Learning Latent Activities from Social Signals with Hierarchical Dirichlet Processes

Understanding human activities is an important research topic, most noticeably in assisted-living and healthcare monitoring environments. Beyond simple forms of activity (e.g., an RFID event of entering a building), learning latent activities that are more semantically interpretable, such as sitting at a desk, meeting with people, or gathering with friends, remains a challenging problem. Supervised learning has been the typical modeling choice in the past. However, this requires labeled training data, is unable to predict never-seen-before activity, and fails to adapt to the continuing growth of data over time. In this chapter, we explore the use of a Bayesian nonparametric method, in particular the hierarchical Dirichlet process, to infer latent activities from sensor data acquired in a pervasive setting. Our framework is unsupervised, requires no labeled data, and is able to discover new activities as data grows. We present experiments on extracting movement and interaction activities from sociometric badge signals and show how to use them for detecting of subcommunities. Using the popular Reality Mining dataset, we further demonstrate the extraction of colocation activities and use them to automatically infer the structure of social subgroups.

[1]  Alex Pentland,et al.  Modeling the co-evolution of behaviors and social relationships using mobile phone data , 2011, MUM.

[2]  Gregory D. Abowd,et al.  Charting past, present, and future research in ubiquitous computing , 2000, TCHI.

[3]  Vassilis P. Plagianakos,et al.  Statistical data mining of streaming motion data for fall detection in assistive environments , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  Rama Chellappa,et al.  Activity Modeling and Recognition Using Shape Theory , 2003 .

[5]  Michel Joseph Lambert Visualizing and analyzing human-centered data streams , 2005 .

[6]  Nigel H. Lovell,et al.  Design of an unobtrusive wireless sensor network for nighttime falls detection , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  Svetha Venkatesh,et al.  The Hidden Permutation Model and Location-Based Activity Recognition , 2008, AAAI.

[8]  Andrea Gaggioli,et al.  A mobile data collection platform for mental health research , 2013, Personal and Ubiquitous Computing.

[9]  R. Suganya,et al.  Data Mining Concepts and Techniques , 2010 .

[10]  Daniel Olgu ´ õn,et al.  Human Activity Recognition: Accuracy across Common Locations for Wearable Sensors , 2006 .

[11]  Jukka Vanhala,et al.  TileTrack: Capacitive human tracking using floor tiles , 2009, 2009 IEEE International Conference on Pervasive Computing and Communications.

[12]  J. Sethuraman A CONSTRUCTIVE DEFINITION OF DIRICHLET PRIORS , 1991 .

[13]  Michael I. Jordan,et al.  Hierarchical Bayesian Nonparametric Models with Applications , 2008 .

[14]  Cristian Borcea,et al.  Leveraging Bluetooth co-location traces in group discovery algorithms , 2014, Pervasive Mob. Comput..

[15]  T. Vicsek,et al.  Clique percolation in random networks. , 2005, Physical review letters.

[16]  Cristian Borcea,et al.  GDC: Group Discovery Using Co-location Traces , 2010, 2010 IEEE Second International Conference on Social Computing.

[17]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[18]  Guang-Zhong Yang,et al.  Direction sensitive fall detection using a triaxial accelerometer and a barometric pressure sensor , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[19]  Mortaza S. Bargh,et al.  Indoor localization based on response rate of bluetooth inquiries , 2008, MELT '08.

[20]  J. Kumpula,et al.  Sequential algorithm for fast clique percolation. , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.

[21]  Gary M. Weiss,et al.  Activity recognition using cell phone accelerometers , 2011, SKDD.

[22]  Anind K. Dey,et al.  Understanding and Using Context , 2001, Personal and Ubiquitous Computing.

[23]  J. Pitman Combinatorial Stochastic Processes , 2006 .

[24]  Mohan Kumar,et al.  High accuracy context recovery using clustering mechanisms , 2009, 2009 IEEE International Conference on Pervasive Computing and Communications.

[25]  Daniel Olguin Olguin,et al.  Sociometric badges : wearable technology for measuring human behavior , 2007 .

[26]  Alessandro Puiatti,et al.  Development of a platform to combine sensor networks and home robots to improve fall detection in the home environment , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[27]  Adrian Burns,et al.  SHIMMER™ – A Wireless Sensor Platform for Noninvasive Biomedical Research , 2010, IEEE Sensors Journal.

[28]  Alex Pentland,et al.  Reality mining: sensing complex social systems , 2006, Personal and Ubiquitous Computing.

[29]  Emmanuel,et al.  Activity recognition in the home setting using simple and ubiquitous sensors , 2003 .

