|
@@ -0,0 +1,862 @@
|
|
1
|
+% This file was created with JabRef 2.3.1.
|
|
2
|
+% Encoding: UTF-8
|
|
3
|
+
|
|
4
|
+@INPROCEEDINGS{Liao2007a,
|
|
5
|
+ author = {Lin Liao and Tanzeem Choudhury and Dieter Fox and Henry A. Kautz},
|
|
6
|
+ title = {Training Conditional Random Fields Using Virtual Evidence Boosting},
|
|
7
|
+ booktitle = {IJCAI},
|
|
8
|
+ year = {2007},
|
|
9
|
+ pages = {2530-2535},
|
|
10
|
+ bibsource = {DBLP, http://dblp.uni-trier.de},
|
|
11
|
+ crossref = {DBLP:conf/ijcai/2007},
|
|
12
|
+ ee = {http://dli.iiit.ac.in/ijcai/IJCAI-2007/PDF/IJCAI07-407.pdf},
|
|
13
|
+ file = {Liao2007a.pdf:Liao2007a.pdf:PDF},
|
|
14
|
+ owner = {chris},
|
|
15
|
+ timestamp = {2009.12.03}
|
|
16
|
+}
|
|
17
|
+
|
|
18
|
+@INPROCEEDINGS{Mahdaviani2007,
|
|
19
|
+ author = {Maryam Mahdaviani and Tanzeem Choudhury},
|
|
20
|
+ title = {Fast and Scalable Training of Semi-Supervised CRFs with Application
|
|
21
|
+ to Activity Recognition},
|
|
22
|
+ booktitle = {NIPS},
|
|
23
|
+ year = {2007},
|
|
24
|
+ bibsource = {DBLP, http://dblp.uni-trier.de},
|
|
25
|
+ crossref = {DBLP:conf/nips/2007},
|
|
26
|
+ ee = {http://books.nips.cc/papers/files/nips20/NIPS2007_0863.pdf},
|
|
27
|
+ file = {Mahdaviani2007.pdf:Mahdaviani2007.pdf:PDF},
|
|
28
|
+ owner = {chris},
|
|
29
|
+ timestamp = {2009.12.03}
|
|
30
|
+}
|
|
31
|
+
|
|
32
|
+@MISC{Abowd1997,
|
|
33
|
+ author = {Gregory D. Abowd and Christopher G. Atkeson and Jason Hong and Sue
|
|
34
|
+ Long and Rob Kooper},
|
|
35
|
+ title = {Cyberguide: A Mobile Context-Aware Tour Guide},
|
|
36
|
+ year = {1997},
|
|
37
|
+ citeseercitationcount = {0},
|
|
38
|
+ citeseerurl = {http://citeseer.ist.psu.edu/36540.html},
|
|
39
|
+ file = {Abowd1997.pdf:Abowd1997.pdf:PDF},
|
|
40
|
+ owner = {chris},
|
|
41
|
+ pdf = {Abowd1997.pdf},
|
|
42
|
+ timestamp = {2009.12.01}
|
|
43
|
+}
|
|
44
|
+
|
|
45
|
+@ARTICLE{Bannach2008,
|
|
46
|
+ author = {Bannach, D. and Lukowicz, P. and Amft, O.},
|
|
47
|
+ title = {Rapid Prototyping of Activity Recognition Applications},
|
|
48
|
+ journal = IEEE_M_PVC,
|
|
49
|
+ year = {2008},
|
|
50
|
+ volume = {7},
|
|
51
|
+ pages = {22--31},
|
|
52
|
+ number = {2},
|
|
53
|
+ month = {April--June },
|
|
54
|
+ comment = {The concept of the CRN Toolbox stems from the observation that most
|
|
55
|
+ activity recognition systems rely on a relatively small set of algorithms.
|
|
56
|
+ These include sliding-window signal partitioning, standard time and
|
|
57
|
+ frequency domain features, classifiers, and time series or event-based
|
|
58
|
+ modeling algorithms.},
|
|
59
|
+ doi = {10.1109/MPRV.2008.36},
|
|
60
|
+ file = {Bannach2008.pdf:Bannach2008.pdf:PDF},
|
|
61
|
+ owner = {chris},
|
|
62
|
+ pdf = {Bannach2008.pdf},
|
|
63
|
+ timestamp = {2009.12.01}
|
|
64
|
+}
|
|
65
|
+
|
|
66
|
+@ARTICLE{Bellavista2008,
|
|
67
|
+ author = {Bellavista, P. and Kupper, A. and Helal, S.},
|
|
68
|
+ title = {Location-Based Services: Back to the Future},
|
|
69
|
+ journal = IEEE_M_PVC,
|
|
70
|
+ year = {2008},
|
|
71
|
+ volume = {7},
|
|
72
|
+ pages = {85--89},
|
|
73
|
+ number = {2},
|
|
74
|
+ month = {April--June },
|
|
75
|
+ doi = {10.1109/MPRV.2008.34},
|
|
76
|
+ file = {Bellavista2008.pdf:Bellavista2008.pdf:PDF},
|
|
77
|
+ owner = {chris},
|
|
78
|
+ timestamp = {2009.12.01}
|
|
79
|
+}
|
|
80
|
+
|
|
81
|
+@INPROCEEDINGS{Bellotti2008,
|
|
82
|
+ author = {Bellotti, Victoria and Begole, Bo and Chi, Ed H. and Ducheneaut,
|
|
83
|
+ Nicolas and Fang, Ji and Isaacs, Ellen and King, Tracy and Newman,
|
|
84
|
+ Mark W. and Partridge, Kurt and Price, Bob and Rasmussen, Paul and
|
|
85
|
+ Roberts, Michael and Schiano, Diane J. and Walendowski, Alan},
|
|
86
|
+ title = {Activity-based serendipitous recommendations with the Magitti mobile
|
|
87
|
+ leisure guide},
|
|
88
|
+ booktitle = {CHI '08: Proceeding of the twenty-sixth annual SIGCHI conference
|
|
89
|
+ on Human factors in computing systems},
|
|
90
|
+ year = {2008},
|
|
91
|
+ pages = {1157--1166},
|
|
92
|
+ address = {New York, NY, USA},
|
|
93
|
+ publisher = {ACM},
|
|
94
|
+ citeulike-article-id = {2859755},
|
|
95
|
+ citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1357237},
|
|
96
|
+ citeulike-linkout-1 = {http://dx.doi.org/10.1145/1357054.1357237},
|
|
97
|
+ doi = {10.1145/1357054.1357237},
|
|
98
|
+ isbn = {9781605580111},
|
|
99
|
+ keywords = {ibm, iphone, triage},
|
|
100
|
+ owner = {chris},
|
|
101
|
+ posted-at = {2008-06-03 19:57:41},
|
|
102
|
+ priority = {5},
|
|
103
|
+ timestamp = {2009.12.03},
|
|
104
|
+ url = {http://dx.doi.org/10.1145/1357054.1357237}
|
|
105
|
+}
|
|
106
|
+
|
|
107
|
+@INPROCEEDINGS{Caros2005,
|
|
108
|
+ author = {Carós, JS. and Chételat, O. and Celka, P. and Dasen, S.},
|
|
109
|
+ title = {Very low complexity algorithm for ambulatory activity classification},
|
|
110
|
+ booktitle = {European Medical \& Biological Engineering Conference and IFMBE European
|
|
111
|
+ Conference on Biomedical Engineering},
|
|
112
|
+ year = {2005},
|
|
113
|
+ file = {Caros2005.pdf:Caros2005.pdf:PDF},
|
|
114
|
+ owner = {chris},
|
|
115
|
+ timestamp = {2009.12.01}
|
|
116
|
+}
|
|
117
|
+
|
|
118
|
+@ARTICLE{Choudhury2008,
|
|
119
|
+ author = {Choudhury, T. and Consolvo, S. and Harrison, B. and Hightower, J.
