Decomposing Activities of Daily Living to Discover Routine Clusters

The modern sensor technology helps us collect time series data for activities of daily living (ADLs), which in turn can be used to infer broad patterns, such as common daily routines. Most of the existing approaches either rely on a model trained by a preselected and manually labeled set of activities, or perform micro-pattern analysis with manually selected length and number of micro-patterns. Since real life ADL datasets are massive, such approaches would be too costly to apply. Thus, there is a need to formulate unsupervised methods that can be applied to different time scales. We propose a novel approach to discover clusters of daily activity routines. We use a matrix decomposition method to isolate routines and deviations to obtain two different sets of clusters.We obtain the final memberships via the cross product of these sets. We validate our approach using two real-life ADL datasets and a well-known artificial dataset. Based on average silhouette width scores, our approach can capture strong structures in the underlying data. Furthermore, results show that our approach improves on the accuracy of the baseline algorithms by 12% with a statistical significance (p <0.05) using the Wilcoxon signed-rank comparison test.

[1]  L. Smarr Quantifying your body: a how-to guide from a systems biology perspective. , 2012, Biotechnology journal.

[2]  Dacheng Tao,et al.  GoDec: Randomized Lowrank & Sparse Matrix Decomposition in Noisy Case , 2011, ICML.

[3]  Majid Sarrafzadeh,et al.  Toward Unsupervised Activity Discovery Using Multi-Dimensional Motif Detection in Time Series , 2009, IJCAI.

[4]  O. Okonkwo,et al.  Mild cognitive impairment and everyday function: evidence of reduced speed in performing instrumental activities of daily living. , 2008, The American journal of geriatric psychiatry : official journal of the American Association for Geriatric Psychiatry.

[5]  Tak-Chung Fu,et al.  A review on time series data mining , 2011, Eng. Appl. Artif. Intell..

[6]  John Wright,et al.  Decomposing background topics from keywords by principal component pursuit , 2010, CIKM.

[7]  G. K. Sandve,et al.  A survey of motif discovery methods in an integrated framework , 2006, Biology Direct.

[8]  John Wright,et al.  RASL: Robust Alignment by Sparse and Low-Rank Decomposition for Linearly Correlated Images , 2012, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Pearl Pu,et al.  HealthyTogether: exploring social incentives for mobile fitness applications , 2014, Chinese CHI '14.

[10]  Patrick Olivier,et al.  A Dynamic Time Warping Approach to Real-Time Activity Recognition for Food Preparation , 2010, AmI.

[11]  Frank Bentley,et al.  Mobile Health Mashups: Making sense of multiple streams of wellbeing and contextual data for presentation on a mobile device , 2012, 2012 6th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops.

[12]  E. Prescott,et al.  Postwar U.S. Business Cycles: An Empirical Investigation , 1997 .

[13]  G. Sapiro,et al.  A collaborative framework for 3D alignment and classification of heterogeneous subvolumes in cryo-electron tomography. , 2013, Journal of structural biology.

[14]  Yi Ma,et al.  Robust principal component analysis? , 2009, JACM.

[15]  Lawrence B. Holder,et al.  Discovering Activities to Recognize and Track in a Smart Environment , 2011, IEEE Transactions on Knowledge and Data Engineering.

[16]  Alex Pentland,et al.  Social sensing for epidemiological behavior change , 2010, UbiComp.

[17]  Mong-Li Lee,et al.  Integrating Frequent Pattern Mining from Multiple Data Domains for Classification , 2012, 2012 IEEE 28th International Conference on Data Engineering.

[18]  Yi Ma,et al.  The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices , 2010, Journal of structural biology.

[19]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[20]  R. Manmatha,et al.  Word image matching using dynamic time warping , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[21]  Volkan Cevher,et al.  MATRIX ALPS: Accelerated low rank and sparse matrix reconstruction , 2012, 2012 IEEE Statistical Signal Processing Workshop (SSP).

[22]  Ali S. Hadi,et al.  Finding Groups in Data: An Introduction to Chster Analysis , 1991 .

[23]  Eamonn J. Keogh,et al.  Scaling up Dynamic Time Warping to Massive Dataset , 1999, PKDD.

[24]  B. Lo,et al.  Pattern mining for routine behaviour discovery in pervasive healthcare environments , 2008, 2008 International Conference on Information Technology and Applications in Biomedicine.

[25]  Yi Ma,et al.  Repairing Sparse Low-Rank Texture , 2012, ECCV.

[26]  Weng-Keen Wong,et al.  Physical Activity Recognition from Accelerometer Data Using a Multi-Scale Ensemble Method , 2013, IAAI.

[27]  S. Chiba,et al.  Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[28]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[29]  Lionel M. Ni,et al.  An unsupervised framework for sensing individual and cluster behavior patterns from human mobile data , 2012, UbiComp.

[30]  Diane J. Cook,et al.  Learning Setting-Generalized Activity Models for Smart Spaces , 2012, IEEE Intelligent Systems.

[31]  Eamonn J. Keogh,et al.  Clustering of time-series subsequences is meaningless: implications for previous and future research , 2004, Knowledge and Information Systems.

[32]  Eamonn J. Keogh,et al.  On the Need for Time Series Data Mining Benchmarks: A Survey and Empirical Demonstration , 2002, Data Mining and Knowledge Discovery.