research-article

On strategies for budget-based online annotation in human activity recognition

Authors:

Daniel RoggenAuthors Info & Claims

UbiComp '14 Adjunct: Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication

Pages 767 - 776

https://doi.org/10.1145/2638728.2641300

Published: 13 September 2014 Publication History

Abstract

Bootstrapping activity recognition systems in ubiquitous and mobile computing scenarios often comes with the challenge of obtaining reliable ground truth annotations. A promising approach to overcome these difficulties involves obtaining online activity annotations directly from users. However, such direct engagement has its limitations as users typically show only limited tolerance for unwanted interruptions such as prompts for annotations. In this paper we explore the effectiveness of approaches to online, user-based annotation of activity data. Our central assumption is the existence of a fixed, limited budget of annotations a user is willing to provide. We evaluate different strategies on how to spend such a budget most effectively. Using the Opportunity benchmark we simulate online annotation scenarios for a variety of budget configurations and we show that effective online annotation can still be achieved using reduced annotation effort.

References

[1]

Alemdar, H., Kasteren, T. v., and Ersoy, C. Using Active Learning to Allow Activity Recognition on a Large Scale. In Proc. AmI (2011).

Digital Library

[2]

Bao, L., and Intille, S. S. Activity Recognition from User-Annotated Acceleration Data. In Proc. Pervasive (2004).

[3]

Bhattacharya, S., Nurmi, P., Hammerla, N., and Plötz, T. Using unlabeled data in a sparse-coding framework for human activity recognition. Pervasive and Mobile Computing (2014). in press.

[4]

Brand, A. Public health genomics and personalized healthcare: a pipeline from cell to society. Drug Metabolism and Interactions (2012).

[5]

Bull, F. C., Kreuter, M. W., and Scharff, D. P. Effects of tailored, personalized and general health messages on physical activity. Patient Education and Counseling (1999).

[6]

Bulling, A., Blanke, U., and Schiele, B. A tutorial on human activity recognition using body-worn inertial sensors. ACM Computing Surveys (2013).

Digital Library

[7]

Chavarriaga, R., et al. The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition. Pattern Recognition Letters (2013).

Digital Library

[8]

Cohn, D. A., Ghahramani, Z., and Jordan, M. I. Active Learning with Statistical Models. Journal of Artificial Intelligence Research (1996).

Digital Library

[9]

Huynh, T., Fritz, M., and Schiele, B. Discovery of activity patterns using topic models. In Proc. UbiComp (2008).

Digital Library

[10]

Intille, S. S., Bao, L., Tapia, E. M., and Rondoni, J. Acquiring in situ training data for context-aware ubiquitous computing applications. In Proc. CHI (2004).

Digital Library

[11]

Lim, B. Y., and Dey, A. K. Investigating Intelligibility for Uncertain Context-Aware Applications. Proc. UbiComp (2011).

Digital Library

[12]

Okeyo, G., Chen, L., Wang, H., and Sterritt, R. Dynamic sensor data segmentation for real-time knowledge-driven activity recognition. PMC (2014).

Digital Library

[13]

Plötz, T., Hammerla, N., and Olivier, P. Feature Learning for Activity Recognition in Ubiquitous Computing. In Proc. Int. Joint Conf. on Art. Intelligence (IJCAI) (2011).

Digital Library

[14]

Plötz, T., Hammerla, N., Rozga, A., Reavis, A., Call, N., and Abowd, G. D. Automatic Assessment of Problem Behavior in Individuals with Developmental Disabilities. In Proc. UbiComp (2012).

Digital Library

[15]

Plötz, T., Moynihan, P., Pham, C., and Olivier, P. Activity Recognition and Healthier Food Preparation. In Activity Recognition in Pervasive Intelligent Environments. Atlantis Press, 2010.

[16]

Rebetez, J., Satizábal, H. F., and Perez-uribe, A. Reducing User Intervention in Incremental Activity Recognition for Assistive Technologies. In Proc. ISWC (2013).

Digital Library

[17]

Sagha, H., Digumarti, S. T., Chavarriaga, R., Calatroni, A., Roggen, D., and Troester, G. Benchmarking classification techniques using the Opportunity human activity dataset. In Proc. SMC (2011).

[18]

Scollon, C. N., Kim-Prieto, C., and Scollon, C. N. Experience Sampling: Promises and Pitfalls, Strengths and Weaknesses. Journal of Happiness Studies (2003).

[19]

Settles, B. Active learning literature survey. University of Wisconsin, Madison (2010).

Digital Library

[20]

Stikic, M., Larlus, D., Ebert, S., and Schiele, B. Weakly Supervised Recognition of Daily Life Activities with Wearable Sensors. TPAMI (2011).