|
|
120
|
+ and LaMarca, A. and LeGrand, L. and Rahimi, A. and Rea, A. and Bordello,
|
|
121
|
+ G. and Hemingway, B. and Klasnja, P. and Koscher, K. and Landay,
|
|
122
|
+ J.A. and Lester, J. and Wyatt, D. and Haehnel, D.},
|
|
123
|
+ title = {The Mobile Sensing Platform: An Embedded Activity Recognition System},
|
|
124
|
+ journal = IEEE_M_PVC,
|
|
125
|
+ year = {2008},
|
|
126
|
+ volume = {7},
|
|
127
|
+ pages = {32--41},
|
|
128
|
+ number = {2},
|
|
129
|
+ month = {April--June },
|
|
130
|
+ comment = {Requirements, general architecture, privacy - audio.
|
|
131
|
+
|
|
132
|
+
|
|
133
|
+ Structured prediction - temporal/structure & activity/context dependencies.
|
|
134
|
+
|
|
135
|
+
|
|
136
|
+ Difficulties with training (labelling large amount of data); semi-supervised
|
|
137
|
+ training},
|
|
138
|
+ doi = {10.1109/MPRV.2008.39},
|
|
139
|
+ file = {Choudhury2008.pdf:Choudhury2008.pdf:PDF},
|
|
140
|
+ owner = {chris},
|
|
141
|
+ timestamp = {2009.12.01}
|
|
142
|
+}
|
|
143
|
+
|
|
144
|
+@ARTICLE{Davies2008,
|
|
145
|
+ author = {Davies, Nigel and Siewiorek, Daniel P. and Sukthankar, Rahul},
|
|
146
|
+ title = {Activity-Based Computing},
|
|
147
|
+ journal = IEEE_M_PVC,
|
|
148
|
+ year = {2008},
|
|
149
|
+ volume = {7},
|
|
150
|
+ pages = {20--21},
|
|
151
|
+ number = {2},
|
|
152
|
+ comment = {General intro and basic history},
|
|
153
|
+ doi = {10.1109/MPRV.2008.26},
|
|
154
|
+ file = {Davies2008.pdf:Davies2008.pdf:PDF},
|
|
155
|
+ issn = {1536-1268},
|
|
156
|
+ keywords = {activity recognition, activity-based computing, context-aware computing},
|
|
157
|
+ owner = {chris},
|
|
158
|
+ pdf = {Davies2008.pdf},
|
|
159
|
+ timestamp = {2009.11.30}
|
|
160
|
+}
|
|
161
|
+
|
|
162
|
+@ARTICLE{Serugendo2008,
|
|
163
|
+ author = {Di Marzo Serugendo, G.},
|
|
164
|
+ title = {Activity-Based Computing},
|
|
165
|
+ journal = IEEE_M_PVC,
|
|
166
|
+ year = {2008},
|
|
167
|
+ volume = {7},
|
|
168
|
+ pages = {58--61},
|
|
169
|
+ number = {2},
|
|
170
|
+ month = {April--June },
|
|
171
|
+ doi = {10.1109/MPRV.2008.25},
|
|
172
|
+ file = {Serugendo2008.pdf:Serugendo2008.pdf:PDF},
|
|
173
|
+ owner = {chris},
|
|
174
|
+ timestamp = {2009.12.01}
|
|
175
|
+}
|
|
176
|
+
|
|
177
|
+@INPROCEEDINGS{Dornbush2005,
|
|
178
|
+ author = {Dornbush, S. and Fisher, K. and McKay, K. and Prikhodko, A. and Segall,
|
|
179
|
+ Z.},
|
|
180
|
+ title = {XPOD - A Human Activity and Emotion Aware Mobile Music Player},
|
|
181
|
+ booktitle = {Proc. 2nd International Conference on Mobile Technology, Applications
|
|
182
|
+ and Systems},
|
|
183
|
+ year = {2005},
|
|
184
|
+ pages = {1--6},
|
|
185
|
+ doi = {10.1109/MTAS.2005.207159},
|
|
186
|
+ file = {Dornbush2005.pdf:Dornbush2005.pdf:PDF},
|
|
187
|
+ keywords = {audio equipment, humanities, mobile handsets, XPod, emotion aware
|
|
188
|
+ mobile music player, human activity, mobile MP3 player, mobile devices,
|
|
189
|
+ mobile phone user experience},
|
|
190
|
+ owner = {chris},
|
|
191
|
+ timestamp = {2009.12.01}
|
|
192
|
+}
|
|
193
|
+
|
|
194
|
+@MISC{Eagle2004,
|
|
195
|
+ author = {Eagle, N. and Pentland, A.},
|
|
196
|
+ title = {Mobile Matchmaking: Proximity Sensing and Cueing},
|
|
197
|
+ year = {2004},
|
|
198
|
+ file = {Eagle2004.pdf:Eagle2004.pdf:PDF},
|
|
199
|
+ journal = {IEEE Pervasive, Special Issue on Smart Phones},
|
|
200
|
+ owner = {chris},
|
|
201
|
+ timestamp = {2009.12.01}
|
|
202
|
+}
|
|
203
|
+
|
|
204
|
+@MISC{Floreen2008,
|
|
205
|
+ author = {Patrik Floréen and Joonas Kukkonen and Eemil Lagerspetz and Petteri
|
|
206
|
+ Nurmi and Jukka Suomela},
|
|
207
|
+ title = {BeTelGeuse: Tool for Context Data Gathering via Bluetooth},
|
|
208
|
+ year = {2008},
|
|
209
|
+ file = {Floreen2008.pdf:Floreen2008.pdf:PDF},
|
|
210
|
+ owner = {chris},
|
|
211
|
+ timestamp = {2009.12.01}
|
|
212
|
+}
|
|
213
|
+
|
|
214
|
+@MASTERSTHESIS{Garakani2009,
|
|
215
|
+ author = {AB Garakani},
|
|
216
|
+ title = {Real-Time Classification of Everyday Fitness Activities on Windows
|
|
217
|
+ Mobile},
|
|
218
|
+ school = {University of Washington},
|
|
219
|
+ year = {2009},
|
|
220
|
+ file = {Garakani2009.pdf:Garakani2009.pdf:PDF},
|
|
221
|
+ owner = {chris},
|
|
222
|
+ timestamp = {2009.12.01}
|
|
223
|
+}
|
|
224
|
+
|
|
225
|
+@MISC{Hein2008,
|
|
226
|
+ author = {Albert Hein and Thomas Kirste},
|
|
227
|
+ title = {Towards Recognizing Abstract Activities: An Unsupervised Approach},
|
|
228
|
+ year = {2008},
|
|
229
|
+ = {http://www.scientificcommons.org/48837277},
|
|
230
|
+ abstract = {Abstract. The recognition of abstract high-level activities using
|
|
231
|
+ wearable sensors is an important prerequisite for context aware mobile
|
|
232
|
+ assistance, especially in AAL and medical care applications. A major
|
|
233
|
+ difficulty in detecting this type of activities is that different
|
|
234
|
+ activities often share similar motion patterns. One possible solution
|
|
235
|
+ is to aggregate these activities from shorter, easier to detect base
|
|
236
|
+ level actions, but the explicit annotation of these is not trivial
|
|
237
|
+ and very time consuming. In this paper we introduce a simple clustering
|
|
238
|
+ based method for the recognition of compound activities at a high
|
|
239
|
+ level of abstraction using k-Means as an unsupervised learning algorithm.
