Inferring Activity Patterns from Sparse Step Counts Data with Recurrent Neural Networks
Authors: 
Keqin Shi, Zhen Chen, Xuejing Li, Zhifei Xiao, Weiqiang Sun, Weisheng HuAuthors Info & Claims
Keqin Shi, Zhen Chen, Xuejing Li, Zhifei Xiao, Weiqiang Sun, Weisheng HuAuthors Info & ClaimsArticle No.: 4, Pages 1 - 20
Abstract
As an accurate measurement of physical activity, step counts data can be collected expediently by smartphones and wearable devices. Complete and high time-resolution step counts data record the time and intensity of individuals’ physical activity in a day, and can be used to mine activity habits or to recommend customized workout plans. However, sparse step counts data are common in practice due to hardware and software limitations. Understanding the value of sparse step counts data can contribute to its application in healthcare, and also can help us design cost-effective hardware and software. In this article, we aim to infer activity patterns from sparse step counts data. We design a deep learning model based on recurrent neural networks, namely MLP-GRU, which considers bidirectional short-term dependency and long-term regularity of sparse step counts data, and implements data-driven imputation and classification. We also develop an interpretable and elastic method to obtain sparse step counts data labeled with multi-granular activity patterns to train MLP-GRU. Evaluations on real-world datasets reveal that MLP-GRU outperforms other strong baseline methods. The results also show that activity patterns can be inferred from extremely sparse step counts data with high accuracy, provided that proper granularity is used for data of different sparsity.
References
[1]
Luai Al Shalabi, Zyad Shaaban, and Basel Kasasbeh. 2006. Data mining: A preprocessing engine. Journal of Computer Science 2, 9 (2006), 735–739.
[2]
Bruce Wayne Bailey, Pamela Borup, Larry Tucker, James LeCheminant, Matthew Allen, and Whitney Hebbert. 2014. Steps measured by pedometry and the relationship to adiposity in college women. Journal of Physical Activity and Health 11, 6 (2014), 1225–1232.
[3]
Gustavo E. Batista and Maria Carolina Monard. 2002. A study of K-nearest neighbour as an imputation method. HIS 87, 251–260 (2002), 48.
[4]
Yoshua Bengio and Francois Gingras. 1996. Recurrent neural networks for missing or asynchronous data. In Advances in Neural Information Processing Systems. Morgan Kaufmann, Denver, CO, 395–401.
[5]
Dena M. Bravata, Crystal Smith-Spangler, Vandana Sundaram, Allison L. Gienger, Nancy Lin, Robyn Lewis, Christopher D. Stave, Ingram Olkin, and John R. Sirard. 2007. Using pedometers to increase physical activity and improve Health: A systematic review. JAMA 298, 19 (112007), 2296–2304.
[6]
Wei Cao, Dong Wang, Jian Li, Hao Zhou, Lei Li, and Yitan Li. 2018. Brits: Bidirectional recurrent imputation for time series. arXiv preprint arXiv:1805.10572.
[7]
Zhengping Che, Sanjay Purushotham, Kyunghyun Cho, David Sontag, and Yan Liu. 2018. Recurrent neural networks for multivariate time series with missing values. Scientific Reports 8, 1 (2018), 1–12.
[8]
Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078.
[9]
Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555.
[10]
Brian Patrick Clarkson. 2002. Life Patterns: Structure from Wearable Sensors. Ph.D. Dissertation. Massachusetts Institute of Technology, Cambridge, MA. https://dspace.mit.edu/handle/1721.1/8030.
[11]
Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, and Serge Belongie. 2019. Class-balanced loss based on effective number of samples. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’19).
[12]
Françoise Fessant and Sophie Midenet. 2002. Self-organising map for data imputation and correction in surveys. Neural Computing & Applications 10, 4 (2002), 300–310.
[13]
Pedro J. García-Laencina, José-Luis Sancho-Gómez, and Aníbal R. Figueiras-Vidal. 2010. Pattern classification with missing data: A review. Neural Computing & Applications 19, 2 (2010), 263–282.
