% This file was created with JabRef 2.3.1. % Encoding: UTF-8 @INPROCEEDINGS{Liao2007a, author = {Lin Liao and Tanzeem Choudhury and Dieter Fox and Henry A. Kautz}, title = {Training Conditional Random Fields Using Virtual Evidence Boosting}, booktitle = {IJCAI}, year = {2007}, pages = {2530-2535}, bibsource = {DBLP, http://dblp.uni-trier.de}, crossref = {DBLP:conf/ijcai/2007}, ee = {http://dli.iiit.ac.in/ijcai/IJCAI-2007/PDF/IJCAI07-407.pdf}, file = {Liao2007a.pdf:Liao2007a.pdf:PDF}, owner = {chris}, timestamp = {2009.12.03} } @INPROCEEDINGS{Mahdaviani2007, author = {Maryam Mahdaviani and Tanzeem Choudhury}, title = {Fast and Scalable Training of Semi-Supervised CRFs with Application to Activity Recognition}, booktitle = {NIPS}, year = {2007}, bibsource = {DBLP, http://dblp.uni-trier.de}, crossref = {DBLP:conf/nips/2007}, ee = {http://books.nips.cc/papers/files/nips20/NIPS2007_0863.pdf}, file = {Mahdaviani2007.pdf:Mahdaviani2007.pdf:PDF}, owner = {chris}, timestamp = {2009.12.03} } @MISC{Abowd1997, author = {Gregory D. Abowd and Christopher G. Atkeson and Jason Hong and Sue Long and Rob Kooper}, title = {Cyberguide: A Mobile Context-Aware Tour Guide}, year = {1997}, citeseercitationcount = {0}, citeseerurl = {http://citeseer.ist.psu.edu/36540.html}, comment = {Not relevant.}, file = {Abowd1997.pdf:Abowd1997.pdf:PDF;Abowd1997.pdf:Abowd1997.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @ARTICLE{Aha1991, author = {Aha, David W. and Kibler, Dennis and Albert, Marc K.}, title = {Instance-Based Learning Algorithms}, journal = {Machine Learning}, year = {1991}, volume = {6}, pages = {37--66}, number = {1}, month = {January}, abstract = {Storing and using specific instances improves the performance of several supervised learning algorithms. These include algorithms that learn decision trees, classification rules, and distributed networks. However, no investigation has analyzed algorithms that use only specific instances to solve incremental learning tasks. In this paper, we describe a framework and methodology, called instance-based learning, that generates classification predictions using only specific instances. Instance-based learning algorithms do not maintain a set of abstractions derived from specific instances. This approach extends the nearest neighbor algorithm, which has large storage requirements. We describe how storage requirements can be significantly reduced with, at most, minor sacrifices in learning rate and classification accuracy. While the storage-reducing algorithm performs well on several real-world databases, its performance degrades rapidly with the level of attribute noise in training instances. Therefore, we extended it with a significance test to distinguish noisy instances. This extended algorithm's performance degrades gracefully with increasing noise levels and compares favorably with a noise-tolerant decision tree algorithm.}, address = {Hingham, MA, USA}, citeulike-article-id = {1527614}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=104717}, citeulike-linkout-1 = {http://dx.doi.org/10.1023/A:1022689900470}, citeulike-linkout-2 = {http://www.springerlink.com/content/kn127378pg361187}, day = {1}, doi = {10.1023/A:1022689900470}, file = {Aha1991.pdf:Aha1991.pdf:PDF}, issn = {0885-6125}, keywords = {learning}, owner = {chris}, posted-at = {2007-08-01 14:37:32}, priority = {4}, publisher = {Kluwer Academic Publishers}, timestamp = {2009.12.06}, url = {http://dx.doi.org/10.1023/A:1022689900470} } @ARTICLE{Bannach2008, author = {Bannach, D. and Lukowicz, P. and Amft, O.}, title = {Rapid Prototyping of Activity Recognition Applications}, journal = IEEE_M_PVC, year = {2008}, volume = {7}, pages = {22--31}, number = {2}, month = {April--June }, comment = {The concept of the CRN Toolbox stems from the observation that most activity recognition systems rely on a relatively small set of algorithms. These include sliding-window signal partitioning, standard time and frequency domain features, classifiers, and time series or event-based modeling algorithms.}, doi = {10.1109/MPRV.2008.36}, file = {Bannach2008.pdf:Bannach2008.pdf:PDF;Bannach2008.pdf:Bannach2008.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @ARTICLE{Bao2004, author = {Bao, L. and Intille, S. S.}, title = {Activity Recognition from User-Annotated Acceleration Data}, journal = {Pervasive Computing}, year = {2004}, volume = {3001}, pages = {1--17}, abstract = {In this work, algorithms are developed and evaluated to detect physical activities from data acquired using five small biaxial accelerometers worn simultaneously on different parts of the body. Acceleration data was collected from 20 subjects without researcher supervision or observation. Subjects were asked to perform a sequence of everyday tasks but not told specifically where or how to do them. Mean, energy, frequency-domain entropy, and correlation of acceleration data was calculated and several classifiers using these features were tested. Decision tree classifiers showed the best performance recognizing everyday activities with an overall accuracy rate of 84\%. The results show that although some activities are recognized well with subject-independent training data, others appear to require subject-specific training data. The results suggest that multiple accelerometers aid in recognition because conjunctions in acceleration feature values can effectively discriminate many activities. With just two biaxial accelerometers – thigh and wrist – the recognition performance dropped only slightly. This is the first work to investigate performance of recognition algorithms with multiple, wire-free accelerometers on 20 activities using datasets annotated by the subjects themselves.}, citeulike-article-id = {1188357}, citeulike-linkout-0 = {http://www.springerlink.com/content/9aqflyk4f47khyjd}, comment = {Multiple accelerometers in different locations. Decision-tree classifiers. Some activities are subject-specific. For instance, laboratory acceleration data of walking displays distinct phases of a consistent gait cycle which can aide recognition of pace and incline [2]. However, acceleration data from the same subject outside of the laboratory may display marked fluctuation in the relation of gait phases and total gait length due to decreased self-awareness and fluctuations in traffic.}, file = {Bao2004.pdf:Bao2004.pdf:PDF}, keywords = {acceleration}, owner = {chris}, posted-at = {2008-04-16 11:42:22}, priority = {4}, timestamp = {2009.12.06}, url = {http://www.springerlink.com/content/9aqflyk4f47khyjd} } @INCOLLECTION{Bardram2005, author = {Bardram, Jakob E.}, title = {The Java Context Awareness Framework (JCAF) - A Service Infrastructure and Programming Framework for Context-Aware Applications}, booktitle = {Pervasive Computing}, publisher = {IEEE}, year = {2005}, pages = {98--115}, abstract = {Context-awareness is a key concept in ubiquitous computing. But to avoid developing dedicated context-awareness sub-systems for specific application areas there is a need for more generic programming frameworks. Such frameworks can help the programmer develop and deploy context-aware applications faster. This paper describes the Java Context-Awareness Framework – JCAF, which is a Java-based context-awareness infrastructure and programming API for creating context-aware computer applications. The paper presents the design goals of JCAF, its runtime architecture, and its programming model. The paper presents some applications of using JCAF in three different applications and discusses lessons learned from using JCAF.