|
|
240
|
+ A general problem of these methods is that the resulting cluster
|
|
241
|
+ affiliations are typically not human readable and some kind of interpretation
|
|
242
|
+ is needed. To achieve this, we developed a hybrid approach using
|
|
243
|
+ a generative probabilistic model built on top of the clusterer. We
|
|
244
|
+ adapted a Hidden Markov Model for mapping the cluster memberships
|
|
245
|
+ onto high-level activities and sucessfully evaluated the feasibility
|
|
246
|
+ of this technique using experimental data from two test runs of a
|
|
247
|
+ home care scenario showing a higher accuracy and robustness than
|
|
248
|
+ conventional discriminative methods.},
|
|
249
|
+ file = {Hein2008.pdf:Hein2008.pdf:PDF},
|
|
250
|
+ institution = {CiteSeerX - Scientific Literature Digital Library and Search Engine
|
|
251
|
+ [http://citeseerx.ist.psu.edu/oai2] (United States)},
|
|
252
|
+ keywords = {High-Level Activities, Clustering, Probabilistic Models, AAL},
|
|
253
|
+ owner = {chris},
|
|
254
|
+ timestamp = {2009.12.01},
|
|
255
|
+ url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.142.6671}
|
|
256
|
+}
|
|
257
|
+
|
|
258
|
+@INPROCEEDINGS{Lee2007,
|
|
259
|
+ author = {Jae Young Lee and Hoff, W.},
|
|
260
|
+ title = {Activity Identification Utilizing Data Mining Techniques},
|
|
261
|
+ booktitle = {Proc. IEEE Workshop on Motion and Video Computing WMVC '07},
|
|
262
|
+ year = {2007},
|
|
263
|
+ pages = {12--12},
|
|
264
|
+ month = {Feb. },
|
|
265
|
+ doi = {10.1109/WMVC.2007.4},
|
|
266
|
+ owner = {chris},
|
|
267
|
+ timestamp = {2009.12.03}
|
|
268
|
+}
|
|
269
|
+
|
|
270
|
+@INPROCEEDINGS{Lester2006,
|
|
271
|
+ author = {Lester, Jonathan and Choudhury, Tanzeem and Borriello, Gaetano},
|
|
272
|
+ title = {A Practical Approach to Recognizing Physical Activities},
|
|
273
|
+ booktitle = {Pervasive Computing},
|
|
274
|
+ year = {2006},
|
|
275
|
+ pages = {1--16},
|
|
276
|
+ = {We are developing a personal activity recognition system that is practical,
|
|
277
|
+ reliable, and can be incorporated into a variety of health-care related
|
|
278
|
+ applications ranging from personal fitness to elder care. To make
|
|
279
|
+ our system appealing and useful, we require it to have the following
|
|
280
|
+ properties: (i) data only from a single body location needed, and
|
|
281
|
+ it is not required to be from the same point for every user; (ii)
|
|
282
|
+ should work out of the box across individuals, with personalization
|
|
283
|
+ only enhancing its recognition abilities; and (iii) should be effective
|
|
284
|
+ even with a cost-sensitive subset of the sensors and data features.
|
|
285
|
+ In this paper, we present an approach to building a system that exhibits
|
|
286
|
+ these properties and provide evidence based on data for 8 different
|
|
287
|
+ activities collected from 12 different subjects. Our results indicate
|
|
288
|
+ that the system has an accuracy rate of approximately 90\% while
|
|
289
|
+ meeting our requirements. We are now developing a fully embedded
|
|
290
|
+ version of our system based on a cell-phone platform augmented with
|
|
291
|
+ a Bluetooth-connected sensor board.},
|
|
292
|
+ citeulike-article-id = {997656},
|
|
293
|
+ citeulike-linkout-0 = {http://dx.doi.org/10.1007/11748625_1},
|
|
294
|
+ citeulike-linkout-1 = {http://www.springerlink.com/content/7048888592382352},
|
|
295
|
+ doi = {10.1007/11748625_1},
|
|
296
|
+ file = {Lester2006.pdf:Lester2006.pdf:PDF},
|
|
297
|
+ journal = {Pervasive Computing},
|
|
298
|
+ keywords = {accelerometer, activity-recognition},
|
|
299
|
+ owner = {chris},
|
|
300
|
+ posted-at = {2007-10-12 10:21:05},
|
|
301
|
+ priority = {2},
|
|
302
|
+ timestamp = {2009.12.03},
|
|
303
|
+ url = {http://dx.doi.org/10.1007/11748625_1}
|
|
304
|
+}
|
|
305
|
+
|
|
306
|
+@ARTICLE{Liao2007,
|
|
307
|
+ author = {Liao, Lin and Fox, Dieter and Kautz, Henry},
|
|
308
|
+ title = {Extracting Places and Activities from GPS Traces Using Hierarchical
|
|
309
|
+ Conditional Random Fields},
|
|
310
|
+ journal = {Int. J. Rob. Res.},
|
|
311
|
+ year = {2007},
|
|
312
|
+ volume = {26},
|
|
313
|
+ pages = {119--134},
|
|
314
|
+ number = {1},
|
|
315
|
+ abstract = {Learning patterns of human behavior from sensor data is extremely
|
|
316
|
+ important for high-level activity inference. This paper describes
|
|
317
|
+ how to extract a person's activities and significant places from
|
|
318
|
+ traces of GPS data. The system uses hierarchically structured conditional
|
|
319
|
+ random fields to generate a consistent model of a person's activities
|
|
320
|
+ and places. In contrast to existing techniques, this approach takes
|
|
321
|
+ the high-level context into account in order to detect the significant
|
|
322
|
+ places of a person. Experiments show significant improvements over
|
|
323
|
+ existing techniques. Furthermore, they indicate that the proposed
|
|
324
|
+ system is able to robustly estimate a person's activities using a
|
|
325
|
+ model that is trained from data collected by other persons.},
|
|
326
|
+ address = {Thousand Oaks, CA, USA},
|
|
327
|
+ citeulike-article-id = {3480910},
|
|
328
|
+ citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1229555.1229562},
|
|
329
|
+ citeulike-linkout-1 = {http://dx.doi.org/10.1177/0278364907073775},
|
|
330
|
+ comment = {NOTE: These notes were supplemented by looking at Liao's dissertation
|
|
331
|
+ writeup of the same work.
