Initial import of papers

.gitignore

@@ -0,0 +1 @@
+/papers/*.bak

papers/project.bib

@@ -0,0 +1,862 @@
+% 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},
+  file = {Abowd1997.pdf:Abowd1997.pdf:PDF},
+  owner = {chris},
+  pdf = {Abowd1997.pdf},
+  timestamp = {2009.12.01}
+}
+
+@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},
+  owner = {chris},
+  pdf = {Bannach2008.pdf},
+  timestamp = {2009.12.01}
+}
+
+@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 },
+  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},
+  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 = {Carós, JS. and Chételat, 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},
+  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}
+}
+
+@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},
+  issn = {1536-1268},
+  keywords = {activity recognition, activity-based computing, context-aware computing},
+  owner = {chris},
+  pdf = {Davies2008.pdf},
+  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 },
+  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},
+  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},
+  file = {Eagle2004.pdf:Eagle2004.pdf:PDF},
+  journal = {IEEE Pervasive, Special Issue on Smart Phones},
+  owner = {chris},
+  timestamp = {2009.12.01}
+}
+
+@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},
+  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},
+  file = {Garakani2009.pdf:Garakani2009.pdf:PDF},
+  owner = {chris},
+  timestamp = {2009.12.01}
+}
+
+@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.},
+  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{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},
+  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}
+}
+
+@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},
+  comment = {NOTE: These notes were supplemented by looking at Liao's dissertation
+	writeup of the same work.
+	
+	Overview: This is a supervised learning scheme done in several stages...
+	the results from early stages are used to build the structure of
+	the model in subsequent stages. Training is done for 3 people, and
+	tested on a 4th person. For the test person, only GPS pings are used
+	as input.
+	
+	specifics: * GPS traces from 4 people, 6 days per person * \~{}40,000
+	GPS measurements per person * manually labeled all activities and
+	significant places in these traces * used maximum pseudo-likelihood
+	for learning
+	
+	hierarchical graphical model with 3 levels. top level: significant
+	places (e.g. home, work, bus stop, parking lot, friend) midlevel:
+	activity sequence (eg. walk, drive, visit, sleep, get on bus, pickup),
+	bottom level: GPS trace (association to streeet map)
+	
+	* their typical GPS trace consists of approximately one GPS reading
+	per second * GPS readings are segmented spatially; we have one activity
+	node for each spatial segment of GPS pings ** e.g. a 12 hour stay
+	at a single location is represented by a single activity node * if
+	street map is available, segmentation is done in association with
+	the street map (with 10m discretization) * "model can reason explicitly
+	about the duration of a stay, for which dynamic models such as standard
+	DBNs or HMMs have only limited support" [12,32]
+	
+	* two main groups of activities: navigation activities, and significant
+	activities (in a single place, or at a transportation mode switch)
+	* "to determine activities, our model relies heavily on temporal
+	features, such as duration or time of day, and geographic information,
+	such as locations of restaurants, stores, and bus stops." * "significant
+	places are those locations that play a significnat role in the activities
+	of a person: hoe, work, bus stops, parking lots typically used, homes
+	of friends, etc...) model allows different activites to occur at
+	same significant place; also, a significnat place can comprise mutiple
+	different locations, mostly because of signal loss and GPS readings
+	
+	The CRF Model for Activity Recognition: 1) CRF for GPS denoising *
+	break up street segments into 10 meter patches * measurement clique
+	between each ping and all nearby street patches (Gaussian noise model
+	from center of patch) * consistency cliques: put a Gaussian noise
+	model on the \_difference\_ between the GPS displacement and the
+	paired street patch displacement for consecutive pings * smoothness
+	cliques: encourage street patch predictions to be stay on the same
+	street, going in the same direction their conditional model for street
+	patches given GPS pings is given in Eqn 26, bottom of page 10
+	
+	Output of the CRF model is taken as the spatial segmentation of the
+	GPS pings... Hierarchical CRF is based on the segmentation, since
+	one 'activity sequence' is associated with each sequence of points
+	on the same 10m street patch * bottom layer of 3 layer CRF, now it's
+	"local evidence" including: ** temporal information (e.g. time od
+	day, day of week, duration of stay -- these can be discretized) clique
+	functions are all binary indicators, one for every possible combination
+	of temporal feature and activity ** average speed through segment
+	-- discretized ** information extracted from geographic databses,
+	such as whether a patch is on a bus route, close to abus stop, near
+	a restaurant or grovery store; use indicator functions to model this
+	information ** each activity node connected to its neighbors; e.g.
+	extremely unlikely tha ta person will get on bus at one location
+	and drive a car at neighboing location right afterwards (?)
+	
+	* Preliminary CRF\_0: just has activity nodes and local evidence nodes
+	[notes from thesis] ** adjacent activity nodes are connected, and
+	each activity node is connected to each 'ftr' with a pairwise potential
+	** features are *** gps based: streetpatch, timeofday (first timestamp,
+	discretized into Moring, Noon, AFternoon, Evening, Night), dayofweek,
+	duration, *** geo database: nearrestaurant, nearstore, nearbusstop,
+	onbusroute [latter extracted from geographic databaddses] *** average
+	speed thru segment (discretized - 'to allow multimodality')
+	
+	* Significant Places [from thesis] ** from the MAP activity sequence,
+	they then (by hand? they refer to an IsSignificant() function) associate
+	each activity with whether or not it belongs to a significant place
+	(e.g. transport does not connect to a significant place, while getting
+	on / off a bus does ...); * spatial clustering performed on the locations
+	of significant places * the cluster centers are the 'signiciant plces'
+	* edge between each place label and each activity label in its vicinity
+	* NOTE: the 'place nodes' are not dynamic; we find K lat,longs that
+	are the locations of the significant places; what we still ned to
+	infer are the labels for these significant places; e.g. several of
+	the lat,longs can be 'shopping', or 'friend's house, etc... certain
+	place labels are associated with certain types of activities * they
+	want to also add features that count the number of 'home', 'workplace',
+	etc., labels that are used. However, this requires making a clique
+	containing all the places, which can be quite large...
+	
+	generate\_places algorithm: * really not clear -- clustering places
+	associated with the same activity? how can you get any confidence
+	in the activities?
+	
+	* Each place (node at the top level of 3 level CRF) connects to all
+	activities that seem to occur in the same place -- built into the
+	structure of the model * multiple activities may occur at the same
+	place
+	
+	* each GPS associated with a 10m patch on a street edge * [20] inference
+	using loopy belief propagation, and parameter learning using pseudo-likelihoodreferences
+	to chase down: bennewitz [4] learn different motion paths between
+	places, [23] how to figure out types of places;},
+  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{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}
+}
+
+@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},
+  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},
+  file = {Nicolai2006.pdf:Nicolai2006.pdf:PDF},
+  owner = {chris},
+  timestamp = {2009.12.01}
+}
+
+@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},
+  keywords = {activity, coact, health, walton, wearable},
+  owner = {chris},
+  pdf = {Parkka2006.pdf},
+  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 Hähnel, 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{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},
+  owner = {chris},
+  pdf = {Reynolds2008.pdf},
+  timestamp = {2009.12.01}
+}
+
+@INPROCEEDINGS{Rudstroem2004,
+  author = {Åsa Rudström and Martinn Svensson and Martin Svensson and Rickard
+	Cöster and Kristina Höök},
+  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{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},
+  comment = {- history, algorithm, description of two bounds},
+  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{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}
+}
+
+@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},
+  isbn = {978-1-60558-566-6},
+  location = {Krak\'{o}w, Poland},
+  owner = {chris},
+  pdf = {Wang2009.pdf},
+  timestamp = {2009.12.03}
+}
+
+@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},
+  owner = {chris},
+  timestamp = {2009.12.03}
+}
+
+@comment{jabref-meta: selector_publisher:}
+
+@comment{jabref-meta: selector_author:}
+
+@comment{jabref-meta: selector_journal:}
+
+@comment{jabref-meta: selector_keywords:}
+