Discovery of activity patterns using topic models
Published 21 September 2008
Tâm Huỳnh, Mario Fritz, Bernt Schiele
Citations444
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Experimental results show the ability of the approach to model and recognize daily routines without user annotation to be able to be used in this work.
Abstract
In this work we propose a novel method to recognize daily routines as a probabilistic combination of activity patterns. The use of topic models enables the automatic discovery of such patterns in a user's daily routine. We report experimental results that show the ability of the approach to model and recognize daily routines without user annotation.
Keywords
Computer ScienceSocial Sciences
Journal of Machine Learning ResearchLatent dirichlet allocation
27,049 Citations2003David M. Blei, Andrew Y. Ng +1 more
Personal and Ubiquitous ComputingReality mining: sensing complex social systems
2,765 Citations2005Nathan Eagle, Alex Pentland
The ability to use standard Bluetooth-enabled mobile telephones to measure information access and use in different contexts, recognize social patterns in daily user activity, infer relationships, identify socially significant locations, and model organizational rhythms is demonstrated.
Machine LearningUnsupervised Learning by Probabilistic Latent Semantic Analysis
2,443 Citations2001Thomas Hofmann
This paper proposes to make use of a temperature controlled version of the Expectation Maximization algorithm for model fitting, which has shown excellent performance in practice, and results in a more principled approach with a solid foundation in statistical inference.
Psychological BulletinEvent structure in perception and conception.
1,138 Citations2001Jeffrey M. Zacks, Barbara Tversky
An analysis of how people use event structure in perception, understanding, planning, and action is constructed and an explanation of how multiple sources of information interact in event perception and conception is explained.
IEEE Pervasive ComputingInferring Activities from Interactions with Objects
872 Citations2004Matthai Philipose, K.P. Fishkin +5 more
The key observation is that the sequence of objects a person uses while performing an ADL robustly characterizes both the ADL's identity and the quality of its execution.
Lecture notes in computer sciencePredestination: Inferring Destinations from Partial Trajectories
454 Citations2006John Krumm, Eric Horvitz
A method called Predestination is described that uses a history of a driver's destinations, along with data about driving behaviors, to predict where a driver is going as a trip progresses, to produce a probabilistic map of destinations.
Fine-Grained Activity Recognition by Aggregating Abstract Object Usage
450 Citations2005Donald J. Patterson, D. Fox +2 more
A sequence of increasingly powerful probabilistic graphical models for activity recognition are presented that can reason tractably about aggregated object instances and gracefully generalizes from object instances to their classes by using abstraction smoothing.
The International Journal of Robotics ResearchExtracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields
411 Citations2007Lin Liao, Dieter Fox +1 more
The proposed system is able to robustly estimate a person’s activities using a model that is trained from data collected by other persons, and shows significant improvements over existing techniques.
Layered representations for human activity recognition
306 Citations2003Nuria Oliver, Eric Horvitz +1 more
The use of representation in a system that diagnoses states of a user's activity based on real-time streams of evidence from video, acoustic, and computer interactions is described.
Lecture notes in computer scienceScalable Recognition of Daily Activities with Wearable Sensors
156 Citations2007Tâm Huỳnh, Ulf Blanke +1 more
This work records a realistic 10h data set and analyzes the performance of four different algorithms for the recognition of both low- and high-level activities, and suggests that the Recognition of high- level activities can be achieved with the same algorithms as therecognition of low-level Activities.
Unsupervised clustering of ambulatory audio and video
143 Citations1999Brian Clarkson, Alex Pentland
This system can (without any prior labeling of data) cluster the audio/visual data into events, such as passing through doors and crossing the street, and hierarchically cluster these events into scenes and get clusters that correlate with visiting the supermarket, or walking down a busy street.
Coordinate: probabilistic forecasting of presence and availability
132 Citations2002Eric Horvitz, Paul Koch +2 more
ProceedingsDiscovering Characteristic Actions from On-Body Sensor Data
128 Citations2006David Minnen, Thad Starner +2 more
The approach to activity discovery, the unsupervised identification and modeling of human actions embedded in a larger sensor stream, is presented and the algorithm successfully discovers motifs that correspond to the real exercises with a recall rate of 96.3% and overall accuracy of 86.7%.
Rhythm modeling, visualizations and applications
105 Citations2003Bo Begole, John Tang +1 more
Algorithms for programatically detecting and modeling temporal patterns from a record of online presence data are presented and the implications of this technology on the design of computer-mediated communication are discussed.
Recognizing and Discovering Human Actions from On-Body Sensor Data
77 Citations2005David Minnen, Thad Starner +3 more
The initial efforts to learn high-level human behaviors from low-level gestures observed using on-body sensors, and an algorithm that can take advantage of such a sensor framework to automatically discover and label recurring behaviors are described.
Long term activity monitoring with a wearable sensor node
50 Citations2006Kristof Van Laerhoven, Hans Gellersen +1 more
An encapsulated sensor node is devised to monitor and record motion patterns over long, quotidian periods of time with potential application in psychological studies by combining tilt switches and accelerometers with customized processing techniques.
Lecture notes in computer scienceRecognising Activities of Daily Life Using Hierarchical Plans
39 Citations2007Usman Naeem, John Bigham +1 more
A tiered approach to deal with recognition of activities that addresses the problem of missing sensor events that can occur while a task is being carried out is described.
Lecture notes in computer scienceRecognition of User Activity Sequences Using Distributed Event Detection
32 Citations2007Oliver Amft, Clemens Lombriser +2 more
The architecture can be scaled in the number of sensor-detectors, activity events and sequences while being adequately quantified by the presented metrics.
Unsupervised activity discovery and characterization from event-streams
24 Citations2005Roszilah Hamid, Siddhartha Maddi +4 more
It is shown how modeling an activity as a variable length Markov process, can be used to discover recurrent event-motifs to characterize the discovered activity-classes and the competence and generalizability of this proposed framework is shown.