|
|
332
|
+
|
|
333
|
+ Overview: This is a supervised learning scheme done in several stages...
|
|
334
|
+ the results from early stages are used to build the structure of
|
|
335
|
+ the model in subsequent stages. Training is done for 3 people, and
|
|
336
|
+ tested on a 4th person. For the test person, only GPS pings are used
|
|
337
|
+ as input.
|
|
338
|
+
|
|
339
|
+ specifics: * GPS traces from 4 people, 6 days per person * \~{}40,000
|
|
340
|
+ GPS measurements per person * manually labeled all activities and
|
|
341
|
+ significant places in these traces * used maximum pseudo-likelihood
|
|
342
|
+ for learning
|
|
343
|
+
|
|
344
|
+ hierarchical graphical model with 3 levels. top level: significant
|
|
345
|
+ places (e.g. home, work, bus stop, parking lot, friend) midlevel:
|
|
346
|
+ activity sequence (eg. walk, drive, visit, sleep, get on bus, pickup),
|
|
347
|
+ bottom level: GPS trace (association to streeet map)
|
|
348
|
+
|
|
349
|
+ * their typical GPS trace consists of approximately one GPS reading
|
|
350
|
+ per second * GPS readings are segmented spatially; we have one activity
|
|
351
|
+ node for each spatial segment of GPS pings ** e.g. a 12 hour stay
|
|
352
|
+ at a single location is represented by a single activity node * if
|
|
353
|
+ street map is available, segmentation is done in association with
|
|
354
|
+ the street map (with 10m discretization) * "model can reason explicitly
|
|
355
|
+ about the duration of a stay, for which dynamic models such as standard
|
|
356
|
+ DBNs or HMMs have only limited support" [12,32]
|
|
357
|
+
|
|
358
|
+ * two main groups of activities: navigation activities, and significant
|
|
359
|
+ activities (in a single place, or at a transportation mode switch)
|
|
360
|
+ * "to determine activities, our model relies heavily on temporal
|
|
361
|
+ features, such as duration or time of day, and geographic information,
|
|
362
|
+ such as locations of restaurants, stores, and bus stops." * "significant
|
|
363
|
+ places are those locations that play a significnat role in the activities
|
|
364
|
+ of a person: hoe, work, bus stops, parking lots typically used, homes
|
|
365
|
+ of friends, etc...) model allows different activites to occur at
|
|
366
|
+ same significant place; also, a significnat place can comprise mutiple
|
|
367
|
+ different locations, mostly because of signal loss and GPS readings
|
|
368
|
+
|
|
369
|
+ The CRF Model for Activity Recognition: 1) CRF for GPS denoising *
|
|
370
|
+ break up street segments into 10 meter patches * measurement clique
|
|
371
|
+ between each ping and all nearby street patches (Gaussian noise model
|
|
372
|
+ from center of patch) * consistency cliques: put a Gaussian noise
|
|
373
|
+ model on the \_difference\_ between the GPS displacement and the
|
|
374
|
+ paired street patch displacement for consecutive pings * smoothness
|
|
375
|
+ cliques: encourage street patch predictions to be stay on the same
|
|
376
|
+ street, going in the same direction their conditional model for street
|
|
377
|
+ patches given GPS pings is given in Eqn 26, bottom of page 10
|
|
378
|
+
|
|
379
|
+ Output of the CRF model is taken as the spatial segmentation of the
|
|
380
|
+ GPS pings... Hierarchical CRF is based on the segmentation, since
|
|
381
|
+ one 'activity sequence' is associated with each sequence of points
|
|
382
|
+ on the same 10m street patch * bottom layer of 3 layer CRF, now it's
|
|
383
|
+ "local evidence" including: ** temporal information (e.g. time od
|
|
384
|
+ day, day of week, duration of stay -- these can be discretized) clique
|
|
385
|
+ functions are all binary indicators, one for every possible combination
|
|
386
|
+ of temporal feature and activity ** average speed through segment
|
|
387
|
+ -- discretized ** information extracted from geographic databses,
|
|
388
|
+ such as whether a patch is on a bus route, close to abus stop, near
|
|
389
|
+ a restaurant or grovery store; use indicator functions to model this
|
|
390
|
+ information ** each activity node connected to its neighbors; e.g.
|
|
391
|
+ extremely unlikely tha ta person will get on bus at one location
|
|
392
|
+ and drive a car at neighboing location right afterwards (?)
|
|
393
|
+
|
|
394
|
+ * Preliminary CRF\_0: just has activity nodes and local evidence nodes
|
|
395
|
+ [notes from thesis] ** adjacent activity nodes are connected, and
|
|
396
|
+ each activity node is connected to each 'ftr' with a pairwise potential
|
|
397
|
+ ** features are *** gps based: streetpatch, timeofday (first timestamp,
|
|
398
|
+ discretized into Moring, Noon, AFternoon, Evening, Night), dayofweek,
|
|
399
|
+ duration, *** geo database: nearrestaurant, nearstore, nearbusstop,
|
|
400
|
+ onbusroute [latter extracted from geographic databaddses] *** average
|
|
401
|
+ speed thru segment (discretized - 'to allow multimodality')
|
|
402
|
+
|
|
403
|
+ * Significant Places [from thesis] ** from the MAP activity sequence,
|
|
404
|
+ they then (by hand? they refer to an IsSignificant() function) associate
|
|
405
|
+ each activity with whether or not it belongs to a significant place
|
|
406
|
+ (e.g. transport does not connect to a significant place, while getting
|
|
407
|
+ on / off a bus does ...); * spatial clustering performed on the locations
|
|
408
|
+ of significant places * the cluster centers are the 'signiciant plces'
|
|
409
|
+ * edge between each place label and each activity label in its vicinity
|
|
410
|
+ * NOTE: the 'place nodes' are not dynamic; we find K lat,longs that
|
|
411
|
+ are the locations of the significant places; what we still ned to
|
|
412
|
+ infer are the labels for these significant places; e.g. several of
|
|
413
|
+ the lat,longs can be 'shopping', or 'friend's house, etc... certain
|
|
414
|
+ place labels are associated with certain types of activities * they
|
|
415
|
+ want to also add features that count the number of 'home', 'workplace',
|
|
416
|
+ etc., labels that are used. However, this requires making a clique
|
|
417
|
+ containing all the places, which can be quite large...
