Software to Support Layout and Data Collection for Machine-Learning-Based Real-World Sensors

Ayane Saito, Wataru Kawai, Yuta Sugiura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

There have been many studies of gesture recognition and posture estimation by combining real-world sensor and machine learning. In such situations, it is important to consider the sensor layout because the measurement result varies depending on the layout and the number of sensors as well as the motion to be measured. However, it takes time and effort to prototype devices multiple times in order to find a sensor layout that has high identification accuracy. Also, although it is necessary to acquire learning data for recognizing gestures, it takes time to get the data when the user changes the sensor layout. In this study, we developed software that can arrange real-world sensors. In this time, the software can handle distance-measuring sensors as real-world sensors. The user places these sensors freely in the software. The software measures the distance between the sensors and a mesh created from measurements of real-world deformation recorded by a Kinect. The classifier is generated using the time-series of distance data recorded by the software. In addition, we created a physical device that had the same sensor layout as the one designed with the software. We experimentally confirmed that the software could recognize the gestures on the physical device by using the generated classifier.

Original languageEnglish
Title of host publicationHCI International 2019 - Posters - 21st International Conference, HCII 2019, Proceedings
EditorsConstantine Stephanidis
PublisherSpringer Verlag
Pages198-205
Number of pages8
ISBN (Print)9783030235277
DOIs
Publication statusPublished - 2019 Jan 1
Event21st International Conference on Human-Computer Interaction, HCI International 2019 - Orlando, United States
Duration: 2019 Jul 262019 Jul 31

Publication series

NameCommunications in Computer and Information Science
Volume1033
ISSN (Print)1865-0929

Conference

Conference21st International Conference on Human-Computer Interaction, HCI International 2019
CountryUnited States
CityOrlando
Period19/7/2619/7/31

Fingerprint

Learning systems
Layout
Machine Learning
Sensor
Software
Sensors
Gesture
Classifiers
Classifier
Gesture recognition
Gesture Recognition
Time series
Mesh
Vary
Prototype
Necessary
Motion

Keywords

  • Distance-measuring sensor
  • Machine learning
  • Sensor layout

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

Cite this

Saito, A., Kawai, W., & Sugiura, Y. (2019). Software to Support Layout and Data Collection for Machine-Learning-Based Real-World Sensors. In C. Stephanidis (Ed.), HCI International 2019 - Posters - 21st International Conference, HCII 2019, Proceedings (pp. 198-205). (Communications in Computer and Information Science; Vol. 1033). Springer Verlag. https://doi.org/10.1007/978-3-030-23528-4_28

Software to Support Layout and Data Collection for Machine-Learning-Based Real-World Sensors. / Saito, Ayane; Kawai, Wataru; Sugiura, Yuta.