[30]  Svetha Venkatesh,et al.  Human Behavior Recognition with Generic Exponential Family Duration Modeling in the Hidden Semi-Markov Model , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[31]  John Nelson,et al.  Activity level classification algorithm using SHIMMER™ wearable sensors for individuals with rheumatoid arthritis , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[32]  Parisa Rashidi Stream Sequence Mining for Human Activity Discovery , 2014 .

[33]  David B. Dunson,et al.  Bayesian Data Analysis , 2010 .

[34]  Michael L. Littman,et al.  Activity Recognition from Accelerometer Data , 2005, AAAI.

[35]  Svetha Venkatesh,et al.  Computable social patterns from sparse sensor data , 2008, LocWeb.

[36]  T. Ferguson A Bayesian Analysis of Some Nonparametric Problems , 1973 .

[37]  Hinrich Schütze,et al.  Introduction to information retrieval , 2008 .

[38]  Urbashi Mitra,et al.  Modeling high-level descriptions of real-life physical activities using latent topic modeling of multimodal sensor signals , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[39]  M. Escobar,et al.  Markov Chain Sampling Methods for Dirichlet Process Mixture Models , 2000 .

[40]  Huiru Zheng,et al.  Human Activity Detection in Smart Home Environment with Self-Adaptive Neural Networks , 2008, 2008 IEEE International Conference on Networking, Sensing and Control.

[41]  P. Müller,et al.  Bayesian Nonparametrics: An invitation to Bayesian nonparametrics , 2010 .

[42]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[43]  T. Vicsek,et al.  Uncovering the overlapping community structure of complex networks in nature and society , 2005, Nature.

[44]  D. Blackwell,et al.  Ferguson Distributions Via Polya Urn Schemes , 1973 .

[45]  Simon Hay,et al.  Bluetooth Tracking without Discoverability , 2009, LoCA.

[46]  Daniel Gatica-Perez,et al.  StressSense: detecting stress in unconstrained acoustic environments using smartphones , 2012, UbiComp.

[47]  Michael I. Jordan,et al.  Hierarchical Dirichlet Processes , 2006 .

[48]  Jukka Vanhala,et al.  Human tracking using electric fields , 2009, 2009 IEEE International Conference on Pervasive Computing and Communications.

[49]  Mohan Kumar,et al.  Unsupervised context detection using wireless signals , 2009, Pervasive Mob. Comput..

[50]  Svetha Venkatesh,et al.  Efficient duration and hierarchical modeling for human activity recognition , 2009, Artif. Intell..

[51]  Shyamal Patel,et al.  Estimating fugl-meyer clinical scores in stroke survivors using wearable sensors , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[52]  Alex Pentland,et al.  Honest Signals - How They Shape Our World , 2008 .

[53]  Jadwiga Indulska,et al.  A survey of context modelling and reasoning techniques , 2010, Pervasive Mob. Comput..

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

[55]  Olga Boric-Lubecke,et al.  Respiratory rate detection using a wearable electromagnetic generator , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[56]  Liang Wang,et al.  Recognizing Human Activities from Silhouettes: Motion Subspace and Factorial Discriminative Graphical Model , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[57]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[58]  Alex Pentland,et al.  Social Sensors for Automatic Data Collection , 2008, AMCIS.

[59]  Dimitrios I. Fotiadis,et al.  Heterogeneous data fusion and intelligent techniques embedded in a mobile application for real-time chronic disease management , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[60]  M. Escobar,et al.  Bayesian Density Estimation and Inference Using Mixtures , 1995 .

[61]  Bernt Schiele,et al.  Unsupervised Discovery of Structure in Activity Data Using Multiple Eigenspaces , 2006, LoCA.

[62]  Bernt Schiele,et al.  Discovery of activity patterns using topic models , 2008 .

[63]  Delbert Dueck,et al.  Clustering by Passing Messages Between Data Points , 2007, Science.

[64]  Michael I. Jordan,et al.  Bayesian Nonparametrics: Hierarchical Bayesian nonparametric models with applications , 2010 .

[65]  O. Mayora-Ibarra,et al.  Smartphone-centred wearable sensors network for monitoring patients with bipolar disorder , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[66]  Zhigang Liu,et al.  The Jigsaw continuous sensing engine for mobile phone applications , 2010, SenSys '10.

[67]  James A. Landay,et al.  The Mobile Sensing Platform: An Embedded Activity Recognition System , 2008, IEEE Pervasive Computing.

[68]  Paul G. Bahn Charting the past , 2004, Nature.

[69]  Shyamal Patel,et al.  Mercury: a wearable sensor network platform for high-fidelity motion analysis , 2009, SenSys '09.