|
|
418
|
+
|
|
419
|
+ generate\_places algorithm: * really not clear -- clustering places
|
|
420
|
+ associated with the same activity? how can you get any confidence
|
|
421
|
+ in the activities?
|
|
422
|
+
|
|
423
|
+ * Each place (node at the top level of 3 level CRF) connects to all
|
|
424
|
+ activities that seem to occur in the same place -- built into the
|
|
425
|
+ structure of the model * multiple activities may occur at the same
|
|
426
|
+ place
|
|
427
|
+
|
|
428
|
+ * each GPS associated with a 10m patch on a street edge * [20] inference
|
|
429
|
+ using loopy belief propagation, and parameter learning using pseudo-likelihoodreferences
|
|
430
|
+ to chase down: bennewitz [4] learn different motion paths between
|
|
431
|
+ places, [23] how to figure out types of places;},
|
|
432
|
+ doi = {10.1177/0278364907073775},
|
|
433
|
+ file = {Liao2007.pdf:Liao2007.pdf:PDF},
|
|
434
|
+ issn = {0278-3649},
|
|
435
|
+ keywords = {activity-prediction, place-finding},
|
|
436
|
+ owner = {chris},
|
|
437
|
+ posted-at = {2008-11-04 21:40:32},
|
|
438
|
+ priority = {2},
|
|
439
|
+ publisher = {Sage Publications, Inc.},
|
|
440
|
+ timestamp = {2009.12.03},
|
|
441
|
+ url = {http://dx.doi.org/10.1177/0278364907073775}
|
|
442
|
+}
|
|
443
|
+
|
|
444
|
+@ARTICLE{Lukowicz2002,
|
|
445
|
+ author = {Lukowicz, P. and Junker, H. and St\"{a}ger, M. and von B\"{u}ren,
|
|
446
|
+ T. and Tr\"{o}ster, G.},
|
|
447
|
+ title = {WearNET: A Distributed Multi-sensor System for Context Aware Wearables},
|
|
448
|
+ journal = {UbiComp 2002: Ubiquitous Computing},
|
|
449
|
+ year = {2002},
|
|
450
|
+ volume = {1},
|
|
451
|
+ pages = {361--370},
|
|
452
|
+ abstract = {This paper describes a distributed, multi-sensor system architecture
|
|
453
|
+ designed to provide a wearable computer with a wide range of complex
|
|
454
|
+ context information. Starting from an analysis of useful high level
|
|
455
|
+ context information we present a top down design that focuses on
|
|
456
|
+ the peculiarities of wearable applications. Thus, our design devotes
|
|
457
|
+ particular attention to sensor placement, system partitioning as
|
|
458
|
+ well as resource requirements given by the power consumption, computational
|
|
459
|
+ intensity and communication overhead. We describe an implementation
|
|
460
|
+ of our architecture and initial experimental results obtained with
|
|
461
|
+ the system.},
|
|
462
|
+ citeulike-article-id = {3909016},
|
|
463
|
+ citeulike-linkout-0 = {http://dx.doi.org/10.1007/3-540-45809-3_28},
|
|
464
|
+ citeulike-linkout-1 = {http://www.springerlink.com/content/kky208rx9e98m0xg},
|
|
465
|
+ doi = {10.1007/3-540-45809-3_28},
|
|
466
|
+ file = {Lukowicz2002.pdf:Lukowicz2002.pdf:PDF},
|
|
467
|
+ keywords = {action, sensors},
|
|
468
|
+ owner = {chris},
|
|
469
|
+ posted-at = {2009-01-19 18:25:29},
|
|
470
|
+ priority = {5},
|
|
471
|
+ timestamp = {2009.12.03},
|
|
472
|
+ url = {http://dx.doi.org/10.1007/3-540-45809-3_28}
|
|
473
|
+}
|
|
474
|
+
|
|
475
|
+@INPROCEEDINGS{Maurer2006,
|
|
476
|
+ author = {Maurer, U. and Rowe, A. and Smailagic, A. and Siewiorek, D.P.},
|
|
477
|
+ title = {eWatch: a wearable sensor and notification platform},
|
|
478
|
+ booktitle = {Proc. International Workshop on Wearable and Implantable Body Sensor
|
|
479
|
+ Networks BSN 2006},
|
|
480
|
+ year = {2006},
|
|
481
|
+ pages = {4 pp.--145},
|
|
482
|
+ doi = {10.1109/BSN.2006.24},
|
|
483
|
+ file = {Maurer2006.pdf:Maurer2006.pdf:PDF},
|
|
484
|
+ keywords = {Bluetooth, biomedical equipment, electric sensing devices, patient
|
|
485
|
+ monitoring, watches, wearable computers, Bluetooth communication,
|
|
486
|
+ eWatch platform, notification platform, online nearest neighbor classification,
|
|
487
|
+ power aware hardware, software architecture, wearable computing platform,
|
|
488
|
+ wearable sensors, wireless links, wrist watch form factor},
|
|
489
|
+ owner = {chris},
|
|
490
|
+ timestamp = {2009.12.03}
|
|
491
|
+}
|
|
492
|
+
|
|
493
|
+@MISC{Miluzzo2009,
|
|
494
|
+ author = {Miluzzo, E., and Oakley, J., and Lu, H., and Lane, N., and Peterson,
|
|
495
|
+ R., and Campbell, A.},
|
|
496
|
+ title = {Evaluating the iPhone as a Mobile Platform for People-Centric Sensing
|
|
497
|
+ Applications},
|
|
498
|
+ year = {2009},
|
|
499
|
+ file = {Miluzzo2009.pdf:Miluzzo2009.pdf:PDF},
|
|
500
|
+ owner = {chris},
|
|
501
|
+ timestamp = {2009.12.01}
|
|
502
|
+}
|
|
503
|
+
|
|
504
|
+@INPROCEEDINGS{Nicolai2006,
|
|
505
|
+ author = {Tom Nicolai and Nils Behrens and Holger Kenn},
|
|
506
|
+ title = {Exploring Social Context with the Wireless Rope},
|
|
507
|
+ booktitle = {In Proc. Workshop MONET: LNCS 4277},
|
|
508
|
+ year = {2006},
|
|
509
|
+ file = {Nicolai2006.pdf:Nicolai2006.pdf:PDF},
|
|
510
|
+ owner = {chris},
|
|
511
|
+ timestamp = {2009.12.01}
|
|
512
|
+}
|
|
513
|
+
|
|
514
|
+@ARTICLE{Parkka2006,
|
|
515
|
+ author = {Parkka, J. and Ermes, M. and Korpipaa, P. and Mantyjarvi, J. and
|
|
516
|
+ Peltola, J. and Korhonen, I.},
|
|
517
|
+ title = {Activity classification using realistic data from wearable sensors},
|
|
518
|
+ journal = {Information Technology in Biomedicine, IEEE Transactions on},
|
|
519
|
+ year = {2006},
|
|
520
|
+ volume = {10},
|
|
521
|
+ pages = {119--128},
|
|
522
|
+ number = {1},
|
|
523
|
+ abstract = {Automatic classification of everyday activities can be used for promotion
|
|
524
|
+ of health-enhancing physical activities and a healthier lifestyle.
