research-article

Open access

Reliable Machine Learning for Wearable Activity Monitoring: Novel Algorithms and Theoretical Guarantees

Authors:

Taha Belkhouja,

Janardhan Rao DoppaAuthors Info & Claims

ICCAD '22: Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design

Article No.: 33, Pages 1 - 9

https://doi.org/10.1145/3508352.3549430

Published: 22 December 2022 Publication History

Abstract

Wearable devices are becoming popular for health and activity monitoring. The machine learning (ML) models for these applications are trained by collecting data in a laboratory with precise control of experimental settings. However, during real-world deployment/usage, the experimental settings (e.g., sensor position or sampling rate) may deviate from those used during training. This discrepancy can degrade the accuracy and effectiveness of the health monitoring applications. Therefore, there is a great need to develop reliable ML approaches that provide high accuracy for real-world deployment. In this paper, we propose a novel statistical optimization approach referred as StatOpt that automatically accounts for the real-world disturbances in sensing data to improve the reliability of ML models for wearable devices. We theoretically derive the upper bounds on sensor data disturbance for StatOpt to produce a ML model with reliability certificates. We validate StatOpt on two publicly available datasets for human activity recognition. Our results show that compared to standard ML algorithms, the reliable ML classifiers enabled by the StatOpt approach improve the accuracy up to 50% in real-world settings with zero overhead, while baseline approaches incur significant overhead and fail to achieve comparable accuracy.

References

[1]

B. Barshan and A. Yurtman. Classifying Daily and Sports Activities Invariantly to the Positioning of Wearable Motion Sensor Units. IEEE Internet of Things J., 7(6):4801--4815, 2020.

[2]

T. Belkhouja and J. R. Doppa. Analyzing Deep Learning for Time-Series Data Through Adversarial Lens in Mobile and IoT Applications. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., 39(11):3190--3201, 2020.

[3]

T. Belkhouja and J. R. Doppa. Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features. J. of Artificial Intelligence Research, 73:1435--1471, 2022.

Digital Library

[4]

T. Belkhouja, Y. Yan, and J. R. Doppa. Dynamic Time Warping based Adversarial Framework for Time-Series Domain. CoRR, abs/2207.04308, 2022.

[5]

T. Belkhouja, Y. Yan, and J. R. Doppa. Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, pages 6055--6063, 2022.

[6]

G. Bhat, N. Tran, H. Shill, and U. Y. Ogras. w-HAR: An Activity Recognition Dataset and Framework using Low-Power Wearable Devices. Sensors, 20(18):5356, 2020.

[7]

N. Carlini and D. Wagner. Towards Evaluating the Robustness of Neural Networks. In 2017 Symp. Sec. and Privacy, pages 39--57, 2017.

[8]

J. Cohen, E. Rosenfeld, and Z. Kolter. Certified Adversarial Robustness via Randomized Smoothing. In Int. Conf. on Machine Learning, pages 1310--1320, 2019.

[9]

P. Dempsey. The Teardown: Apple Watch. Engg. & Tech., 10(6):88--89, 2015.

[10]

T. G. Dietterich. Steps Toward Robust Artificial Intelligence. AI Magazine, 38(3):3--24, 2017.

Digital Library

[11]

M. Gil, F. Alajaji, and T. Linder. Rényi Divergence Measures for Commonly Used Univariate Continuous Distributions. Information Sciences, 249:124--131, 2013.

[12]

D. Hussein, G. Bhat, and J. R. Doppa. Adaptive Energy Management for Self-Sustainable Wearables in Mobile Health. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, pages 11935--11944, 2022.

[13]

D. Hussein, A. Jain, and G. Bhat. Robust Human Activity Recognition Using Generative Adversarial Imputation Networks. In 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), pages 84--87, 2022.

[14]

H. Ismail Fawaz, G. Forestier, J. Weber, L. Idoumghar, and P.-A. Muller. Deep Learning for Time Series Classification: A Review. Data Mining and Knowledge Discovery, 2019.

[15]

G. James, D. Witten, T. Hastie, and R. Tibshirani. An Introduction to Statistical Learning, volume 112. Springer, 2013.

[16]

H. Kim, J. Shin, S. Kim, Y. Ko, K. Lee, H. Cha, S.-i. Hahm, and T. Kwon. Collaborative Classification for Daily Activity Recognition with a Smartwatch. In 2016 IEEE Int. Conf. on Syst., Man, and Cybernetics (SMC), pages 003707--003712, 2016.

[17]

D. P. Kingma and J. Ba. Adam: A Method for Stochastic Optimization. In The Int. Conf. on Learning Representations (Poster), 2015.

