Context-aware mobile computing: learning context- dependent personal preferences from a wearable sensor array
IEEE Transactions on Mobile ComputingPublished 1 February 2006
Andreas Krause, Asim Smailagic, Daniel P. Siewiorek
Citations210
SJR quartileQ1
SJR score2.33
SNIP2.38
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
A wearable system which can learn context-dependent personal preferences by identifying individual user states and observing how the user interacts with the system in these states is designed, implemented, and evaluated.
Abstract
Context-aware computing describes the situation where a wearable/mobile computer is aware of its user's state and surroundings and modifies its behavior based on this information. We designed, implemented, and evaluated a wearable system which can learn context-dependent personal preferences by identifying individual user states and observing how the user interacts with the system in these states. This learning occurs online and does not require external supervision. The system relies on techniques from machine learning and statistical analysis. A case study integrates the approach in a context-aware mobile phone. The results indicate that the method is able to create a meaningful user context model while only requiring data from comfortable wearable sensor devices.
Keywords
Computer ScienceSocial Sciences
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Cluster Separation Measure
8,543 Citations1979David L. Davies, Donald W. Bouldin
A measure is presented which indicates the similarity of clusters which are assumed to have a data density which is a decreasing function of distance from a vector characteristic of the cluster which can be used to infer the appropriateness of data partitions.
Machine LearningA Bayesian Method for the Induction of Probabilistic Networks from Data
3,525 Citations1992Gregory F. Cooper, Edward H. Herskovits
This paper presents a Bayesian method for constructing probabilistic networks from databases, focusing on constructing Bayesian belief networks, and extends the basic method to handle missing data and hidden variables.
Machine LearningA Bayesian method for the induction of probabilistic networks from data
2,344 Citations1992Gregory F. Cooper, Edward H. Herskovits
This paper presents a Bayesian method for constructing probabilistic networks from databases, focusing on constructing Bayesian belief networks, and extends the basic method to handle missing data and hidden variables.
Trends in Cognitive SciencesCatastrophic forgetting in connectionist networks
2,295 Citations1999Robert M. French, R French
The causes, consequences and numerous solutions to the problem of catastrophic forgetting in neural networks are examined and the brain might have overcome this problem and the consequences for distributed connectionist networks are explored.
Software Practice and ExperienceAn open graph visualization system and its applications to software engineering
1,103 Citations2000Emden R. Gansner, Stephen C. North
A package of practical tools and libraries for manipulating graphs and their drawings that includes stream and event interfaces for graph operations, high‐quality static and dynamic layout algorithms, and the ability to handle sizeable graphs is described.
Software Practice and ExperienceAn open graph visualization system and its applications to software engineering
610 Citations2000Emden R. Gansner, Stephen C. North
Design for wearability
451 Citations2002Francine Gemperle, C. Kasabach +3 more
This paper explores the concept of dynamic wearability, through design research, to locate, understand, and define the spaces on the human body where solid and flexible forms can rest-without interfering with fluid human movement.
Social Science Computer ReviewAn Introduction to Computerized Experience Sampling in Psychology
423 Citations2001Lisa Feldman Barrett, Daniel Barrett
The authors explain how palmtop computers have expanded the repertoire of experience-sampling techniques and reduced or eliminated some traditional problems with pen-and-paper methods.
IEEE Wireless CommunicationsLocation sensing and privacy in a context-aware computing environment
333 Citations2002A. Smailagic, Dmitry Kogan
The method reduces training complexity by a factor of eight over previous algorithms, and yields noticeably better accuracy, which uses less power than previous models, and offers a more secure privacy model.
SenSay: a context-aware mobile phone
303 Citations2004Daniel P. Siewiorek, Asim Smailagic +6 more
Results from the threshold analyses show a clear delineation can be made among several user states by examining sensor data trends.
Predicting human interruptibility with sensors
295 Citations2003Scott E. Hudson, James Fogarty +6 more
The results of this Wizard of Oz study are very promising, with the overall accuracy of several models reaching about 78%.
Wearable sensor badge and sensor jacket for context awareness
239 Citations2003J. Farringdon, Alessandra Moore +3 more
A wearable sensor badge is described constructed from (hard) electronic components, which can sense perambulatory activities for context-awareness, and a wearable sensor jacket is described that uses advanced knitting techniques to form (soft) fabric stretch sensors positioned to measure upper limb and body movement.
What shall we teach our pants?
229 Citations2002Kristof Van Laerhoven, Ozan Cakmakci
Using a combination of machine learning techniques such as Kohonen maps and probabilistic models, this work builds a system that is able to learn activities while requiring minimal user attention.
MIThril 2003: applications and architecture
159 Citations2004R.W. DeVaul, Michael Sung +2 more
The power and functionality of MIThril 2003 is demonstrated by describing compelling real-worldwearable research applications created using MIThrill2003 technology.
Unsupervised, dynamic identification of physiological and activity context in wearable computing
151 Citations2004Andreas Krause, Daniel P. Siewiorek +2 more
The results indicate the power of the method to determine a meaningful user context model while only requiring data from a comfortable physiological sensor device.
Examining the robustness of sensor-based statistical models of human interruptibility
134 Citations2004James Fogarty, Scott E. Hudson +1 more
It is demonstrated that sensor-based statistical models of human interruptibility can provide robust estimates for a variety of office workers in a range of circumstances and can do so with accuracy as good as or better than people.
IEEE International Conference on Neural NetworksThings you haven't heard about the self-organizing map
127 Citations2002Teuvo Kohonen
The self-organizing map algorithm can be related to a biological neural network in many essential known details; even cyclic behavior automatically ensues from a simple nonlinear neural model, whereby these cycles correspond to the steps of the discrete-time SOM algorithm.
DSpace@MIT (Massachusetts Institute of Technology)Life patterns : structure from wearable sensors
102 Citations2002Brian Clarkson
This thesis develops and evaluates computational methods for extracting life's patterns from wearable sensor data and shows how to use the redundancies in an individual's life to predict his actions from his past behavior.
Lecture notes in computer scienceCombining the Self-Organizing Map and K-Means Clustering for On-Line Classification of Sensor Data
73 Citations2001Kristof Van Laerhoven
An adaptive approach that uses a Kohonen Self-Organizing Map, augmented with on-line k-means clustering for classification of the incoming sensor data is proposed, which avoids overwriting of prototypes on the map.
IEEE Pervasive ComputingApplication design for wearable and context-aware computers
56 Citations2002Asim Smailagic, Daniel P. Siewiorek
To address mobile-application design challenges, the authors created four user interface models that map problem-solving capabilities to application requirements.
SoundButton: design of a low power wearable audio classification system
48 Citations2004Mathias Stäger, Paul Lukowicz +4 more
The paper deals with the design of a sound recognitions system focused on an ultra low power hardware implementation in a button like miniature form factor and presents the VHDL model of the hardware showing that the method can be implemented with minimal resources.
Predicting human interruptibility with sensors
14 Citations2003Scott E. Hudson, James Fogarty +6 more
Lancaster EPrints (Lancaster University)Combining the Kohonen Self-Organizing Map and K-Means for On-Line Classification of Sensordata
14 Citations2001Kristof Van Laerhoven
This paper proposes an adaptive approach that uses a Kohonen Self-Organizing Map, augmented with on-line k-means clustering for classification of the incoming sensor data.