|
|
525
|
+ In this paper, methods used for classification of everyday activities
|
|
526
|
+ like walking, running, and cycling are described. The aim of the
|
|
527
|
+ study was to find out how to recognize activities, which sensors
|
|
528
|
+ are useful and what kind of signal processing and classification
|
|
529
|
+ is required. A large and realistic data library of sensor data was
|
|
530
|
+ collected. Sixteen test persons took part in the data collection,
|
|
531
|
+ resulting in approximately 31 h of annotated, 35-channel data recorded
|
|
532
|
+ in an everyday environment. The test persons carried a set of wearable
|
|
533
|
+ sensors while performing several activities during the 2-h measurement
|
|
534
|
+ session. Classification results of three classifiers are shown: custom
|
|
535
|
+ decision tree, automatically generated decision tree, and artificial
|
|
536
|
+ neural network. The classification accuracies using leave-one-subject-out
|
|
537
|
+ cross validation range from 58 to 97\% for custom decision tree classifier,
|
|
538
|
+ from 56 to 97\% for automatically generated decision tree, and from
|
|
539
|
+ 22 to 96\% for artificial neural network. Total classification accuracy
|
|
540
|
+ is 82\% for custom decision tree classifier, 86\% for automatically
|
|
541
|
+ generated decision tree, and 82\% for artificial neural network.},
|
|
542
|
+ booktitle = {Information Technology in Biomedicine, IEEE Transactions on},
|
|
543
|
+ citeulike-article-id = {3759728},
|
|
544
|
+ citeulike-linkout-0 = {http://dx.doi.org/10.1109/TITB.2005.856863},
|
|
545
|
+ citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1573714},
|
|
546
|
+ citeulike-linkout-2 = {http://dx.doi.org/http://dx.doi.org/10.1109/TITB.2005.856863},
|
|
547
|
+ citeulike-linkout-3 = {http://dx.doi.org/10.1109/TITB.2005.856863},
|
|
548
|
+ doi = {10.1109/TITB.2005.856863},
|
|
549
|
+ keywords = {activity, coact, health, walton, wearable},
|
|
550
|
+ owner = {chris},
|
|
551
|
+ pdf = {Parkka2006.pdf},
|
|
552
|
+ posted-at = {2008-12-09 14:55:55},
|
|
553
|
+ priority = {2},
|
|
554
|
+ timestamp = {2009.12.03},
|
|
555
|
+ url = {http://dx.doi.org/10.1109/TITB.2005.856863}
|
|
556
|
+}
|
|
557
|
+
|
|
558
|
+@MISC{Patterson2004,
|
|
559
|
+ author = {Donald J. Patterson and Dieter Fox and Henry Kautz and Kenneth Fishkin
|
|
560
|
+ and Mike Perkowitz and Matthai Philipose},
|
|
561
|
+ title = {Contextual Computer Support for Human Activity},
|
|
562
|
+ year = {2004},
|
|
563
|
+ citeseercitationcount = {0},
|
|
564
|
+ citeseerurl = {http://citeseer.ist.psu.edu/635960.html},
|
|
565
|
+ file = {Patterson2004.pdf:Patterson2004.pdf:PDF},
|
|
566
|
+ owner = {chris},
|
|
567
|
+ timestamp = {2009.12.01}
|
|
568
|
+}
|
|
569
|
+
|
|
570
|
+@MISC{Philipose2003,
|
|
571
|
+ author = {Matthai Philipose and Sunny Consolvo and Kenneth Fishkin and Perkowitz
|
|
572
|
+ Ian Smith},
|
|
573
|
+ title = {Fast, Detailed Inference of Diverse Daily Human Activities},
|
|
574
|
+ year = {2003},
|
|
575
|
+ file = {Philipose2003.pdf:Philipose2003.pdf:PDF},
|
|
576
|
+ owner = {chris},
|
|
577
|
+ timestamp = {2009.12.01}
|
|
578
|
+}
|
|
579
|
+
|
|
580
|
+@ARTICLE{Philipose2004,
|
|
581
|
+ author = {Philipose, M. and Fishkin, K.P. and Perkowitz, M. and Patterson,
|
|
582
|
+ D.J. and Fox, D. and Kautz, H. and Hahnel, D.},
|
|
583
|
+ title = {Inferring activities from interactions with objects},
|
|
584
|
+ journal = IEEE_M_PVC,
|
|
585
|
+ year = {2004},
|
|
586
|
+ volume = {3},
|
|
587
|
+ pages = {50--57},
|
|
588
|
+ number = {4},
|
|
589
|
+ doi = {10.1109/MPRV.2004.7},
|
|
590
|
+ file = {Philipose2004.pdf:Philipose2004.pdf:PDF},
|
|
591
|
+ issn = {1536-1268},
|
|
592
|
+ keywords = {computerised monitoring, data mining, home automation, home computing,
|
|
593
|
+ radiofrequency identification, ubiquitous computing, ADL inferencing,
|
|
594
|
+ ADL monitoring, Proactive Activity Toolkit, daily living activity
|
|
595
|
+ recognition, daily living activity recording, data mining, elder
|
|
596
|
+ care, pervasive computing, probabilistic inference engine, radio-frequency-identification
|
|
597
|
+ technology, ADL monitoring, Proact, Proactive Activity Toolkit, context-aware
|
|
598
|
+ computing, sensor networks},
|
|
599
|
+ owner = {chris},
|
|
600
|
+ timestamp = {2009.12.01}
|
|
601
|
+}
|
|
602
|
+
|
|
603
|
+@MISC{Philipose2003a,
|
|
604
|
+ author = {Philipose, M. and Fishkin, K. and Perkowitz, M. and Patterson, D.
