Author(s):
- Luke McCully
- Hung Cao
- Monica Wachowicz
- Patricia A.H. Williams
- Stephanie Champion
Abstract:
Purpose
A new research domain known as the Quantified Self has recently emerged and is described as gaining self-knowledge through using wearable technology to acquire information on self-monitoring activities and physical health related problems. However, very little is known about the impact of time window models on discovering self-quantified patterns that can yield new self-knowledge insights. This paper aims to discover the self-quantified patterns using multi-time window models.
Design/methodology/approach
This paper proposes a multi-time window analytical workflow developed to support the streaming k-means clustering algorithm, based on an online/offline approach that combines both sliding and damped time window models. An intervention experiment with 15 participants is used to gather Fitbit data logs and implement the proposed analytical workflow.
Findings
The clustering results reveal the impact of a time window model has on exploring the evolution of micro-clusters and the labelling of macro-clusters to accurately explain regular and irregular individual physical behaviour.
Originality/value
The preliminary results demonstrate the impact they have on finding meaningful patterns.
Documentation:
https://doi.org/10.1108/ACI-12-2021-0331
References:
Jo A, Bryanl DC, Coakes CE, Mainous AG III. Is there a benefit to patients using wearable devices such as fitbit or health apps on mobiles? a systematic review. Am J Med. 2019; 132(12): 1394-400.
Waheed B. Utilization of wearable technology: A synthesis of literature review. EasyChair: Technical report; 2019.
Hu R, Helena van Velthoven M, Meinert E. Perspectives of people who are over- weight and obese on using wearable technology for weight management: systematic review. JMIR mHealth and uHealth. 2020; 8(1): e12651.
Frey A-L, Karran M, Jimenez RC, Baxter J, Adeogun M, Chan D, Crawford J, Paul D, Everson R, Hinds C, et al. Harnessing the potential of digital technologies for the early detection of neurodegenerative diseases; 2019.
Md Zuraini HH, Ismail W, Hendradi R, Justitia A. Students activity recognition by heart rate monitoring in classroom using k-means classification. J Inf Syst Eng Bus Intell. 2020; 6(1): 46-54.
Shah Y, Dunn J, Huebner E, Landry S. Wearables data integration: data- driven modeling to adjust for differences in jawbone and Fitbit estimations of steps, calories, and resting heart-rate. Comput Industry. 2017; 86: 72-81.
Bini SA, Shah RF, Bendich I, Patterson JT, Hwang KM, Zaid MB. Machine learning algorithms can use wearable sensor data to accurately predict six-week patient- reported outcome scores following joint replacement in a prospective trial. J Arthroplasty. 2019; 34(10): 2242-7.
Park S, Lee SW, Han S, Cha M. Clustering insomnia patterns by data from wearable devices: algorithm development and validation study. JMIR mHealth and uHealth. 2019; 7(12): e14473.
Jang J-Y, Hee-Seok O, Lim Y, Cheung YK. Ensemble clustering for step data via binning. Biometrics; 2020.
Mansalis S, Ntoutsi E, Pelekis N, Theodoridis Y. An evaluation of data stream clustering algorithms. Stat Anal Data Mining ASA Data Sci J. 2018; 11(4): 167-87.
Carnein M, Trautmann H. Optimizing data stream representation: an extensive survey on stream clustering algorithms. Bus Inform Syst Eng. 2019; 61(3): 277-97.
Thorp EO. The invention of the first wearable computer. In: Digest of Papers. Second international symposium on wearable computers (Cat. No. 98EX215). IEEE; 1998. p. 4-8.
Shanhong L. Fitbit – statistics & facts, 2019. Available from: https://www.statista.com/topics/2595/fitbit/(accessed 11 August 2020).
Fitbit. How do i track my heart rate with my fitbit device?; 2020. Available from: https://help.fitbit.com/articles/en_US/Help_article/1565.htm (accessed 11 August 2020).
Lynne MF, Geldman J, Sayre EC, Park C, Ezzat AM, Yoo JY, Hamilton CB, Li LC. Accuracy of fitbit devices: systematic review and narrative syntheses of quantitative data. JMIR mHealth and uHealth. 2018; 6(8): e10527.
Eleonore HK, W van Hees H, van Lummel RC, Dekhuijzen R, Remco SD, Spruit MA, Hul AJ. “Can do” versus “do do”: a novel concept to better understand physical functioning in patients with chronic obstructive pulmonary disease. J Clin Med. 2019; 8(3): 340.
Jain AK. Data clustering: 50 years beyond k-means. Pattern Recogn Lett. 2010; 31(8): 651-66.
MacQueen J et al. Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability. Oakland, CA, USA. 1967; 1: 281-97.
Steinhaus H. Sur la division des corp materiels en parties. Bull Acad Polon Sci. 1956; 1(804): 801.
Hahsler M, Bolanos M, Forrest J, et al. Introduction to stream: an extensible frame- work for data stream clustering research with r. J Stat Softw. 2017; 76(14): 1-50.
Keogh E, Lin J. Clustering of time-series subsequences is meaningless: implications for previous and future research. Knowl Inf Syst. 2005; 8(2): 154-77.
Rabl T, Sakr S, Hirzel M. Big stream processing systems (dagstuhl seminar 17441). In: Dagstuhl reports, volume 7. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik; 2018.
Albert B, Holmes G, Pfahringer B, Kranen P, Kremer H, Jansen T, Seidl T. Moa: massive online analysis, a framework for stream classification and clustering. In Proceedings of the First Workshop on Applications of Pattern Analysis: 2010; 44-50.
Zaharia M, Chen A, Davidson A, Ali G, Hong SA, Konwinski A, Murching S, Nykodym T, Paul O, Parkhe M, et al. Accelerating the machine learning lifecycle with MLflow. IEEE Data Eng Bull. 2018; 41(4): 39-45.
Singh RV and Bhatia MPS. Data clustering with modified k-means algorithm. In 2011 In- ternational Conference on Recent Trends in Information Technology (ICRTIT), IEEE: 2011; 717-21.
Cao C, Estert M, Qian W, Zhou A. Density-based clustering over an evolving data stream with noise. In Proceedings of the 2006 SIAM international conference on data mining, SIAM, 2006; 328-39.
Ghesmoune M, Lebbah M, Azzag H. State-of-the-art on clustering data streams. Big Data Analytics. 2016; 1(1): 13.
Hahsler M, Bolanos M, Forrest J. streammoa: interface for moa stream clustering algorithms. R package version; 2015. p. 1-1.
Maechler M, Rousseeuw P, Struyf A, Hubert M, Hornik K. Cluster: Cluster analysis basics and extensions. r package v. 2.0. 5; 2016.
Qiu W, Joe H, Qiu MW. Package ‘clustergeneration’; 2015.
Hennig C. fpc: flexible procedures for clustering. r package version 2; 2015. p. 1-10. Available from: https://cran.R-project.org/package=fpc.