}, citeulike-article-id = {1145979}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/11428572_7}, citeulike-linkout-1 = {http://www.springerlink.com/content/yl2fen8clqqwq2tb}, doi = {10.1007/11428572_7}, file = {Bardram2005.pdf:Bardram2005.pdf:PDF}, journal = {Pervasive Computing}, keywords = {awareness, context, framework}, owner = {chris}, posted-at = {2007-06-26 09:54:05}, priority = {4}, timestamp = {2009.12.06}, url = {http://dx.doi.org/10.1007/11428572_7} } @ARTICLE{Bellavista2008, author = {Bellavista, P. and Kupper, A. and Helal, S.}, title = {Location-Based Services: Back to the Future}, journal = IEEE_M_PVC, year = {2008}, volume = {7}, pages = {85--89}, number = {2}, month = {April--June }, comment = {Android mail milestone in LBSs, LBS originated with E911 mandate. Moving LSBs from operator controlled to user controlled major factor in success, helped by open systems such as Android and Openmoko.}, doi = {10.1109/MPRV.2008.34}, file = {Bellavista2008.pdf:Bellavista2008.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @INPROCEEDINGS{Bellotti2008, author = {Bellotti, Victoria and Begole, Bo and Chi, Ed H. and Ducheneaut, Nicolas and Fang, Ji and Isaacs, Ellen and King, Tracy and Newman, Mark W. and Partridge, Kurt and Price, Bob and Rasmussen, Paul and Roberts, Michael and Schiano, Diane J. and Walendowski, Alan}, title = {Activity-based serendipitous recommendations with the Magitti mobile leisure guide}, booktitle = {CHI '08: Proceeding of the twenty-sixth annual SIGCHI conference on Human factors in computing systems}, year = {2008}, pages = {1157--1166}, address = {New York, NY, USA}, publisher = {ACM}, citeulike-article-id = {2859755}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1357237}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1357054.1357237}, doi = {10.1145/1357054.1357237}, file = {Bellotti2008.pdf:Bellotti2008.pdf:PDF}, isbn = {9781605580111}, keywords = {ibm, iphone, triage}, owner = {chris}, posted-at = {2008-06-03 19:57:41}, priority = {5}, timestamp = {2009.12.03}, url = {http://dx.doi.org/10.1145/1357054.1357237} } @INPROCEEDINGS{Caros2005, author = {Car\'os, JS. and Ch\'etelat, O. and Celka, P. and Dasen, S.}, title = {Very low complexity algorithm for ambulatory activity classification}, booktitle = {European Medical \& Biological Engineering Conference and IFMBE European Conference on Biomedical Engineering}, year = {2005}, comment = {Mechanism of walking is defined as controlled falling, where the centre of gravity oscillates over the supporting limb following an inverted pendulum movement. At the end of each pendulum movement, the strike of the heel on the floor deaccelerates the swinging phase by generating an abrupt vertical acceleration. *Discrete time index, discrete time Dirac distribution*. Double integration - walking/stairs.}, file = {Caros2005.pdf:Caros2005.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @ARTICLE{Choudhury2008, author = {Choudhury, T. and Consolvo, S. and Harrison, B. and Hightower, J. and LaMarca, A. and LeGrand, L. and Rahimi, A. and Rea, A. and Bordello, G. and Hemingway, B. and Klasnja, P. and Koscher, K. and Landay, J.A. and Lester, J. and Wyatt, D. and Haehnel, D.}, title = {The Mobile Sensing Platform: An Embedded Activity Recognition System}, journal = IEEE_M_PVC, year = {2008}, volume = {7}, pages = {32--41}, number = {2}, month = {April--June }, comment = {Requirements, general architecture, privacy - audio. Structured prediction - temporal/structure & activity/context dependencies. Difficulties with training (labelling large amount of data); semi-supervised training}, doi = {10.1109/MPRV.2008.39}, file = {Choudhury2008.pdf:Choudhury2008.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @INPROCEEDINGS{Consolvo2008, author = {Consolvo, Sunny and Mcdonald, David W. and Toscos, Tammy and Chen, Mike Y. and Froehlich, Jon and Harrison, Beverly and Klasnja, Predrag and Lamarca, Anthony and Legrand, Louis and Libby, Ryan and Smith, Ian and Landay, James A.}, title = {Activity sensing in the wild: a field trial of ubifit garden}, booktitle = {CHI '08: Proceeding of the twenty-sixth annual SIGCHI conference on Human factors in computing systems}, year = {2008}, pages = {1797--1806}, address = {New York, NY, USA}, publisher = {ACM}, citeulike-article-id = {2977124}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1357054.1357335}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1357054.1357335}, doi = {10.1145/1357054.1357335}, file = {Consolvo2008.pdf:Consolvo2008.pdf:PDF}, isbn = {9781605580111}, keywords = {sensing, ubiquitous}, location = {Florence, Italy}, owner = {chris}, posted-at = {2008-08-25 01:26:32}, priority = {2}, timestamp = {2009.12.06}, url = {http://dx.doi.org/10.1145/1357054.1357335} } @ARTICLE{Davies2008, author = {Davies, Nigel and Siewiorek, Daniel P. and Sukthankar, Rahul}, title = {Activity-Based Computing}, journal = IEEE_M_PVC, year = {2008}, volume = {7}, pages = {20--21}, number = {2}, comment = {General intro and basic history}, doi = {10.1109/MPRV.2008.26}, file = {Davies2008.pdf:Davies2008.pdf:PDF;Davies2008.pdf:Davies2008.pdf:PDF}, issn = {1536-1268}, keywords = {activity recognition, activity-based computing, context-aware computing}, owner = {chris}, timestamp = {2009.11.30} } @ARTICLE{Serugendo2008, author = {Di Marzo Serugendo, G.}, title = {Activity-Based Computing}, journal = IEEE_M_PVC, year = {2008}, volume = {7}, pages = {58--61}, number = {2}, month = {April--June }, comment = {Not relevant.}, doi = {10.1109/MPRV.2008.25}, file = {Serugendo2008.pdf:Serugendo2008.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @INPROCEEDINGS{Dornbush2005, author = {Dornbush, S. and Fisher, K. and McKay, K. and Prikhodko, A. and Segall, Z.}, title = {XPOD - A Human Activity and Emotion Aware Mobile Music Player}, booktitle = {Proc. 2nd International Conference on Mobile Technology, Applications and Systems}, year = {2005}, pages = {1--6}, comment = {We used classifiers from the open source Weka library[Witten and Frank, 2005] and neural networks from the open source Joone library[Marrone and Team, 2006]. Decision Tree (J48) [Quinlan, 1993] 41% acc. AdaBoost [Freund and Schapire, 1996] 46% acc. Support Vector Machine (SVM) [Platt, 1998; Keerthi et al 2001] 43%. K-Nearest Neighbours [Aha and Kibler, 1991] 47% acc. Neural networks 43% acc.}, doi = {10.1109/MTAS.2005.207159}, file = {Dornbush2005.pdf:Dornbush2005.pdf:PDF}, keywords = {audio equipment, humanities, mobile handsets, XPod, emotion aware mobile music player, human activity, mobile MP3 player, mobile devices, mobile phone user experience}, owner = {chris}, timestamp = {2009.12.01} } @MISC{Eagle2004, author = {Eagle, N. and Pentland, A.}, title = {Mobile Matchmaking: Proximity Sensing and Cueing}, year = {2004}, comment = {Bluetooth battery life; relationship type based on time of day and bluetooth density; Gaussian mixture model 90%, SVM better?}, file = {Eagle2004.pdf:Eagle2004.pdf:PDF}, journal = {IEEE Pervasive, Special Issue on Smart Phones}, owner = {chris}, timestamp = {2009.12.01} } @ARTICLE{Eagle2006, author = {Eagle, Nathan and Sandy Pentland, Alex}, title = {Reality mining: sensing complex social systems}, journal = {Personal and Ubiquitous Computing}, year = {2006}, volume = {10}, pages = {255--268}, number = {4}, month = {May}, abstract = {Abstract\ \ We introduce a system for sensing complex social systems with data collected from 100 mobile phones over the course of 9\ months. We demonstrate 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.