|
|
605
|
+ and Hähnel, D.},
|
|
606
|
+ title = {The Probabilistic Activity Toolkit: Towards Enabling Activity-Aware
|
|
607
|
+ Computer Interfaces},
|
|
608
|
+ year = {2003},
|
|
609
|
+ file = {Philipose2003a.pdf:Philipose2003a.pdf:PDF},
|
|
610
|
+ owner = {chris},
|
|
611
|
+ timestamp = {2009.12.01}
|
|
612
|
+}
|
|
613
|
+
|
|
614
|
+@ARTICLE{Reynolds2008,
|
|
615
|
+ author = {Reynolds, F.},
|
|
616
|
+ title = {Camera Phones: A Snapshot of Research and Applications},
|
|
617
|
+ journal = IEEE_M_PVC,
|
|
618
|
+ year = {2008},
|
|
619
|
+ volume = {7},
|
|
620
|
+ pages = {16--19},
|
|
621
|
+ number = {2},
|
|
622
|
+ month = {April--June },
|
|
623
|
+ comment = {"over one billion camera phones were sold last year"},
|
|
624
|
+ doi = {10.1109/MPRV.2008.28},
|
|
625
|
+ file = {Reynolds2008.pdf:Reynolds2008.pdf:PDF},
|
|
626
|
+ owner = {chris},
|
|
627
|
+ pdf = {Reynolds2008.pdf},
|
|
628
|
+ timestamp = {2009.12.01}
|
|
629
|
+}
|
|
630
|
+
|
|
631
|
+@INPROCEEDINGS{Rudstroem2004,
|
|
632
|
+ author = {Åsa Rudström and Martinn Svensson and Martin Svensson and Rickard
|
|
633
|
+ Cöster and Kristina Höök},
|
|
634
|
+ title = {MobiTip: Using Bluetooth as a Mediator of Social Context},
|
|
635
|
+ booktitle = {In Ubicomp 2004 Adjunct Proceedings},
|
|
636
|
+ year = {2004},
|
|
637
|
+ file = {Rudstroem2004.pdf:Rudstroem2004.pdf:PDF},
|
|
638
|
+ owner = {chris},
|
|
639
|
+ timestamp = {2009.12.01}
|
|
640
|
+}
|
|
641
|
+
|
|
642
|
+@MISC{Schapire1999,
|
|
643
|
+ author = {Schapire, Robert E.},
|
|
644
|
+ title = {A Brief Introduction to Boosting},
|
|
645
|
+ year = {1999},
|
|
646
|
+ abstract = {Boosting is a general method for improving the accuracy of any given
|
|
647
|
+ learning algorithm. This short paper introduces the boosting algorithm
|
|
648
|
+ AdaBoost, and explains the underlying theory of boosting, including
|
|
649
|
+ an explanation of why boosting often does not suffer from overfitting.
|
|
650
|
+ Some examples of recent applications of boosting are also described.
|
|
651
|
+ Background Boosting is a general method which attempts to \&\#034;boost\&\#034;
|
|
652
|
+ the accuracy of any given learning algorithm. Boosting has its roots
|
|
653
|
+ in a theoretical framework for studying machine learning called the
|
|
654
|
+ \&\#034;PAC\&\#034; learning model, due to Valiant [37]; see Kearns
|
|
655
|
+ and Vazirani [24] for a good introduction to this model. Kearns and
|
|
656
|
+ Valiant [22, 23] were the first to pose the question of whether a
|
|
657
|
+ \&\#034;weak\&\#034; learning algorithm which performs just slightly
|
|
658
|
+ better than random guessing in the PAC model can be \&\#034;boosted\&\#034;
|
|
659
|
+ into an arbitrarily accurate \&\#034;strong\&\#034; learning algorithm.
|
|
660
|
+ Schapire [30] came up with the first provable polynomial-time boosting
|
|
661
|
+ algorithm in ...},
|
|
662
|
+ citeulike-article-id = {6212085},
|
|
663
|
+ citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.7.8772},
|
|
664
|
+ comment = {- history, algorithm, description of two bounds},
|
|
665
|
+ file = {Schapire1999.pdf:Schapire1999.pdf:PDF},
|
|
666
|
+ keywords = {boosting},
|
|
667
|
+ owner = {chris},
|
|
668
|
+ posted-at = {2009-11-25 20:48:42},
|
|
669
|
+ priority = {2},
|
|
670
|
+ timestamp = {2009.12.03},
|
|
671
|
+ url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.7.8772}
|
|
672
|
+}
|
|
673
|
+
|
|
674
|
+@MISC{Schilit1994,
|
|
675
|
+ author = {Bill Schilit and Norman Adams and Roy Want},
|
|
676
|
+ title = {Context-Aware Computing Applications},
|
|
677
|
+ year = {1994},
|
|
678
|
+ citeseercitationcount = {0},
|
|
679
|
+ citeseerurl = {http://citeseer.ist.psu.edu/339782.html},
|
|
680
|
+ file = {Schilit1994.pdf:Schilit1994.pdf:PDF},
|
|
681
|
+ owner = {chris},
|
|
682
|
+ timestamp = {2009.12.01}
|
|
683
|
+}
|
|
684
|
+
|
|
685
|
+@MISC{Schmidt2008,
|
|
686
|
+ author = {Albrecht Schmidt and Kofi Asante Aidoo and Antti Takaluoma and Urpo
|
|
687
|
+ Tuomela and Kristof Van Laerhoven and Walter Van de Velde},
|
|
688
|
+ title = {iLearn on the iPhone: Real-Time Human Activity Classification on
|
|
689
|
+ Commodity Mobile Phones},
|
|
690
|
+ year = {2008},
|
|
691
|
+ file = {Schmidt2008.pdf:Schmidt2008.pdf:PDF},
|
|
692
|
+ owner = {chris},
|
|
693
|
+ timestamp = {2009.12.03}
|
|
694
|
+}
|
|
695
|
+
|
|
696
|
+@ARTICLE{Schmidt1999,
|
|
697
|
+ author = {Schmidt, A. and Aidoo, K. A. and Takaluoma, A. and Tuomela, U. and
|
|
698
|
+ Van Laerhoven, K. and Van de Velde, W.},
|
|
699
|
+ title = {Advanced Interaction in Context},
|
|
700
|
+ journal = {Lecture Notes in Computer Science},
|
|
701
|
+ year = {1999},
|
|
702
|
+ volume = {1707},
|
|
703
|
+ pages = {89--??},
|
|
704
|
+ abstract = {. Mobile information appliances are increasingly used in numerous
|
|
705
|
+
|
|
706
|
+ different situations and locations, setting new requirements to their
|
|
707
|
+ interaction
|
|
708
|
+
|
|
709
|
+ methods. When the user's situation, place or activity changes, the
|
|
710
|
+ functionality
|
|
711
|
+
|
|
712
|
+ of the device should adapt to these changes. In this work we propose
|
|
713
|
+ a layered
|
|
714
|
+
|
|
715
|
+ real-time architecture for this kind of context-aware adaptation based
|
|
716
|
+ on
|
|
717
|
+
|
