research-article

An integrated framework for human activity classification

Authors:

Minh Nhut Nguyen,

Shonali Krishnaswamy,

Xiao-Li LiAuthors Info & Claims

UbiComp '12: Proceedings of the 2012 ACM Conference on Ubiquitous Computing

Pages 331 - 340

https://doi.org/10.1145/2370216.2370268

Published: 05 September 2012 Publication History

Abstract

This paper presents an integrated framework to enable using standard non-sequential machine learning tools for accurate multi-modal activity recognition. We develop a novel framework that contains simple pre- and post-classification strategies to improve the overall performance. We achieve this through class-imbalance correction on the learning data using structure preserving oversampling (SPO), leveraging the sequential nature of sensory data using smoothing of the predicted label sequence and classifier fusion, respectively. Through evaluation on recent publicly available activity datasets comprising of a large amount of multi-dimensional sensory data, we demonstrate that our proposed strategies are effective in improving classification performance over common techniques such as One Nearest Neighbor (1NN) and Support Vector Machines (SVM). Our framework also shows better performance over sequential probabilistic models, such as Conditional Random Field (CRF) and Hidden Markov Model (HMM) and when these models are used as meta-learners.

References

[1]

Bao, L., Intille, S. S.: Activity Recognition from User-Annotated Acceleration Data. In: Pervasive Computing, LNCS 3001, 1--17, (2004)

[2]

Krishnan, N. C., Colbry, et al.: Real Time Human Activity Recognition using Tri-Axial Accelerometers. In: Sensors Signals and Info. Processing Workshop, (2008)

[3]

Long, X., Yin, B., Aarts, R. M.: Single-Accelerometer-based Daily Physical Activity Classification. In: IEEE Eng. Med. Biol. Soc., 1, 6107--10, (2009)

[4]

Lee, S. W., Mase, K.: Activity and Location Recognition Using Wearable Sensors. In: IEEE Pervasive Computing, 1(3), 24--32, (2002)

Digital Library

[5]

Lester, J., Choudhury, T., et al.: A Hybrid Discriminative/Generative Approach for Modeling Human Activities. In: IJCAI'05, 766--772, (2005)

Digital Library

[6]

Maurer, U., Smailagic, A., et al.: Activity Recognition and Monitoring using Multiple Sensors on Different Body Positions. In: BSN '06, 113--116, (2006)

Digital Library

[7]

Helmi, M., Almodarresi, S. M. T.: Human Activity Recognition using a Fuzzy Inference System. In: IEEE Int. Conf. on Fuzzy Systems, 1897--1902, (2009)

[8]

Huynh, T., Fritz, M., Schiele, B.: Discovery of Activity Patterns using Topic Models. In: UbiComp '08, 10--19, (2008)

Digital Library

[9]

Li, F., Dustdar, S.: Incorporating Unsupervised Learning in Activity Recognition. In: AAAI Workshops at the 25^th AAAI Conference on Artificial Intelligence, (2011)

[10]

Longstaff, B., Reddy, S., Estrin, D.: Improving Activity Classification for Health Applications on Mobile Devices using Active and Semi-Supervised Learning. In: PervasiveHealth'10, 1--7, (2010)

[11]

Nguyen, M. N., Li X.-L., Ng, S.-K.: Positive Unlabeled Learning for Time Series Classification. In: IJCAI'11, 1421--1426, (2011).

Digital Library

[12]

Preece, S. J., Goulermas, J. Y., et al.: Activity Identification using Body-Mounted Sensors: a Review of Classification Techniques, Physiological Measurement, 30(4), R1--R33, (2009)

[13]

Van Kasteren, T., Noulas, A., Englebienne, G., Krose, B.: Accurate Activity Recognition in a Home Setting. In: UbiComp'08, 1--9, (2008)

Digital Library

[14]

Sagha, H., Digumarti, S. T., et al.: Benchmarking Classification Techniques using the Opportunity Human Activity Dataset. In: IEEE Int. Conf. on Systems, Man, and Cybernetics (2011)

[15]

Roggen, D., Calatroni, A., et al.: Collecting Complex Activity Datasets in Highly Rich Networked Sensor Environments. In: Seventh Int. INSS'10, 233--240, (2010)

[16]

Farin, G.: Curves and Surfaces for Computer Aided Geometric Design: A Practical Guild. 4^th ed, Academic, New York, (1996)

Digital Library

[17]