}, address = {London, UK}, citeulike-article-id = {899208}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1122739.1122745}, citeulike-linkout-1 = {http://dx.doi.org/10.1007/s00779-005-0046-3}, citeulike-linkout-2 = {http://www.springerlink.com/content/l562745318077t54}, day = {1}, doi = {10.1007/s00779-005-0046-3}, file = {Eagle2006.pdf:Eagle2006.pdf:PDF}, issn = {1617-4909}, keywords = {complex, mining, reality, sensing, social, systems}, owner = {chris}, posted-at = {2009-10-12 11:59:33}, priority = {2}, publisher = {Springer-Verlag}, timestamp = {2009.12.06}, url = {http://dx.doi.org/10.1007/s00779-005-0046-3} } @MISC{Floreen2008, author = {Patrik Floréen and Joonas Kukkonen and Eemil Lagerspetz and Petteri Nurmi and Jukka Suomela}, title = {BeTelGeuse: Tool for Context Data Gathering via Bluetooth}, year = {2008}, comment = {Not relevant.}, file = {Floreen2008.pdf:Floreen2008.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @MASTERSTHESIS{Garakani2009, author = {AB Garakani}, title = {Real-Time Classification of Everyday Fitness Activities on Windows Mobile}, school = {University of Washington}, year = {2009}, comment = {Instant/smooth classification ideas. Discrete fourier transform on accelerometer data. 24 features per axis. Naive bayes model. 25Hz accelerometer sampling battery life - 7 days down to 24 hours.}, file = {Garakani2009.pdf:Garakani2009.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @INBOOK{Han2006, chapter = {6}, pages = {348-350}, title = {Data mining: concepts and techniques}, publisher = {Morgan Kaufmann}, year = {2006}, author = {Han, J and Kamber, M}, owner = {chris}, timestamp = {2010.01.14} } @MISC{Hein2008, author = {Albert Hein and Thomas Kirste}, title = {Towards Recognizing Abstract Activities: An Unsupervised Approach}, year = {2008}, = {http://www.scientificcommons.org/48837277}, abstract = {Abstract. The recognition of abstract high-level activities using wearable sensors is an important prerequisite for context aware mobile assistance, especially in AAL and medical care applications. A major difficulty in detecting this type of activities is that different activities often share similar motion patterns. One possible solution is to aggregate these activities from shorter, easier to detect base level actions, but the explicit annotation of these is not trivial and very time consuming. In this paper we introduce a simple clustering based method for the recognition of compound activities at a high level of abstraction using k-Means as an unsupervised learning algorithm. A general problem of these methods is that the resulting cluster affiliations are typically not human readable and some kind of interpretation is needed. To achieve this, we developed a hybrid approach using a generative probabilistic model built on top of the clusterer. We adapted a Hidden Markov Model for mapping the cluster memberships onto high-level activities and sucessfully evaluated the feasibility of this technique using experimental data from two test runs of a home care scenario showing a higher accuracy and robustness than conventional discriminative methods.}, comment = {Unsupervised learning for basic actions, then overlying hiden markov model to classify into higher-level activities. K-means clustering algorithm for identification and detection of base-level motion patterns.}, file = {Hein2008.pdf:Hein2008.pdf:PDF}, institution = {CiteSeerX - Scientific Literature Digital Library and Search Engine [http://citeseerx.ist.psu.edu/oai2] (United States)}, keywords = {High-Level Activities, Clustering, Probabilistic Models, AAL}, owner = {chris}, timestamp = {2009.12.01}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.142.6671} } @INPROCEEDINGS{Hightower2005, author = {Hightower, Jeffrey and Consolvo, Sunny and Lamarca, Anthony and Smith, Ian and Hughes, Jeff}, title = {Learning and Recognizing the Places We Go}, booktitle = {UbiComp 2005: Ubiquitous Computing}, year = {2005}, pages = {159--176}, abstract = {Location-enhanced mobile devices are becoming common, but applications built for these devices find themselves suffering a mismatch between the latitude and longitude that location sensors provide and the colloquial place label that applications need. Conveying my location to my spouse, for example as (48.13641N, 11.57471E), is less informative than saying "at home". We introduce an algorithm called BeaconPrint that uses WiFi and GSM radio fingerprints collected by someone's personal mobile device to automatically learn the places they go and then detect when they return to those places. BeaconPrint does not automatically assign names or semantics to places. Rather, it provides the technological foundation to support this task. We compare BeaconPrint to three existing algorithms using month-long trace logs from each of three people. Algorithmic results are supplemented with a survey study about the places people go. BeaconPrint is over 90\% accurate in learning and recognizing places. Additionally, it improves accuracy in recognizing places visited infrequently or for short durations - a category where previous approaches have fared poorly. BeaconPrint demonstrates 63\% accuracy for places someone returns to only once or visits for less than 10 minutes, increasing to 80\% accuracy for places visited twice.}, citeulike-article-id = {1382076}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/11551201_10}, comment = {K-means clustering. 9.6 minute windows. Most algorithms rely on GPS blackouts or Wifi beacons.}, doi = {10.1007/11551201_10}, file = {Hightower2005.pdf:Hightower2005.pdf:PDF}, journal = {UbiComp 2005: Ubiquitous Computing}, keywords = {learning, location, places, prediction, significant}, owner = {chris}, posted-at = {2009-03-24 14:34:56}, priority = {0}, timestamp = {2009.12.06}, url = {http://dx.doi.org/10.1007/11551201_10} } @INPROCEEDINGS{Horvitz1998, author = {Horvitz, E. and Breese, J. and Heckerman, D. and Hovel, D. and Rommelse, K.}, title = {The Lumiere project: Bayesian user modeling for inferring the goals and needs of software users}, booktitle = {In Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence}, year = {1998}, pages = {256--265}, address = {Madison, WI}, month = {July}, abstract = {The Lumi`ere Project centers on harnessing probability and utility to provide assistance to computer software users. We review work on Bayesian user models that can be employed to infer a user's needs by considering a user's background, actions, and queries. Several problems were tackled in Lumi`ere research, including (1) the construction of Bayesian models for reasoning about the time-varying goals of computer users from their observed actions and queries, (2) gaining access to a stream of...