[18]

K. Kunze and P. Lukowicz. Sensor Placement Variations in Wearable Activity Recognition. IEEE Perv. Comput., 13(4):32--41, 2014.

[19]

K. Kunze, P. Lukowicz, K. Partridge, and B. Begole. Which Way am I Facing: Inferring Horizontal Device Orientation From an Accelerometer Signal. In 2009 Int. Symp. on Wearable Computers, pages 149--150, 2009.

Digital Library

[20]

J. R. Kwapisz, G. M. Weiss, and S. A. Moore. Activity Recognition Using Cell Phone Accelerometers. ACM SigKDD Explorations Newsletter, 12(2):74--82, 2011.

Digital Library

[21]

O. D. Lara and M. A. Labrador. A Survey on Human Activity Recognition Using Wearable Sensors. IEEE Commun. Surveys & Tut., 15(3):1192--1209, 2012.

[22]

B. Li, C. Chen, W. Wang, and L. Carin. Certified Adversarial Robustness with Additive Noise. In Advances in Neural Information Processing Syst., pages 9459--9469, 2019.

[23]

A. Limaye and T. Adegbija. HERMIT: A Benchmark Suite for the Internet of Medical Things. IEEE Internet Things J., 5(5):4212--4222, 2018.

[24]

W. Maetzler, J. Klucken, and M. Horne. A Clinical View on the Development of Technology-Based Tools in Managing Parkinson's Disease. Movement Disorders, 31(9):1263--1271, 2016.

[25]

D. Mizell. Using Gravity to Estimate Accelerometer Orientation. In Int. Symp. Wearable Comput., pages 252--252, 2003.

[26]

A. Mosenia, S. Sur-Kolay, A. Raghunathan, and N. K. Jha. Wearable Medical Sensor-Based System Design: A Survey. IEEE Trans. Multi-Scale Comput. Syst., 3(2):124--138, 2017.

[27]

A. Ozanne, D.Johansson, U. Hällgren Graneheim, K. Malmgren, F. Bergquist, and M. Alt Murphy. Wearables in Epilepsy and Parkinson's disease - A Focus Group Study. Acta Neurologica Scandinavica, 137(2):188--194, 2018.

[28]

J. Shi, D. Zuo, Z. Zhang, and D. Luo. Sensor-based Activity Recognition Independent of Device Placement and Orientation. Trans. on Emerging Telecommun. Tech., 31(4):e3823, 2020.

Digital Library

[29]

A. Stisen, H. Blunck, S. Bhattacharya, T. S. Prentow, M. B. Kjærgaard, A. Dey, T. Sonne, and M. M. Jensen. Smart Devices are Different: Assessing and Mitigating mobile Sensing Heterogeneities for Activity Recognition. In Proc. ACM Conf. on Embedd. Networked Sensor Syst., pages 127--140, 2015.

Digital Library

[30]

Texas Instruments Inc. CC2652R Microcontroller. [Online] https://www.ti.com/product/CC2652R, accessed August 12, 2022, 2018.

[31]

I. O. Tolstikhin, B. K. Sriperumbudur, and B. Schölkopf. Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels. In Advances in Neural Information Processing Syst., volume 29, 2016.

[32]

L. Van der Maaten and G. Hinton. Visualizing Data Using t-SNE. J. of Machine Learning Research, 9(11), 2008.

[33]

A. Wang, G. Chen, J. Yang, S. Zhao, and C.-Y. Chang. A Comparative Study on Human Activity Recognition Using Inertial Sensors in a Smartphone. IEEE Sensors J., 16(11):4566--4578, 2016.

[34]

N. Yamin, G. Bhat, and J. R. Doppa. DIET: A Dynamic Energy Management Approach for Wearable Health Monitoring Devices. In 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), pages 1--6, 2022.

[35]

P. Zappi, T. Stiefmeier, E. Farella, D. Roggen, L. Benini, and G. Troster. Activity Recognition from On-Body Sensors by Classifier Fusion: Sensor Scalability and Robustness. In Proc. Int. Conf. on Intell. Sensors, Sensor Netw. and Info., pages 281--286, 2007.