Sagha, H., Millan, J. R., et al. A Probabilistic Approach to Handel Missing Data for Multi-Sensory Activity Recognition. In: Workshop on Context Awareness and Information Processing in Opportunistic Ubiquitous Systems at Ubicomp'10, (2010)

[18]

Albinali, F., Davies, N. and Friday, A. Structural Learning of Activities from Sparse Datasets. In: PerCom'07, 221--228, (2007)

Digital Library

[19]

Junker, H., Amft, O., et al.: Gesture Spotting with Body-Worn Inertial Sensors to Detect User Activities. vol. 41(6), 2010--2024, (2008)

Digital Library

[20]

Stager, M, Lukowicz, P. and Troster, G. Dealing with Class Skew in Context Recognition, Proc. ICDCSW'06, pp. 58--63, (2006)

Digital Library

[21]

Chiewchanwattana S. and Lursinsap, C.: FI-GEM Networks for Incomplete Time-Series Prediction. Proc. IJCNN'02, pp. 1757--1762, (2002)

[22]

Oliver, N., Horvitz, E. and Garg A.: Layered Representations for Human Activity Recognition. Proc. Int. Conf. on Multimedia Interfaces, (2002)

Digital Library

[23]

Cao, H., Li, X.-L., et al.: SPO: Structure Preserving Oversampling for Imbalanced Time Series Classification. In: Proc. IEEE Int. Conf. on Data Mining, (2011)

Digital Library

[24]

Chawla, N. V., Bowyer, K. W., et al.: SMOTE: Synthetic Minority Over-Sampling Technique. J. Artificial Intelligence, 16, 321--357, (2002)

Digital Library

[25]

Jiang, X., Mandal, B., Kot, A. C.: Eigenfeature Regularization and Extraction in Face Recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence, 30(3), 383--394, (2008)

Digital Library

[26]

Tomek, I.: Two Modifications of CNN. IEEE Trans. System, Man, Cybernetics, 6(11), 769--772, (1976)

[27]

Hsu, C.-W., Chang C.-C., Lin, C.-J.: A Practical Guide to Support Vector Classification, (2008)

[28]

Keogh E., Kasetty, S.: On the Need for Time Series Data Mining Benchmarks: A Survey and Empirical Demonstration. Data Mining and Knowledge Discovery, 7(4), 349--371, (2003)

Digital Library

[29]

Lafferty, J., McCallum, A., Pereira, F.: Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In: ICML'01, 282--289, (2001)

Digital Library

[30]

Rabiner, L.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proc. of IEEE. 77 (2), 257--286, (1989)

[31]

McCallum, A.: MALLET: A Machine Learning for Language Toolkit. (2002), https://mallet.cs.umass.edu

[32]

List of Activity Classification Datasets. Available at: https://ailab.wsu.edu/casas/datasets/index.html

Cited By

Cherian JRay STaele PKoh JHammond T(2024)Exploring the Impact of the NULL Class on In-the-Wild Human Activity RecognitionSensors10.3390/s2412389824:12(3898)Online publication date: 16-Jun-2024
https://doi.org/10.3390/s24123898
Ghorrati ZEsmaeili AEric Matson T(2024)A Multi-Section Hierarchical Deep Neural Network Model for Time Series Classification: Applied to Wearable Sensor-Based Human Activity RecognitionIEEE Access10.1109/ACCESS.2024.346251512(137851-137869)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3462515
Chen SSun X(2024)Validating CircaCP: a generic sleep–wake cycle detection algorithm for unlabelled actigraphy dataRoyal Society Open Science10.1098/rsos.23146811:5Online publication date: 29-May-2024
https://doi.org/10.1098/rsos.231468
Show More Cited By

Index Terms

An integrated framework for human activity classification
1. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
        Supervised learning by classification
    2. Machine learning approaches
      1. Classification and regression trees
2. Software and its engineering
  1. Software notations and tools
    1. General programming languages
      1. Language features
        Frameworks

Recommendations

An integrated framework for human activity recognition
UbiComp '12: Proceedings of the 2012 ACM Conference on Ubiquitous Computing

This poster presents an integrated framework to enable using standard non-sequential machine learning tools for accurate multi-modal activity recognition. Our framework contains simple pre- and post-classification strategies such as class-imbalance ...
Wearable Sensing Framework for Human Activity Monitoring
WearSys '15: Proceedings of the 2015 workshop on Wearable Systems and Applications