}, citeulike-article-id = {1269522}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.39.8472}, file = {Horvitz1998.pdf:Horvitz1998.pdf:PDF}, keywords = {bayesian, computing, inference, modeling, user}, owner = {chris}, posted-at = {2007-05-14 23:50:35}, priority = {4}, timestamp = {2009.12.06}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.39.8472} } @INPROCEEDINGS{Hudson2003, author = {Hudson, Scott and Fogarty, James and Atkeson, Christopher and Avrahami, Daniel and Forlizzi, Jodi and Kiesler, Sara and Lee, Johnny and Yang, Jie}, title = {Predicting human interruptibility with sensors: a Wizard of Oz feasibility study}, booktitle = {CHI '03: Proceedings of the SIGCHI conference on Human factors in computing systems}, year = {2003}, pages = {257--264}, publisher = {ACM Press}, = {New York, NY, USA}, citeulike-article-id = {410042}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=642657}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/642611.642657}, doi = {10.1145/642611.642657}, file = {Hudson2003.pdf:Hudson2003.pdf:PDF}, isbn = {1581136307}, keywords = {interruptibility, wizard\_of\_oz}, owner = {chris}, posted-at = {2005-12-04 00:50:45}, priority = {0}, timestamp = {2010.01.11}, url = {http://dx.doi.org/10.1145/642611.642657} } @INPROCEEDINGS{Huynh2005, author = {Huynh, T\^{a}m and Schiele, Bernt}, title = {Analyzing features for activity recognition}, booktitle = {sOc-EUSAI '05: Proceedings of the 2005 joint conference on Smart objects and ambient intelligence}, year = {2005}, pages = {159--163}, address = {New York, NY, USA}, publisher = {ACM}, abstract = {Human activity is one of the most important ingredients of context information. In wearable computing scenarios, activities such as walking, standing and sitting can be inferred from data provided by body-worn acceleration sensors. In such settings, most approaches use a single set of features, regardless of which activity to be recognized. In this paper we show that recognition rates can be improved by careful selection of individual features for each activity. We present a systematic analysis of features computed from a real-world data set and show how the choice of feature and the window length over which the feature is computed affects the recognition rates for different activities. Finally, we give a recommendation of suitable features and window lengths for a set of common activities.}, citeulike-article-id = {1076182}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1107591}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1107548.1107591}, comment = {Better recognition rates when selecting features based on activity. Popular features: mean, standard deviation, energy, entropy, correleation between axis, discrete FFT coefficients. FFT features generally best, but different coefficients and windows for each activity.}, doi = {10.1145/1107548.1107591}, file = {Huynh2005.pdf:Huynh2005.pdf:PDF}, isbn = {1-59593-304-2}, keywords = {activity, recognition}, location = {Grenoble, France}, owner = {chris}, posted-at = {2007-03-17 06:17:32}, priority = {2}, timestamp = {2009.12.06}, url = {http://dx.doi.org/10.1145/1107548.1107591} } @MISC{Keerthi1999, author = {Keerthi, S. and Shevade, S. and Bhattacharyya, C. and Murthy, K.}, title = {Improvements to Platt's SMO algorithm for SVM classifier design}, year = {1999}, abstract = {This paper points out an important source of confusion and ineciency in Platt's Sequential Minimal Optimization (SMO) algorithm that is caused by the use of a single threshold value. Using clues from the KKT conditions for the dual problem, two threshold parameters are employed to derive modi cations of SMO. These modi ed algorithms perform signi cantly faster than the original SMO on all benchmark datasets tried. 1 Introduction In the past few years, there has been a lot of excitement...}, citeulike-article-id = {1772853}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.46.8538}, file = {Keerthi1999.pdf:Keerthi1999.pdf:PDF}, keywords = {smo, svm}, owner = {chris}, posted-at = {2008-04-12 20:18:51}, priority = {2}, timestamp = {2009.12.06}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.46.8538} } @INPROCEEDINGS{Lee2007, author = {Jae Young Lee and Hoff, W.}, title = {Activity Identification Utilizing Data Mining Techniques}, booktitle = {Proc. IEEE Workshop on Motion and Video Computing WMVC '07}, year = {2007}, pages = {12--12}, month = {Feb. }, doi = {10.1109/WMVC.2007.4}, file = {Lee2007.pdf:Lee2007.pdf:PDF}, owner = {chris}, timestamp = {2009.12.03} } @INPROCEEDINGS{Lester2006, author = {Lester, Jonathan and Choudhury, Tanzeem and Borriello, Gaetano}, title = {A Practical Approach to Recognizing Physical Activities}, booktitle = {Pervasive Computing}, year = {2006}, pages = {1--16}, = {We are developing a personal activity recognition system that is practical, reliable, and can be incorporated into a variety of health-care related applications ranging from personal fitness to elder care. To make our system appealing and useful, we require it to have the following properties: (i) data only from a single body location needed, and it is not required to be from the same point for every user; (ii) should work out of the box across individuals, with personalization only enhancing its recognition abilities; and (iii) should be effective even with a cost-sensitive subset of the sensors and data features. In this paper, we present an approach to building a system that exhibits these properties and provide evidence based on data for 8 different activities collected from 12 different subjects. Our results indicate that the system has an accuracy rate of approximately 90\% while meeting our requirements. We are now developing a fully embedded version of our system based on a cell-phone platform augmented with a Bluetooth-connected sensor board.}, citeulike-article-id = {997656}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/11748625_1}, citeulike-linkout-1 = {http://www.springerlink.com/content/7048888592382352}, doi = {10.1007/11748625_1}, file = {Lester2006.pdf:Lester2006.pdf:PDF}, journal = {Pervasive Computing}, keywords = {accelerometer, activity-recognition}, owner = {chris}, posted-at = {2007-10-12 10:21:05}, priority = {2}, timestamp = {2009.12.03}, url = {http://dx.doi.org/10.1007/11748625_1} } @INPROCEEDINGS{Lester2005, author = {Lester, Jonathan and Choudhury, Tanzeem and Kern, Nicky and Borriello, Gaetano and Hannaford, Blake}, title = {A hybrid discriminative/generative approach for modeling human activities}, booktitle = {In Proc. of the International Joint Conference on Artificial Intelligence (IJCAI}, year = {2005}, pages = {766--772}, abstract = {Accurate recognition and tracking of human activities is an important goal of ubiquitous computing. Recent advances in the development of multi-modal wearable sensors enable us to gather rich datasets of human activities. However, the problem of automatically identifying the most useful features for modeling such activities remains largely unsolved. In this paper we present a hybrid approach to recognizing activities, which combines boosting to discriminatively select useful features and learn an ensemble of static classifiers to recognize different activities, with hidden Markov models (HMMs) to capture the temporal regularities and smoothness of activities. We tested the activity recognition system using over 12 hours of wearable-sensor data collected by volunteers in natural unconstrained environments. The models succeeded in identifying a small set of maximally informative features, and were able identify ten different human activities with an accuracy of 95\%. 1}, citeulike-article-id = {3291348}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.77.5776}, file = {Lester2005.pdf:Lester2005.pdf:PDF}, keywords = {transitgenie}, owner = {chris}, posted-at = {2009-07-11 19:30:29}, priority = {4}, timestamp = {2009.12.06}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.77.5776} } @ARTICLE{Liao2007, author = {Liao, Lin and Fox, Dieter and Kautz, Henry}, title = {Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields}, journal = {Int. J. Rob. Res.}, year = {2007}, volume = {26}, pages = {119--134}, number = {1}, abstract = {Learning patterns of human behavior from sensor data is extremely important for high-level activity inference. This paper describes how to extract a person's activities and significant places from traces of GPS data. The system uses hierarchically structured conditional random fields to generate a consistent model of a person's activities and places. In contrast to existing techniques, this approach takes the high-level context into account in order to detect the significant places of a person. Experiments show significant improvements over existing techniques. Furthermore, they indicate that the proposed system is able to robustly estimate a person's activities using a model that is trained from data collected by other persons.