Digital Library

Cited By

Hiremath SPlötz T(2024)Maintenance Required: Updating and Extending Bootstrapped Human Activity Recognition Systems for Smart Homes2024 International Conference on Activity and Behavior Computing (ABC)10.1109/ABC61795.2024.10651685(1-13)Online publication date: 29-May-2024
https://doi.org/10.1109/ABC61795.2024.10651685
Hiremath SPlötz T(2023)The Lifespan of Human Activity Recognition Systems for Smart HomesSensors10.3390/s2318772923:18(7729)Online publication date: 7-Sep-2023
https://doi.org/10.3390/s23187729
Hiremath SNishimura YChernova SPlötz T(2022)Bootstrapping Human Activity Recognition Systems for Smart Homes from ScratchProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/35502946:3(1-27)Online publication date: 7-Sep-2022
https://dl.acm.org/doi/10.1145/3550294
Show More Cited By

Index Terms

On strategies for budget-based online annotation in human activity recognition
1. Computing methodologies
  1. Modeling and simulation

Recommendations

Handling annotation uncertainty in human activity recognition
ISWC '19: Proceedings of the 2019 ACM International Symposium on Wearable Computers

Developing systems for Human Activity Recognition (HAR) using wearables typically relies on datasets that were manually annotated by human experts with regards to precise timings of instances of relevant activities. However, obtaining such data ...
Exploring human activity annotation using a privacy preserving 3D model
UbiComp '16: Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct

Annotating activity recognition datasets is a very time consuming process. Using lay annotators (e.g. using crowd-sourcing) has been suggested to speed this up. However, this requires to preserve privacy of users and may preclude relying on video for ...
Facilitating Human Activity Data Annotation via Context-Aware Change Detection on Smartwatches

Annotating activities of daily living (ADL) is vital for developing machine learning models for activity recognition. In addition, it is critical for self-reporting purposes such as in assisted living where the users are asked to log their ADLs. However,...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

UbiComp '14 Adjunct: Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication

September 2014

1409 pages

ISBN:9781450330473

DOI:10.1145/2638728

General Chairs:
AJ Brush
Microsoft Research
,
Adrian Friday
Lancaster University, UK
,
Program Chairs:
Julie Kientz
University of Washington
,
James Scott
Microsoft Research, UK
,
Junehwa Song
Korea Advanced Institute of Science and Technology (KAIST), KR

Copyright © 2014 ACM.

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 ACM 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

SIGSPATIAL: ACM Special Interest Group on Spatial Information

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 13 September 2014

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Research Councils UK

Conference

UbiComp '14

Sponsor:

UbiComp '14: The 2014 ACM Conference on Ubiquitous Computing

September 13 - 17, 2014

Washington, Seattle

Acceptance Rates

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

Upcoming Conference

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
178
Total Downloads

Downloads (Last 12 months)4
Downloads (Last 6 weeks)0

Reflects downloads up to 01 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Hiremath SPlötz T(2024)Maintenance Required: Updating and Extending Bootstrapped Human Activity Recognition Systems for Smart Homes2024 International Conference on Activity and Behavior Computing (ABC)10.1109/ABC61795.2024.10651685(1-13)Online publication date: 29-May-2024
https://doi.org/10.1109/ABC61795.2024.10651685
Hiremath SPlötz T(2023)The Lifespan of Human Activity Recognition Systems for Smart HomesSensors10.3390/s2318772923:18(7729)Online publication date: 7-Sep-2023
https://doi.org/10.3390/s23187729
Hiremath SNishimura YChernova SPlötz T(2022)Bootstrapping Human Activity Recognition Systems for Smart Homes from ScratchProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/35502946:3(1-27)Online publication date: 7-Sep-2022
https://dl.acm.org/doi/10.1145/3550294
Reich CMansour AVan Laerhoven K(2019)Collecting Labels for Rare Anomalies via Direct Human Feedback—An Industrial Application StudyInformatics10.3390/informatics60300386:3(38)Online publication date: 2-Sep-2019
https://doi.org/10.3390/informatics6030038
Gjoreski HRoggen DLee STakayama LTruong KHealey JPloetz T(2017)Unsupervised online activity discovery using temporal behaviour assumptionProceedings of the 2017 ACM International Symposium on Wearable Computers10.1145/3123021.3123044(42-49)Online publication date: 11-Sep-2017
https://dl.acm.org/doi/10.1145/3123021.3123044
Miu TMissier PPlotz T(2015)Bootstrapping Personalised Human Activity Recognition Models Using Online Active Learning2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing10.1109/CIT/IUCC/DASC/PICOM.2015.170(1138-1147)Online publication date: Oct-2015
https://doi.org/10.1109/CIT/IUCC/DASC/PICOM.2015.170

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten