial data gait analysis inertial sensors to estimate gender, age and height accelerometers |
url | http://www.mdpi.com/1424-8220/15/12/29907 |
work_keys_str_mv | AT qaiserriaz onesmallstepforamanestimationofgenderageandheightfromrecordingsofonestepbyasingleinertialsensor AT annavogele onesmallstepforamanestimationofgenderageandheightfromrecordingsofonestepbyasingleinertialsensor AT bjornkruger onesmallstepforamanestimationofgenderageandheightfromrecordingsofonestepbyasingleinertialsensor AT andreasweber onesmallstepforamanestimationofgenderageandheightfromrecordingsofonestepbyasingleinertialsensor |