}, address = {Thousand Oaks, CA, USA}, citeulike-article-id = {3480910}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1229555.1229562}, citeulike-linkout-1 = {http://dx.doi.org/10.1177/0278364907073775}, doi = {10.1177/0278364907073775}, file = {Liao2007.pdf:Liao2007.pdf:PDF}, issn = {0278-3649}, keywords = {activity-prediction, place-finding}, owner = {chris}, posted-at = {2008-11-04 21:40:32}, priority = {2}, publisher = {Sage Publications, Inc.}, timestamp = {2009.12.03}, url = {http://dx.doi.org/10.1177/0278364907073775} } @ARTICLE{Liao2007b, author = {Liao, Lin and Patterson, Donald J. and Fox, Dieter and Kautz, Henry}, title = {Learning and inferring transportation routines}, journal = {Artificial Intelligence}, year = {2007}, volume = {171}, pages = {311--331}, number = {5-6}, month = {April}, = {This paper introduces a hierarchical Markov model that can learn and infer a user's daily movements through an urban community. The model uses multiple levels of abstraction in order to bridge the gap between raw GPS sensor measurements and high level information such as a user's destination and mode of transportation. To achieve efficient inference, we apply Rao-Blackwellized particle filters at multiple levels of the model hierarchy. Locations such as bus stops and parking lots, where the user frequently changes mode of transportation, are learned from GPS data logs without manual labeling of training data. We experimentally demonstrate how to accurately detect novel behavior or user errors (e.g. taking a wrong bus) by explicitly modeling activities in the context of the user's historical data. Finally, we discuss an application called "Opportunity Knocks" that employs our techniques to help cognitively-impaired people use public transportation safely.}, citeulike-article-id = {1541495}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1238288}, citeulike-linkout-1 = {http://dx.doi.org/10.1016/j.artint.2007.01.006}, citeulike-linkout-2 = {http://www.sciencedirect.com/science/article/B6TYF-4N49VP9-1/2/8f05b8caf7327ceb8762ab5e1b95efc9}, doi = {10.1016/j.artint.2007.01.006}, file = {Liao2007b.pdf:Liao2007b.pdf:PDF}, keywords = {learning, statistical-inference}, owner = {chris}, posted-at = {2008-11-28 02:40:32}, priority = {2}, timestamp = {2010.01.13}, url = {http://dx.doi.org/10.1016/j.artint.2007.01.006} } @ARTICLE{Lukowicz2002, author = {Lukowicz, P. and Junker, H. and St\"{a}ger, M. and von B\"{u}ren, T. and Tr\"{o}ster, G.}, title = {WearNET: A Distributed Multi-sensor System for Context Aware Wearables}, journal = {UbiComp 2002: Ubiquitous Computing}, year = {2002}, volume = {1}, pages = {361--370}, abstract = {This paper describes a distributed, multi-sensor system architecture designed to provide a wearable computer with a wide range of complex context information. Starting from an analysis of useful high level context information we present a top down design that focuses on the peculiarities of wearable applications. Thus, our design devotes particular attention to sensor placement, system partitioning as well as resource requirements given by the power consumption, computational intensity and communication overhead. We describe an implementation of our architecture and initial experimental results obtained with the system.}, citeulike-article-id = {3909016}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/3-540-45809-3_28}, citeulike-linkout-1 = {http://www.springerlink.com/content/kky208rx9e98m0xg}, doi = {10.1007/3-540-45809-3_28}, file = {Lukowicz2002.pdf:Lukowicz2002.pdf:PDF}, keywords = {action, sensors}, owner = {chris}, posted-at = {2009-01-19 18:25:29}, priority = {5}, timestamp = {2009.12.03}, url = {http://dx.doi.org/10.1007/3-540-45809-3_28} } @ARTICLE{Mathie2004, author = {Mathie, M. and Celler, B. and Lovell, N. and Coster, A.}, title = {Classification of basic daily movements using a triaxial accelerometer}, journal = {Medical and Biological Engineering and Computing}, year = {2004}, volume = {42}, pages = {679--687}, number = {5}, month = {September}, abstract = {Abstract\ \ A generic framework for the automated classification of human movements using an accelerometry monitoring system is introduced. The framework was structured around a binary decision tree in which movements were divided into classes and subclasses at different hierarchical levels. General distinctions between movements were applied in the top levels, and successively more detailed subclassifications were made in the lower levels of the tree. The structure was modular and flexible: parts of the tree could be reordered, pruned or extended, without the remainder of the tree being affected. This framework was used to develop a classifier to identify basic movements from the signals obtained from a single, waist-mounted triaxial accelerometer. The movements were first divided into activity and rest. The activities were classified as falls, walking, transition between postural orientations, or other movement. The postural orientations during rest were classified as sitting, standing or lying. In controlled laboratory studies in which 26 normal, healthy subjects carried out a set of basic movements, the sensitivity of every classification exceeded 87\%, and the specificity exceeded 94\%; the overall accuracy of the system, measured as the number of correct classifications across all levels of the hierarchy, was a sensitivity of 97.7\% and a specificity of 98.7\% over a data set of 1309 movements.}, citeulike-article-id = {4636969}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/BF02347551}, citeulike-linkout-1 = {http://www.springerlink.com/content/wm35501wq8352865}, day = {12}, doi = {10.1007/BF02347551}, file = {Mathie2004.pdf:Mathie2004.pdf:PDF}, owner = {chris}, posted-at = {2009-05-26 20:42:51}, timestamp = {2009.12.06}, url = {http://dx.doi.org/10.1007/BF02347551} } @INPROCEEDINGS{Maurer2006, author = {Maurer, U. and Rowe, A. and Smailagic, A. and Siewiorek, D.P.}, title = {eWatch: a wearable sensor and notification platform}, booktitle = {Proc. International Workshop on Wearable and Implantable Body Sensor Networks BSN 2006}, year = {2006}, pages = {4 pp.--145}, doi = {10.1109/BSN.2006.24}, file = {Maurer2006.pdf:Maurer2006.pdf:PDF}, keywords = {Bluetooth, biomedical equipment, electric sensing devices, patient monitoring, watches, wearable computers, Bluetooth communication, eWatch platform, notification platform, online nearest neighbor classification, power aware hardware, software architecture, wearable computing platform, wearable sensors, wireless links, wrist watch form factor}, owner = {chris}, timestamp = {2009.12.03} } @MISC{Miluzzo2009, author = {Miluzzo, E., and Oakley, J., and Lu, H., and Lane, N., and Peterson, R., and Campbell, A.}, title = {Evaluating the iPhone as a Mobile Platform for People-Centric Sensing Applications}, year = {2009}, comment = {No background apps on iPhone, no access to BT or Wifi stacks.}, file = {Miluzzo2009.pdf:Miluzzo2009.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @INPROCEEDINGS{Nicolai2006, author = {Tom Nicolai and Nils Behrens and Holger Kenn}, title = {Exploring Social Context with the Wireless Rope}, booktitle = {In Proc. Workshop MONET: LNCS 4277}, year = {2006}, comment = {Definition of familiar strangers. DynStra/DynFam formula.