[14]
Amit Gupta and Monica S. Lam. 1996. Estimating missing values using neural networks. Journal of the Operational Research Society 47, 2 (1996), 229–238.
[15]
KeqinShi HaoqiFu and Weiqiang Sun. 2019. Robust classification of step data of exercise.
[16]
Charles R. Harris, K. Jarrod Millman, Stéfan J. van der Walt, Ralf Gommers, Pauli Virtanen, David Cournapeau, Eric Wieser, et al. 2020. Array programming with NumPy. Nature 585 (2020), 357–362.
[17]
Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation 9, 8 (1997), 1735–1780.
[18]
Kurt Hornik, Maxwell Stinchcombe, and Halbert White. 1989. Multilayer feedforward networks are universal approximators. Neural Networks 2, 5 (1989), 359–366.
[19]
Tâm Huynh, Mario Fritz, and Bernt Schiele. 2008. Discovery of activity patterns using topic models. In Proceedings of the 10th International Conference on Ubiquitous Computing. 10–19.
[20]
Chuanyi Ji and Anwar Elwalid. 2000. Measurement-based network monitoring: Missing data formulation and scalability analysis. In Proceedings of the 2000 IEEE International Symposium on Information Theory. IEEE, Los Alamitos, CA, 78.
[21]
Yeo-Jin Kim and Min Chi. 2018. Temporal belief memory: Imputing missing data during RNN training. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI’18).
[22]
Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
[23]
Paul Kofman and Ian G. Sharpe. 2003. Using multiple imputation in the analysis of incomplete observations in finance. Journal of Financial Econometrics 1, 2 (2003), 216–249.
[24]
Kamakshi Lakshminarayan, Steven A. Harp, and Tariq Samad. 1999. Imputation of missing data in industrial databases. Applied Intelligence 11, 3 (1999), 259–275.
[25]
Zhiguo Li, Subhro Das, James Codella, Tian Hao, Kun Lin, Chandramouli Maduri, and Ching-Hua Chen. 2018. An adaptive, data-driven personalized advisor for increasing physical activity. IEEE Journal of Biomedical and Health Informatics 23, 3 (2018), 999–1010.
[26]
Zachary C. Lipton, David Kale, and Randall Wetzel. 2016. Directly modeling missing data in sequences with RNNs: Improved classification of clinical time series. In Proceedings of the Conference on Machine Learning for Healthcare. 253–270.
[27]
Peng Liu, Elia El-Darzi, Lei Lei, Christos Vasilakis, Panagiotis Chountas, and Wei Huang. 2005. An analysis of missing data treatment methods and their application to health care dataset. In Proceedings of the International Conference on Advanced Data Mining and Applications. 583–590.
[28]
Yonghong Luo, Xiangrui Cai, Ying Zhang, Jun Xu, and Xiaojie Yuan. 2018. Multivariate time series imputation with generative adversarial networks. In Proceedings of the 32nd International Conference on Neural Information Processing Systems. 1603–1614.
[29]
Yonghong Luo, Ying Zhang, Xiangrui Cai, and Xiaojie Yuan. 2019. E2GAN: End-to-end generative adversarial network for multivariate time series imputation. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI’19). 3094–3100.
[30]
Elijah S. Meyer, Tan Tran, and Mark C. Greenwood. 2016. Statistical methods for detecting groups of patterns in daily step count activity profiles. Skyline: The Big Sky Undergraduate Journal 4, 1 (2016), 1–21. https://scholarworks.montana.edu/xmlui/handle/1/14924.
[31]
Susan Michie, Maartje M. van Stralen, and Robert West. 2011. The behaviour change wheel: A new method for characterising and designing behaviour change interventions. Implementation Science 6, 1 (2011), 42.