Cited By

Elshazli MHussein DBhat GAbdel-Rahim AIbrahim A(2024)Advancing infrastructure resilience: machine learning-based prediction of bridges’ rating factors under autonomous truck platoonsJournal of Infrastructure Preservation and Resilience10.1186/s43065-024-00096-x5:1Online publication date: 7-Apr-2024
https://doi.org/10.1186/s43065-024-00096-x
Hussein DBhat G(2024)SensorGAN: A Novel Data Recovery Approach for Wearable Human Activity RecognitionACM Transactions on Embedded Computing Systems10.1145/360942523:3(1-28)Online publication date: 11-May-2024
https://dl.acm.org/doi/10.1145/3609425
Belkhouja TDoppa JElkind E(2023)Adversarial framework with certified robustness for time-series domain via statistical features (extended abstract)Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence10.24963/ijcai.2023/767(6845-6850)Online publication date: 19-Aug-2023
https://dl.acm.org/doi/10.24963/ijcai.2023/767
Show More Cited By

Index Terms

Reliable Machine Learning for Wearable Activity Monitoring: Novel Algorithms and Theoretical Guarantees

Index terms have been assigned to the content through auto-classification.

Recommendations

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 ...
Lifelong Machine Learning
A survey on unsupervised learning for wearable sensor-based activity recognition
Abstract
Human Activity Recognition (HAR) is an essential task in various applications such as pervasive healthcare, smart environment, and security and surveillance. The need to develop accurate HAR systems has motivated researchers to propose various ...
Highlights
- Adoption of unsupervised learning in wearable sensor-datasets.
- Survey to investigate the evolution of human activity recognition.
- Existing wearable sensor-based datasets and state-of-the-art clustering approach.
- Existing data ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

ICCAD '22: Proceedings of the 41st IEEE/ACM International Conference on Computer-Aided Design

October 2022

1467 pages

ISBN:9781450392174

DOI:10.1145/3508352

Conference Chair:
Tulika Mitra
National University of Singapore
,
Program Chairs:
Evangeline Young
The Chinese University of Hong Kong
,
Jinjun Xiong
University at Buffalo (UB)

Copyright © 2022 Owner/Author.

This work is licensed under a Creative Commons Attribution International 4.0 License.

Sponsors

SIGDA: ACM Special Interest Group on Design Automation

In-Cooperation

IEEE-EDS: Electronic Devices Society
IEEE CAS
IEEE CEDA

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 22 December 2022

Check for updates

Qualifiers

Research-article

Conference

ICCAD '22

Sponsor:

SIGDA

ICCAD '22: IEEE/ACM International Conference on Computer-Aided Design

October 30 - November 3, 2022

California, San Diego

Acceptance Rates

Overall Acceptance Rate 457 of 1,762 submissions, 26%

Upcoming Conference

ICCAD '24

Sponsor:
sigda

IEEE/ACM International Conference on Computer-Aided Design

October 27 - 31, 2024

New York , NY , USA

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
304
Total Downloads

Downloads (Last 12 months)171
Downloads (Last 6 weeks)17

Reflects downloads up to 02 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Elshazli MHussein DBhat GAbdel-Rahim AIbrahim A(2024)Advancing infrastructure resilience: machine learning-based prediction of bridges’ rating factors under autonomous truck platoonsJournal of Infrastructure Preservation and Resilience10.1186/s43065-024-00096-x5:1Online publication date: 7-Apr-2024
https://doi.org/10.1186/s43065-024-00096-x
Hussein DBhat G(2024)SensorGAN: A Novel Data Recovery Approach for Wearable Human Activity RecognitionACM Transactions on Embedded Computing Systems10.1145/360942523:3(1-28)Online publication date: 11-May-2024
https://dl.acm.org/doi/10.1145/3609425
Belkhouja TDoppa JElkind E(2023)Adversarial framework with certified robustness for time-series domain via statistical features (extended abstract)Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence10.24963/ijcai.2023/767(6845-6850)Online publication date: 19-Aug-2023
https://dl.acm.org/doi/10.24963/ijcai.2023/767
Belkhouja TYan YDoppa J(2023)Out-of-distribution Detection in Time-series Domain: A Novel Seasonal Ratio Scoring ApproachACM Transactions on Intelligent Systems and Technology10.1145/363063315:1(1-24)Online publication date: 19-Dec-2023
https://dl.acm.org/doi/10.1145/3630633
Belkhouja TYan YDoppa J(2023)Dynamic Time Warping Based Adversarial Framework for Time-Series DomainIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2022.322475445:6(7353-7366)Online publication date: 1-Jun-2023
https://dl.acm.org/doi/10.1109/TPAMI.2022.3224754
Hussein DBelkhouja TBhat GDoppa J(2023)Energy-Efficient Missing Data Recovery in Wearable Devices: A Novel Search-Based Approach2023 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)10.1109/ISLPED58423.2023.10244309(1-6)Online publication date: 7-Aug-2023
https://doi.org/10.1109/ISLPED58423.2023.10244309

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

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

Media

Figures

Other

Tables

View Table of Contents