}, file = {Nicolai2006.pdf:Nicolai2006.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @INPROCEEDINGS{Nurmi2006, author = {Nurmi, Petteri and Koolwaaij, Johan}, title = {Identifying meaningful locations}, booktitle = {Mobile and Ubiquitous Systems: Networking \& Services, 2006 Third Annual International Conference on}, year = {2006}, pages = {1--8}, abstract = {Existing context-aware mobile applications often rely on location information. However, raw location data such as GPS coordinates or GSM cell identifiers are usually meaningless to the user and, as a consequence, researchers have proposed different methods for inferring so-called places from raw data. The places are locations that carry some meaning to user and to which the user can potentially attach some (meaningful) semantics. Examples of places include home, work and airport. A lack in existing work is that the labeling has been done in an ad hoc fashion and no motivation has been given for why places would be interesting to the user. As our first contribution we use social identity theory to motivate why some locations really are significant to the user. We also discuss what potential uses for location information social identity theory implies. Another flaw in the existing work is that most of the proposed methods are not suited to realistic mobile settings as they rely on the availability of GPS information. As our second contribution we consider a more realistic setting where the information consists of GSM cell transitions that are enriched with GPS information whenever a GPS device is available. We present four different algorithms for this problem and compare them using real data gathered throughout Europe. In addition, we analyze the suitability of our algorithms for mobile devices}, citeulike-article-id = {2420217}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/MOBIQ.2006.340429}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4141782}, comment = {Algorithms for identifying places, use cases, recognise commuting}, doi = {10.1109/MOBIQ.2006.340429}, file = {Nurmi2006.pdf:Nurmi2006.pdf:PDF}, journal = {Mobile and Ubiquitous Systems: Networking \& Services, 2006 Third Annual International Conference on}, keywords = {cs-location, read}, owner = {chris}, posted-at = {2008-02-24 02:03:54}, priority = {2}, timestamp = {2009.12.06}, url = {http://dx.doi.org/10.1109/MOBIQ.2006.340429} } @ARTICLE{Parkka2006, author = {Parkka, J. and Ermes, M. and Korpipaa, P. and Mantyjarvi, J. and Peltola, J. and Korhonen, I.}, title = {Activity classification using realistic data from wearable sensors}, journal = {Information Technology in Biomedicine, IEEE Transactions on}, year = {2006}, volume = {10}, pages = {119--128}, number = {1}, abstract = {Automatic classification of everyday activities can be used for promotion of health-enhancing physical activities and a healthier lifestyle. In this paper, methods used for classification of everyday activities like walking, running, and cycling are described. The aim of the study was to find out how to recognize activities, which sensors are useful and what kind of signal processing and classification is required. A large and realistic data library of sensor data was collected. Sixteen test persons took part in the data collection, resulting in approximately 31 h of annotated, 35-channel data recorded in an everyday environment. The test persons carried a set of wearable sensors while performing several activities during the 2-h measurement session. Classification results of three classifiers are shown: custom decision tree, automatically generated decision tree, and artificial neural network. The classification accuracies using leave-one-subject-out cross validation range from 58 to 97\% for custom decision tree classifier, from 56 to 97\% for automatically generated decision tree, and from 22 to 96\% for artificial neural network. Total classification accuracy is 82\% for custom decision tree classifier, 86\% for automatically generated decision tree, and 82\% for artificial neural network.}, booktitle = {Information Technology in Biomedicine, IEEE Transactions on}, citeulike-article-id = {3759728}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TITB.2005.856863}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1573714}, citeulike-linkout-2 = {http://dx.doi.org/http://dx.doi.org/10.1109/TITB.2005.856863}, citeulike-linkout-3 = {http://dx.doi.org/10.1109/TITB.2005.856863}, doi = {10.1109/TITB.2005.856863}, file = {Parkka2006.pdf:Parkka2006.pdf:PDF;Parkka2006.pdf:Parkka2006.pdf:PDF}, keywords = {activity, coact, health, walton, wearable}, owner = {chris}, posted-at = {2008-12-09 14:55:55}, priority = {2}, timestamp = {2009.12.03}, url = {http://dx.doi.org/10.1109/TITB.2005.856863} } @MISC{Patterson2004, author = {Donald J. Patterson and Dieter Fox and Henry Kautz and Kenneth Fishkin and Mike Perkowitz and Matthai Philipose}, title = {Contextual Computer Support for Human Activity}, year = {2004}, citeseercitationcount = {0}, citeseerurl = {http://citeseer.ist.psu.edu/635960.html}, file = {Patterson2004.pdf:Patterson2004.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @MISC{Philipose2003, author = {Matthai Philipose and Sunny Consolvo and Kenneth Fishkin and Perkowitz Ian Smith}, title = {Fast, Detailed Inference of Diverse Daily Human Activities}, year = {2003}, file = {Philipose2003.pdf:Philipose2003.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @ARTICLE{Philipose2004, author = {Philipose, M. and Fishkin, K.P. and Perkowitz, M. and Patterson, D.J. and Fox, D. and Kautz, H. and Hahnel, D.}, title = {Inferring activities from interactions with objects}, journal = IEEE_M_PVC, year = {2004}, volume = {3}, pages = {50--57}, number = {4}, doi = {10.1109/MPRV.2004.7}, file = {Philipose2004.pdf:Philipose2004.pdf:PDF}, issn = {1536-1268}, keywords = {computerised monitoring, data mining, home automation, home computing, radiofrequency identification, ubiquitous computing, ADL inferencing, ADL monitoring, Proactive Activity Toolkit, daily living activity recognition, daily living activity recording, data mining, elder care, pervasive computing, probabilistic inference engine, radio-frequency-identification technology, ADL monitoring, Proact, Proactive Activity Toolkit, context-aware computing, sensor networks}, owner = {chris}, timestamp = {2009.12.01} } @MISC{Philipose2003a, author = {Philipose, M. and Fishkin, K. and Perkowitz, M. and Patterson, D. and H\"ahnel, D.}, title = {The Probabilistic Activity Toolkit: Towards Enabling Activity-Aware Computer Interfaces}, year = {2003}, file = {Philipose2003a.pdf:Philipose2003a.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @ARTICLE{Raento2005, author = {Raento, Mika and Oulasvirta, Antti and Petit, Renaud and Toivonen, Hannu}, title = {ContextPhone: A Prototyping Platform for Context-Aware Mobile Applications}, journal = {IEEE Pervasive Computing}, year = {2005}, volume = {4}, pages = {51--59}, number = {2}, month = {April}, abstract = {ContextPhone is an open-source prototyping platform for context-aware mobile applications. Its development was based on an iterative, human-centered strategy aimed at enabling real-world applications that are easily integrated into users\&\#253; everyday lives. The strategy included rapid response to feedback from field evaluations. The developers also studied other applications as well as general mobility issues. Their work resulted in prioritized design goals, including an emphasis on context, unobtrusiveness, truthfulness, seamfulness, timeliness and fast interaction. These design goals have been realized in several robust components running on top of the Series 60 Smartphone platform. These components include basic services like error recovery and service starting, sensors for gathering context data, communication channels for interacting with the outside world, and customizable versions of the Smartphone applications. Several real-world applications have been built on top of ContextPhone and the platform is released under an open-source license for use in further research.