skip to main content
10.1145/3267305.3267509acmconferencesArticle/Chapter ViewAbstractPublication PagesubicompConference Proceedingsconference-collections
research-article

A Multi-Sensor Setting Activity Recognition Simulation Tool

Published: 08 October 2018 Publication History

Abstract

Motion capture generates data which are often more accurate than those captured by multiple of accelerometer sensors by their physical specification. Based on the observation that accelerometer data can be obtained by the second derivation of position data from motion capture, we propose a simulator, called MEASURed, for activity recognition classifiers. MEASURed can accommodate any number of virtual accelerometer sensors on the body based on some given motion capture data. Therefore, MEASURed can evaluate activity recognition classifiers in settings with different number, placement, and sampling rate of accelerometer sensors. Our results show that the F1-Score estimated by MEASURed is close to that obtained with the real accelerometer data.

References

[1]
P. Asare, R. F. Dickerson, and et al. 2013. BodySim: a multi-domain modeling and simulation framework for body sensor networks research and design. In Proc. of SenSys '13. 1--2.
[2]
O. Banos, A. Calatroni, and et al. 2012. Kinect=IMU? Learning MIMO Signal Mappings to Automatically Translate Activity Recognition Systems Across Sensor Modalities. In Proc. of the 16th ISWC. IEEE Comp. Soc., Washington, DC, USA, 92--99.
[3]
F. Ofli et al. 2013. Berkeley MHAD: A comprehensive Multimodal Human Action Database. In 2013 IEEE WACV. 53--60.
[4]
H. Gjoreski et al. 2017. A Versatile Annotated Dataset for Multimodal Locomotion Analytics with Mobile Devices. In Proceedings (SenSys '17). ACM, New York, NY, USA, Article 61, 2 pages.
[5]
A. D. Young, M. J. Ling, and D. K. Arvind. 2011. IMUSim: A simulation environment for inertial sensing algorithm design and evaluation. In Proc. 10th ACM/IEEE IPSN. 199--210.

Cited By

View all
  • (2024)Physical Non-inertial Poser (PNP): Modeling Non-inertial Effects in Sparse-inertial Human Motion CaptureACM SIGGRAPH 2024 Conference Papers10.1145/3641519.3657436(1-11)Online publication date: 13-Jul-2024
  • (2024)CROMOSim: A Deep Learning-Based Cross-Modality Inertial Measurement SimulatorIEEE Transactions on Mobile Computing10.1109/TMC.2022.323037023:1(302-312)Online publication date: Jan-2024
  • (2023)Towards Generalized mmWave-based Human Pose Estimation through Signal AugmentationProceedings of the 29th Annual International Conference on Mobile Computing and Networking10.1145/3570361.3613302(1-15)Online publication date: 2-Oct-2023
  • Show More Cited By

Index Terms

  1. A Multi-Sensor Setting Activity Recognition Simulation Tool

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    UbiComp '18: Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers
    October 2018
    1881 pages
    ISBN:9781450359665
    DOI:10.1145/3267305
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Sponsors

    In-Cooperation

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 08 October 2018

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. activity recognition
    2. inertial sensors
    3. motion capture

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    UbiComp '18
    Sponsor:

    Acceptance Rates

    Overall Acceptance Rate 764 of 2,912 submissions, 26%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)23
    • Downloads (Last 6 weeks)4
    Reflects downloads up to 15 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2024)Physical Non-inertial Poser (PNP): Modeling Non-inertial Effects in Sparse-inertial Human Motion CaptureACM SIGGRAPH 2024 Conference Papers10.1145/3641519.3657436(1-11)Online publication date: 13-Jul-2024
    • (2024)CROMOSim: A Deep Learning-Based Cross-Modality Inertial Measurement SimulatorIEEE Transactions on Mobile Computing10.1109/TMC.2022.323037023:1(302-312)Online publication date: Jan-2024
    • (2023)Towards Generalized mmWave-based Human Pose Estimation through Signal AugmentationProceedings of the 29th Annual International Conference on Mobile Computing and Networking10.1145/3570361.3613302(1-15)Online publication date: 2-Oct-2023
    • (2022)Virtual IMU Data Augmentation by Spring-Joint Model for Motion Exercises Recognition without Using Real DataProceedings of the 2022 ACM International Symposium on Wearable Computers10.1145/3544794.3558460(79-83)Online publication date: 11-Sep-2022
    • (2022)CROMOSim: A Deep Learning-based Cross-modality Inertial Measurement Simulator2022 2nd International Workshop on Cyber-Physical-Human System Design and Implementation (CPHS)10.1109/CPHS56133.2022.9804560(1-6)Online publication date: May-2022
    • (2021)Complex Deep Neural Networks from Large Scale Virtual IMU Data for Effective Human Activity Recognition Using WearablesSensors10.3390/s2124833721:24(8337)Online publication date: 13-Dec-2021
    • (2021)Optimizing Sensor Position with Virtual Sensors in Human Activity Recognition System DesignSensors10.3390/s2120689321:20(6893)Online publication date: 18-Oct-2021
    • (2021)Translating Videos into Synthetic Training Data for Wearable Sensor-Based Activity Recognition Systems Using Residual Deep Convolutional NetworksApplied Sciences10.3390/app1107309411:7(3094)Online publication date: 31-Mar-2021
    • (2021)Can You See It?GetMobile: Mobile Computing and Communications10.1145/3486880.348689125:2(38-42)Online publication date: 15-Sep-2021
    • (2021)When Video meets Inertial SensorsProceedings of the International Conference on Internet-of-Things Design and Implementation10.1145/3450268.3453537(182-194)Online publication date: 18-May-2021
    • Show More Cited By

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media