[32]
François Modave, Yi Guo, Jiang Bian, Matthew J. Gurka, Alice Parish, Megan D. Smith, Alexandra M. Lee, and Thomas W. Buford. 2017. Mobile device accuracy for step counting across age groups. JMIR Mhealth Uhealth 5, 6 (June 2017), e88.
[33]
Carla Moreira, Rute Santos, José Cazuza de Farias Júnior, Susana Vale, Paula C. Santos, Luísa Soares-Miranda, Ana I. Marques, and Jorge Mota. 2011. Metabolic risk factors, physical activity and physical fitness in Azorean adolescents: A cross-sectional study. BMC Public Health 11, 1 (2011), 1–7.
[34]
Hyuntae Park, Sungjin Park, Roy J. Shephard, and Yukitoshi Aoyagi. 2010. Yearlong physical activity and sarcopenia in older adults: The Nakanojo study. European Journal of Applied Physiology 109, 5 (2010), 953–961.
[35]
Kenneth E. Powell, Linda M. Martin, and Pranesh P. Chowdhury. 2003. Places to walk: Convenience and regular physical activity. American Journal of Public Health 93, 9 (2003), 1519–1521.
[36]
Joseph L. Schafer. 1997. Analysis of Incomplete Multivariate Data. CRC Press, Boca Raton, FL.
[37]
David W. Scott. 2015. Multivariate Density Estimation: Theory, Practice, and Visualization. John Wiley & Sons.
[38]
S. S. M. Silva, Madawa W. Jayawardana, and Denny Meyer. 2018. Statistical methods to model and evaluate physical activity programs, using step counts: A systematic review. PLoS One 13, 11 (2018), e0206763.
[39]
Upkar Varshney. 2007. Pervasive healthcare and wireless health monitoring. Mobile Networks and Applications 12, 2 (2007), 113–127.
[40]
Onur Yürüten, Jiyong Zhang, and Pearl Pu. 2014. Decomposing activities of daily living to discover routine clusters. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 28.
[41]
Jiangchuan Zheng and Lionel M. Ni. 2012. An unsupervised framework for sensing individual and cluster behavior patterns from human mobile data. In Proceedings of the 2012 ACM Conference on Ubiquitous Computing. 153–162.
Index Terms
- Inferring Activity Patterns from Sparse Step Counts Data with Recurrent Neural Networks
Recommendations
Online gradient method with smoothing ź0 regularization for feedforward neural networks
źp regularization has been a popular pruning method for neural networks. The parameter p was usually set as 0 < p ź 2 in the literature, and practical training algorithms with ź0 regularization are lacking due to the NP-hard nature of the ź0 ...
A recurrent neural network architecture to model physical activity energy expenditure in older people
AbstractThrough the quantification of physical activity energy expenditure (PAEE), health care monitoring has the potential to stimulate vital and healthy ageing, inducing behavioural changes in older people and linking these to personal health gains. To ...
Multiresolution-based bilinear recurrent neural network
PAKDD'07: Proceedings of the 11th Pacific-Asia conference on Advances in knowledge discovery and data miningA Multiresolution-based BiLinear Recurrent Neural Network (MBLRNN) is proposed in this paper. The proposed M-BLRNN is based on the BLRNN that has been proven to have robust abilities in modeling and predicting time series. The learning process is ...
Comments
Information & Contributors
Information
Published In
January 2023
217 pages
EISSN:2637-8051
DOI:10.1145/3582897
- Editors:
- Insup Lee,
- John A. Stankovic,
- Gang Zhou
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].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 27 February 2023
Online AM: 30 August 2022
Accepted: 24 August 2022
Received: 01 March 2022
Published in HEALTH Volume 4, Issue 1
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Key Research and Development Project of China
- National Social Science Foundation of China
- NSFC
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 305Total Downloads
- Downloads (Last 12 months)109
- Downloads (Last 6 weeks)10
Reflects downloads up to 10 Aug 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderFull Text
View this article in Full Text.
Full TextHTML Format
View this article in HTML Format.
HTML Format