}, address = {Piscataway, NJ, USA}, booktitle = {Pervasive Computing, IEEE}, citeulike-article-id = {2926228}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1070601.1070628}, citeulike-linkout-1 = {http://dx.doi.org/10.1109/MPRV.2005.29}, citeulike-linkout-2 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1427649}, doi = {10.1109/MPRV.2005.29}, file = {Raento2005.pdf:Raento2005.pdf:PDF}, issn = {1536-1268}, keywords = {adaptive\_interfaces, location\_aware\_computing}, owner = {chris}, posted-at = {2008-06-25 17:18:22}, priority = {2}, publisher = {IEEE Educational Activities Department}, timestamp = {2009.12.06}, url = {http://dx.doi.org/10.1109/MPRV.2005.29} } @INPROCEEDINGS{Ravi2005, author = {Ravi, Nishkam and Nikhil, D. and Mysore, Preetham and Littman, Michael L.}, title = {Activity recognition from accelerometer data}, booktitle = {Proceedings of the Seventeenth Conference on Innovative Applications of Artificial Intelligence(IAAI}, year = {2005}, pages = {1541--1546}, abstract = {Activity recognition fits within the bigger framework of context awareness. In this paper, we report on our efforts to recognize user activity from accelerometer data. Activity recognition is formulated as a classification problem. Performance of base-level classifiers and meta-level classifiers is compared. Plurality Voting is found to perform consistently well across different settings.}, citeulike-article-id = {5157220}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.92.1333}, citeulike-linkout-1 = {https://www.aaai.org/Papers/IAAI/2005/IAAI05-013.pdf}, file = {Ravi2005.pdf:Ravi2005.pdf:PDF}, keywords = {accelerometer, activity-inferencing}, owner = {chris}, posted-at = {2009-07-15 10:33:20}, priority = {2}, timestamp = {2009.12.06}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.92.1333} } @ARTICLE{Reynolds2008, author = {Reynolds, F.}, title = {Camera Phones: A Snapshot of Research and Applications}, journal = IEEE_M_PVC, year = {2008}, volume = {7}, pages = {16--19}, number = {2}, month = {April--June }, comment = {"over one billion camera phones were sold last year"}, doi = {10.1109/MPRV.2008.28}, file = {Reynolds2008.pdf:Reynolds2008.pdf:PDF;Reynolds2008.pdf:Reynolds2008.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @INPROCEEDINGS{Rudstroem2004, author = {Asa Rudstr\"om and Martinn Svensson and Martin Svensson and Rickard C\"oster and Kristina H\"o\"ok}, title = {MobiTip: Using Bluetooth as a Mediator of Social Context}, booktitle = {In Ubicomp 2004 Adjunct Proceedings}, year = {2004}, file = {Rudstroem2004.pdf:Rudstroem2004.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @MISC{Salber1999, author = {Salber, Daniel and Dey, Anind K. and Abowd, Gregory D.}, title = {The Context Toolkit: Aiding the Development of Context-Enabled Applications}, year = {1999}, abstract = {Context-enabled applications are just emerging and promise richer interaction by taking environmental context into account. However, they are difficult to build due to their distributed nature and the use of unconventional sensors. The concepts of toolkits and widget libraries in graphical user interfaces has been tremendously successful, allowing programmers to leverage off existing building blocks to build interactive systems more easily. We introduce the concept of context widgets that mediate between the environment and the application in the same way graphical widgets mediate between the user and the application. We illustrate the concept of context widgets with the beginnings of a widget library we have developed for sensing presence, identity and activity of people and things. We assess the success of our approach with two example context-enabled applications we have built and an existing application to which we have added contextsensing capabilities.}, citeulike-article-id = {3753280}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.2110}, citeulike-linkout-1 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.2110}, file = {Salber1999.pdf:Salber1999.pdf:PDF}, keywords = {applications, context, context\_awareness, toolkit}, owner = {chris}, pages = {434--441}, posted-at = {2008-12-07 12:33:46}, priority = {4}, timestamp = {2009.12.06}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.2110} } @MISC{Schapire1999, author = {Schapire, Robert E.}, title = {A Brief Introduction to Boosting}, year = {1999}, abstract = {Boosting is a general method for improving the accuracy of any given learning algorithm. This short paper introduces the boosting algorithm AdaBoost, and explains the underlying theory of boosting, including an explanation of why boosting often does not suffer from overfitting. Some examples of recent applications of boosting are also described. Background Boosting is a general method which attempts to \&\#034;boost\&\#034; the accuracy of any given learning algorithm. Boosting has its roots in a theoretical framework for studying machine learning called the \&\#034;PAC\&\#034; learning model, due to Valiant [37]; see Kearns and Vazirani [24] for a good introduction to this model. Kearns and Valiant [22, 23] were the first to pose the question of whether a \&\#034;weak\&\#034; learning algorithm which performs just slightly better than random guessing in the PAC model can be \&\#034;boosted\&\#034; into an arbitrarily accurate \&\#034;strong\&\#034; learning algorithm. Schapire [30] came up with the first provable polynomial-time boosting algorithm in ...}, citeulike-article-id = {6212085}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.7.8772}, file = {Schapire1999.pdf:Schapire1999.pdf:PDF}, keywords = {boosting}, owner = {chris}, posted-at = {2009-11-25 20:48:42}, priority = {2}, timestamp = {2009.12.03}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.7.8772} } @MISC{Schilit1994, author = {Bill Schilit and Norman Adams and Roy Want}, title = {Context-Aware Computing Applications}, year = {1994}, citeseercitationcount = {0}, citeseerurl = {http://citeseer.ist.psu.edu/339782.html}, file = {Schilit1994.pdf:Schilit1994.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @MISC{Schmidt2008, author = {Albrecht Schmidt and Kofi Asante Aidoo and Antti Takaluoma and Urpo Tuomela and Kristof Van Laerhoven and Walter Van de Velde}, title = {iLearn on the iPhone: Real-Time Human Activity Classification on Commodity Mobile Phones}, year = {2008}, file = {Schmidt2008.pdf:Schmidt2008.pdf:PDF}, owner = {chris}, timestamp = {2009.12.03} } @ARTICLE{Schmidt1999, author = {Schmidt, A. and Aidoo, K. A. and Takaluoma, A. and Tuomela, U. and Van Laerhoven, K. and Van de Velde, W.}, title = {Advanced Interaction in Context}, journal = {Lecture Notes in Computer Science}, year = {1999}, volume = {1707}, pages = {89--??}, abstract = {. Mobile information appliances are increasingly used in numerous different situations and locations, setting new requirements to their interaction methods. When the user's situation, place or activity changes, the functionality of the device should adapt to these changes. In this work we propose a layered real-time architecture for this kind of context-aware adaptation based on redundant collections of low-level sensors. Two kinds of sensors are distinguished: physical and logical...