Wearable computation is getting integrated into our daily life day by day. In this work, we propose a generic framework to continuously monitor users' daily activities. The framework proposes light computation tasks on the wearable device to reduce the ...
WagTag: a dog collar accessory for monitoring canine activity levels
UbiComp '13 Adjunct: Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publication

Technological advancements are leading to the emergence of wearable computing devices as a major consumer category. Several companies have developed, or are developing, wearable accessories to monitor human activity. But the health and wellness ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

UbiComp '12: Proceedings of the 2012 ACM Conference on Ubiquitous Computing

September 2012

1268 pages

ISBN:9781450312240

DOI:10.1145/2370216

General Chair:
Anind K. Dey
Carnegie Mellon University
,
Program Chairs:
Hao-Hua Chu
National Taiwan University, Taiwan
,
Gillian Hayes
University of California, Irvine

Copyright © 2012 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: 05 September 2012

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

Ubicomp '12

Sponsor:

Ubicomp '12: The 2012 ACM Conference on Ubiquitous Computing

September 5 - 8, 2012

Pennsylvania, Pittsburgh

Acceptance Rates

UbiComp '12 Paper Acceptance Rate 58 of 301 submissions, 19%;

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

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

36
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 01 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Cherian JRay STaele PKoh JHammond T(2024)Exploring the Impact of the NULL Class on In-the-Wild Human Activity RecognitionSensors10.3390/s2412389824:12(3898)Online publication date: 16-Jun-2024
https://doi.org/10.3390/s24123898
Ghorrati ZEsmaeili AEric Matson T(2024)A Multi-Section Hierarchical Deep Neural Network Model for Time Series Classification: Applied to Wearable Sensor-Based Human Activity RecognitionIEEE Access10.1109/ACCESS.2024.346251512(137851-137869)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3462515
Chen SSun X(2024)Validating CircaCP: a generic sleep–wake cycle detection algorithm for unlabelled actigraphy dataRoyal Society Open Science10.1098/rsos.23146811:5Online publication date: 29-May-2024
https://doi.org/10.1098/rsos.231468
Lee SHofmann AWilliams B(2022)A Model-Based Human Activity Recognition for Human–Robot Collaboration2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)10.1109/IROS40897.2019.8967650(736-743)Online publication date: 28-Dec-2022
https://dl.acm.org/doi/10.1109/IROS40897.2019.8967650
Zhu HSamtani SBrown RChen H(2021)A Deep Learning Approach for Recognizing Activity of Daily Living (ADL) for Senior Care: Exploiting Interaction Dependency and Temporal PatternsMIS Quarterly10.25300/MISQ/2021/1557445:2(859-896)Online publication date: 1-Jun-2021
https://doi.org/10.25300/MISQ/2021/15574
Khan NGhani M(2021)A Survey of Deep Learning Based Models for Human Activity RecognitionWireless Personal Communications: An International Journal10.1007/s11277-021-08525-w120:2(1593-1635)Online publication date: 1-Sep-2021
https://dl.acm.org/doi/10.1007/s11277-021-08525-w
Dang XCao YHao ZLiu Y(2020)WiGId: Indoor Group Identification with CSI-Based Random ForestSensors10.3390/s2016460720:16(4607)Online publication date: 17-Aug-2020
https://doi.org/10.3390/s20164607
Caviedes JLi BJammula V(2020)Wearable Sensor Array Design for Spine Posture Monitoring During Exercise Incorporating BiofeedbackIEEE Transactions on Biomedical Engineering10.1109/TBME.2020.297190767:10(2828-2838)Online publication date: Oct-2020
https://doi.org/10.1109/TBME.2020.2971907
Li QYang YYang P(2020)Human activity recognition based on triaxial accelerometer using multi-feature weighted ensemble2020 IEEE 18th International Conference on Industrial Informatics (INDIN)10.1109/INDIN45582.2020.9442172(561-566)Online publication date: 20-Jul-2020
https://doi.org/10.1109/INDIN45582.2020.9442172
Hu YZhang XXu LXian He FTian ZShe WLiu W(2020)Harmonic Loss Function for Sensor-Based Human Activity Recognition Based on LSTM Recurrent Neural NetworksIEEE Access10.1109/ACCESS.2020.30031628(135617-135627)Online publication date: 2020
https://doi.org/10.1109/ACCESS.2020.3003162
Show More Cited By

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

Media

Figures

Other

Tables

View Table of Contents