HCI International 2019 - Posters - 21st International Conference, HCII 2019, Proceedings. ed. / Constantine Stephanidis. Springer Verlag, 2019. p. 198-205 (Communications in Computer and Information Science; Vol. 1033).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Saito, A, Kawai, W & Sugiura, Y 2019, Software to Support Layout and Data Collection for Machine-Learning-Based Real-World Sensors. in C Stephanidis (ed.), HCI International 2019 - Posters - 21st International Conference, HCII 2019, Proceedings. Communications in Computer and Information Science, vol. 1033, Springer Verlag, pp. 198-205, 21st International Conference on Human-Computer Interaction, HCI International 2019, Orlando, United States, 19/7/26. https://doi.org/10.1007/978-3-030-23528-4_28
Saito A, Kawai W, Sugiura Y. Software to Support Layout and Data Collection for Machine-Learning-Based Real-World Sensors. In Stephanidis C, editor, HCI International 2019 - Posters - 21st International Conference, HCII 2019, Proceedings. Springer Verlag. 2019. p. 198-205. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-030-23528-4_28
Saito, Ayane ; Kawai, Wataru ; Sugiura, Yuta. / Software to Support Layout and Data Collection for Machine-Learning-Based Real-World Sensors. HCI International 2019 - Posters - 21st International Conference, HCII 2019, Proceedings. editor / Constantine Stephanidis. Springer Verlag, 2019. pp. 198-205 (Communications in Computer and Information Science).
@inproceedings{3e27f4bd58764be3bc52c913bd3da5b2,
title = "Software to Support Layout and Data Collection for Machine-Learning-Based Real-World Sensors",
abstract = "There have been many studies of gesture recognition and posture estimation by combining real-world sensor and machine learning. In such situations, it is important to consider the sensor layout because the measurement result varies depending on the layout and the number of sensors as well as the motion to be measured. However, it takes time and effort to prototype devices multiple times in order to find a sensor layout that has high identification accuracy. Also, although it is necessary to acquire learning data for recognizing gestures, it takes time to get the data when the user changes the sensor layout. In this study, we developed software that can arrange real-world sensors. In this time, the software can handle distance-measuring sensors as real-world sensors. The user places these sensors freely in the software. The software measures the distance between the sensors and a mesh created from measurements of real-world deformation recorded by a Kinect. The classifier is generated using the time-series of distance data recorded by the software. In addition, we created a physical device that had the same sensor layout as the one designed with the software. We experimentally confirmed that the software could recognize the gestures on the physical device by using the generated classifier.",
keywords = "Distance-measuring sensor, Machine learning, Sensor layout",
author = "Ayane Saito and Wataru Kawai and Yuta Sugiura",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-3-030-23528-4_28",
language = "English",
isbn = "9783030235277",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "198--205",
editor = "Constantine Stephanidis",
booktitle = "HCI International 2019 - Posters - 21st International Conference, HCII 2019, Proceedings",
address = "Germany",

}

TY - GEN

T1 - Software to Support Layout and Data Collection for Machine-Learning-Based Real-World Sensors

AU - Saito, Ayane

AU - Kawai, Wataru

AU - Sugiura, Yuta

PY - 2019/1/1

Y1 - 2019/1/1

N2 - There have been many studies of gesture recognition and posture estimation by combining real-world sensor and machine learning. In such situations, it is important to consider the sensor layout because the measurement result varies depending on the layout and the number of sensors as well as the motion to be measured. However, it takes time and effort to prototype devices multiple times in order to find a sensor layout that has high identification accuracy. Also, although it is necessary to acquire learning data for recognizing gestures, it takes time to get the data when the user changes the sensor layout. In this study, we developed software that can arrange real-world sensors. In this time, the software can handle distance-measuring sensors as real-world sensors. The user places these sensors freely in the software. The software measures the distance between the sensors and a mesh created from measurements of real-world deformation recorded by a Kinect. The classifier is generated using the time-series of distance data recorded by the software. In addition, we created a physical device that had the same sensor layout as the one designed with the software. We experimentally confirmed that the software could recognize the gestures on the physical device by using the generated classifier.

AB - There have been many studies of gesture recognition and posture estimation by combining real-world sensor and machine learning. In such situations, it is important to consider the sensor layout because the measurement result varies depending on the layout and the number of sensors as well as the motion to be measured. However, it takes time and effort to prototype devices multiple times in order to find a sensor layout that has high identification accuracy. Also, although it is necessary to acquire learning data for recognizing gestures, it takes time to get the data when the user changes the sensor layout. In this study, we developed software that can arrange real-world sensors. In this time, the software can handle distance-measuring sensors as real-world sensors. The user places these sensors freely in the software. The software measures the distance between the sensors and a mesh created from measurements of real-world deformation recorded by a Kinect. The classifier is generated using the time-series of distance data recorded by the software. In addition, we created a physical device that had the same sensor layout as the one designed with the software. We experimentally confirmed that the software could recognize the gestures on the physical device by using the generated classifier.

KW - Distance-measuring sensor

KW - Machine learning

KW - Sensor layout

UR - http://www.scopus.com/inward/record.url?scp=85069731452&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069731452&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-23528-4_28

DO - 10.1007/978-3-030-23528-4_28

M3 - Conference contribution

AN - SCOPUS:85069731452

SN - 9783030235277

T3 - Communications in Computer and Information Science

SP - 198

EP - 205

BT - HCI International 2019 - Posters - 21st International Conference, HCII 2019, Proceedings

A2 - Stephanidis, Constantine

PB - Springer Verlag

ER -