}, citeulike-article-id = {1284635}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.40.2408}, file = {Schmidt1999.pdf:Schmidt1999.pdf:PDF}, keywords = {context, mobile, pervasive, ubicomp}, owner = {chris}, posted-at = {2007-05-09 07:15:21}, priority = {4}, timestamp = {2009.12.03}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.40.2408} } @MISC{Shen2004, author = {Jianqiang Shen}, title = {Machine Learning for Activity Recognition}, year = {2004}, file = {Shen2004.pdf:Shen2004.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @INPROCEEDINGS{Siewiorek2003, author = {Siewiorek, D. and Smailagic, A. and Furukawa, J. and Krause, A. and Moraveji, N. and Reiger, K. and Shaffer, J. and Wong, Fei L.}, title = {SenSay: a context-aware mobile phone}, booktitle = {Wearable Computers, 2003. Proceedings. Seventh IEEE International Symposium on}, year = {2003}, pages = {248--249}, citeulike-article-id = {898575}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/ISWC.2003.1241422}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1241422}, doi = {10.1109/ISWC.2003.1241422}, file = {Siewiorek2003.pdf:Siewiorek2003.pdf:PDF}, journal = {Wearable Computers, 2003. Proceedings. Seventh IEEE International Symposium on}, keywords = {aware, context, mobile, phone}, owner = {chris}, posted-at = {2008-09-16 14:38:06}, priority = {2}, timestamp = {2009.12.06}, url = {http://dx.doi.org/10.1109/ISWC.2003.1241422} } @INPROCEEDINGS{Song2005, author = {Song, K. and Wang, Y.}, title = {Remote Activity Monitoring of the Elderly Using a Two-Axis Accelerometer}, booktitle = {CACS Automatic Control Conference}, year = {2005}, file = {Song2005.pdf:Song2005.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @ARTICLE{Stiefmeier2008, author = {Stiefmeier, T. and Roggen, D. and Troster, G. and Ogris, G. and Lukowicz, P.}, title = {Wearable Activity Tracking in Car Manufacturing}, journal = IEEE_M_PVC, year = {2008}, volume = {7}, pages = {42--50}, number = {2}, month = {April--June }, doi = {10.1109/MPRV.2008.40}, file = {Stiefmeier2008.pdf:Stiefmeier2008.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @ARTICLE{Tentori2008, author = {Tentori, M. and Favela, J.}, title = {Activity-Aware Computing for Healthcare}, journal = IEEE_M_PVC, year = {2008}, volume = {7}, pages = {51--57}, number = {2}, month = {April--June }, doi = {10.1109/MPRV.2008.24}, file = {Tentori2008.pdf:Tentori2008.pdf:PDF}, owner = {chris}, timestamp = {2009.12.01} } @INPROCEEDINGS{Terry2002, author = {Terry, Michael and Mynatt, Elizabeth D. and Ryall, Kathy and Leigh, Darren}, title = {Social net: using patterns of physical proximity over time to infer shared interests}, booktitle = {CHI '02: CHI '02 extended abstracts on Human factors in computing systems}, year = {2002}, pages = {816--817}, address = {New York, NY, USA}, publisher = {ACM Press}, citeulike-article-id = {934249}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=506443.506612}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/506443.506612}, doi = {10.1145/506443.506612}, file = {Terry2002.pdf:Terry2002.pdf:PDF}, isbn = {1581134541}, keywords = {networking, social}, owner = {chris}, posted-at = {2008-08-21 15:56:49}, priority = {2}, timestamp = {2009.12.06}, url = {http://dx.doi.org/10.1145/506443.506612} } @ARTICLE{Voida2002, author = {Voida, S. and Mynatt, E.D. and MacIntyre, B. and Corso, G.M.}, title = {Integrating virtual and physical context to support knowledge workers}, journal = IEEE_M_PVC, year = {2002}, volume = {1}, pages = {73--79}, number = {3}, doi = {10.1109/MPRV.2002.1037725}, file = {Voida2002.pdf:Voida2002.pdf:PDF}, issn = {1536-1268}, keywords = {distributed processing, groupware, management information systems, user interfaces, Kimura system, data sources, electronic whiteboard, knowledge workers, networked peripheral devices, pervasive computing}, owner = {chris}, timestamp = {2009.12.01} } @INPROCEEDINGS{Wang2009, author = {Wang, Yi and Lin, Jialiu and Annavaram, Murali and Jacobson, Quinn A. and Hong, Jason and Krishnamachari, Bhaskar and Sadeh, Norman}, title = {A framework of energy efficient mobile sensing for automatic user state recognition}, booktitle = {MobiSys '09: Proceedings of the 7th international conference on Mobile systems, applications, and services}, year = {2009}, pages = {179--192}, address = {New York, NY, USA}, publisher = {ACM}, doi = {http://doi.acm.org/10.1145/1555816.1555835}, file = {Wang2009.pdf:Wang2009.pdf:PDF;Wang2009.pdf:Wang2009.pdf:PDF}, isbn = {978-1-60558-566-6}, location = {Krak\'{o}w, Poland}, owner = {chris}, timestamp = {2009.12.03} } @INBOOK{Witten2000, chapter = {3}, pages = {72-75}, title = {Data Mining: Practical Machine Learning Tools and. Techniques with Java Implementations}, publisher = {Morgan Kaufmann}, year = {2000}, author = {Ian H. Witten and Eibe Frank}, owner = {chris}, timestamp = {2010.01.14} } @INPROCEEDINGS{Wyatt2007, author = {Wyatt, D. and Choudhury, T. and Kautz, H.}, title = {Capturing Spontaneous Conversation and Social Dynamics: A Privacy-Sensitive Data Collection Effort}, booktitle = {Proc. IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2007}, year = {2007}, volume = {4}, pages = {IV-213--IV-216}, doi = {10.1109/ICASSP.2007.367201}, file = {Wyatt2007.pdf:Wyatt2007.pdf:PDF}, issn = {1520-6149}, keywords = {data acquisition, speech intelligibility, UW dynamic social network, paralinguistic features, privacy constraints, privacy-sensitive data collection effort, prosodic features, social dynamics, spontaneous conversation, spontaneous face-to-face conversations, Data acquisition, oral communication, privacy, speech analysis}, owner = {chris}, timestamp = {2009.12.03} } @INPROCEEDINGS{Yang2008, author = {Sung-Ihk Yang and Sung-Bae Cho}, title = {Recognizing human activities from accelerometer and physiological sensors}, booktitle = {Proc. IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems MFI 2008}, year = {2008}, pages = {100--105}, month = {20--22 Aug. }, doi = {10.1109/MFI.2008.4648116}, file = {Yang2008.pdf:Yang2008.pdf:PDF}, owner = {chris}, timestamp = {2009.12.03} } @MISC{ChangeWave2010, title = {http://www.changewaveresearch.com/articles/2010/01/smart\_phone\_20100104.html}, owner = {chris}, timestamp = {2010.01.12}, url = {http://www.changewaveresearch.com/articles/2010/01/smart_phone_20100104.html} } @MISC{ComputerWorld2010, title = {http://www.computerworld.com/s/article/9139026/}, owner = {chris}, timestamp = {2010.01.12}, url = {http://www.computerworld.com/s/article/9139026/Android_to_grab_No._2_spot_by_2012_says_Gartner} } @MISC{TwoFortyFourAm2010, title = {http://www.twofortyfouram.com/}, owner = {chris}, timestamp = {2010.01.14}, url = {http://www.twofortyfouram.com/} } @comment{jabref-meta: selector_publisher:} @comment{jabref-meta: selector_author:} @comment{jabref-meta: selector_journal:} @comment{jabref-meta: selector_keywords:} @comment{jabref-meta: groupsversion:3;} @comment{jabref-meta: groupstree: 0 AllEntriesGroup:; 1 ExplicitGroup:Unread\;0\;Aha1991\;Bardram2005\;Bellotti2008\;Consolv o2008\;Eagle2006\;Horvitz1998\;Hudson2003\;Keerthi1999\;Lee2007\;Leste r2005\;Lester2006\;Liao2007\;Liao2007a\;Liao2007b\;Lukowicz2002\;Mahda viani2007\;Mathie2004\;Maurer2006\;Parkka2006\;Patterson2004\;Philipos e2003\;Philipose2003a\;Philipose2004\;Raento2005\;Ravi2005\;Rudstroem2 004\;Salber1999\;Schapire1999\;Schilit1994\;Schmidt1999\;Siewiorek2003 \;Song2005\;Stiefmeier2008\;Tentori2008\;Terry2002\;Voida2002\;Wang200 9\;Wyatt2007\;Yang2008\;; }