|
718
|
+ redundant collections of low-level sensors. Two kinds of sensors are
|
|
719
|
+
|
|
720
|
+ distinguished: physical and logical...},
|
|
721
|
+ citeulike-article-id = {1284635},
|
|
722
|
+ citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.40.2408},
|
|
723
|
+ file = {Schmidt1999.pdf:Schmidt1999.pdf:PDF},
|
|
724
|
+ keywords = {context, mobile, pervasive, ubicomp},
|
|
725
|
+ owner = {chris},
|
|
726
|
+ posted-at = {2007-05-09 07:15:21},
|
|
727
|
+ priority = {4},
|
|
728
|
+ timestamp = {2009.12.03},
|
|
729
|
+ url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.40.2408}
|
|
730
|
+}
|
|
731
|
+
|
|
732
|
+@MISC{Shen2004,
|
|
733
|
+ author = {Jianqiang Shen},
|
|
734
|
+ title = {Machine Learning for Activity Recognition},
|
|
735
|
+ year = {2004},
|
|
736
|
+ file = {Shen2004.pdf:Shen2004.pdf:PDF},
|
|
737
|
+ owner = {chris},
|
|
738
|
+ timestamp = {2009.12.01}
|
|
739
|
+}
|
|
740
|
+
|
|
741
|
+@INPROCEEDINGS{Song2005,
|
|
742
|
+ author = {Song, K. and Wang, Y.},
|
|
743
|
+ title = {Remote Activity Monitoring of the Elderly Using a Two-Axis Accelerometer},
|
|
744
|
+ booktitle = {CACS Automatic Control Conference},
|
|
745
|
+ year = {2005},
|
|
746
|
+ file = {Song2005.pdf:Song2005.pdf:PDF},
|
|
747
|
+ owner = {chris},
|
|
748
|
+ timestamp = {2009.12.01}
|
|
749
|
+}
|
|
750
|
+
|
|
751
|
+@ARTICLE{Stiefmeier2008,
|
|
752
|
+ author = {Stiefmeier, T. and Roggen, D. and Troster, G. and Ogris, G. and Lukowicz,
|
|
753
|
+ P.},
|
|
754
|
+ title = {Wearable Activity Tracking in Car Manufacturing},
|
|
755
|
+ journal = IEEE_M_PVC,
|
|
756
|
+ year = {2008},
|
|
757
|
+ volume = {7},
|
|
758
|
+ pages = {42--50},
|
|
759
|
+ number = {2},
|
|
760
|
+ month = {April--June },
|
|
761
|
+ doi = {10.1109/MPRV.2008.40},
|
|
762
|
+ file = {Stiefmeier2008.pdf:Stiefmeier2008.pdf:PDF},
|
|
763
|
+ owner = {chris},
|
|
764
|
+ timestamp = {2009.12.01}
|
|
765
|
+}
|
|
766
|
+
|
|
767
|
+@ARTICLE{Tentori2008,
|
|
768
|
+ author = {Tentori, M. and Favela, J.},
|
|
769
|
+ title = {Activity-Aware Computing for Healthcare},
|
|
770
|
+ journal = IEEE_M_PVC,
|
|
771
|
+ year = {2008},
|
|
772
|
+ volume = {7},
|
|
773
|
+ pages = {51--57},
|
|
774
|
+ number = {2},
|
|
775
|
+ month = {April--June },
|
|
776
|
+ doi = {10.1109/MPRV.2008.24},
|
|
777
|
+ file = {Tentori2008.pdf:Tentori2008.pdf:PDF},
|
|
778
|
+ owner = {chris},
|
|
779
|
+ timestamp = {2009.12.01}
|
|
780
|
+}
|
|
781
|
+
|
|
782
|
+@ARTICLE{Voida2002,
|
|
783
|
+ author = {Voida, S. and Mynatt, E.D. and MacIntyre, B. and Corso, G.M.},
|
|
784
|
+ title = {Integrating virtual and physical context to support knowledge workers},
|
|
785
|
+ journal = IEEE_M_PVC,
|
|
786
|
+ year = {2002},
|
|
787
|
+ volume = {1},
|
|
788
|
+ pages = {73--79},
|
|
789
|
+ number = {3},
|
|
790
|
+ doi = {10.1109/MPRV.2002.1037725},
|
|
791
|
+ file = {Voida2002.pdf:Voida2002.pdf:PDF},
|
|
792
|
+ issn = {1536-1268},
|
|
793
|
+ keywords = {distributed processing, groupware, management information systems,
|
|
794
|
+ user interfaces, Kimura system, data sources, electronic whiteboard,
|
|
795
|
+ knowledge workers, networked peripheral devices, pervasive computing},
|
|
796
|
+ owner = {chris},
|
|
797
|
+ timestamp = {2009.12.01}
|
|
798
|
+}
|
|
799
|
+
|
|
800
|
+@INPROCEEDINGS{Wang2009,
|
|
801
|
+ author = {Wang, Yi and Lin, Jialiu and Annavaram, Murali and Jacobson, Quinn
|
|
802
|
+ A. and Hong, Jason and Krishnamachari, Bhaskar and Sadeh, Norman},
|
|
803
|
+ title = {A framework of energy efficient mobile sensing for automatic user
|
|
804
|
+ state recognition},
|
|
805
|
+ booktitle = {MobiSys '09: Proceedings of the 7th international conference on Mobile
|
|
806
|
+ systems, applications, and services},
|
|
807
|
+ year = {2009},
|
|
808
|
+ pages = {179--192},
|
|
809
|
+ address = {New York, NY, USA},
|
|
810
|
+ publisher = {ACM},
|
|
811
|
+ doi = {http://doi.acm.org/10.1145/1555816.1555835},
|
|
812
|
+ file = {Wang2009.pdf:Wang2009.pdf:PDF},
|
|
813
|
+ isbn = {978-1-60558-566-6},
|
|
814
|
+ location = {Krak\'{o}w, Poland},
|
|
815
|
+ owner = {chris},
|
|
816
|
+ pdf = {Wang2009.pdf},
|
|
817
|
+ timestamp = {2009.12.03}
|
|
818
|
+}
|
|
819
|
+
|
|
820
|
+@INPROCEEDINGS{Wyatt2007,
|
|
821
|
+ author = {Wyatt, D. and Choudhury, T. and Kautz, H.},
|
|
822
|
+ title = {Capturing Spontaneous Conversation and Social Dynamics: A Privacy-Sensitive
|
|
823
|
+ Data Collection Effort},
|
|
824
|
+ booktitle = {Proc. IEEE International Conference on Acoustics, Speech and Signal
|
|
825
|
+ Processing ICASSP 2007},
|
|
826
|
+ year = {2007},
|
|
827
|
+ volume = {4},
|
|
828
|
+ pages = {IV-213--IV-216},
|
|
829
|
+ doi = {10.1109/ICASSP.2007.367201},
|
|
830
|
+ file = {Wyatt2007.pdf:Wyatt2007.pdf:PDF},
|
|
831
|
+ issn = {1520-6149},
|
|
832
|
+ keywords = {data acquisition, speech intelligibility, UW dynamic social network,
|
|
833
|
+ paralinguistic features, privacy constraints, privacy-sensitive data
|
|
834
|
+ collection effort, prosodic features, social dynamics, spontaneous
|
|
835
|
+ conversation, spontaneous face-to-face conversations, Data acquisition,
|
|
836
|
+ oral communication, privacy, speech analysis},
|
|
837
|
+ owner = {chris},
|
|
838
|
+ timestamp = {2009.12.03}
|
|
839
|
+}
|
|
840
|
+
|
|
841
|
+@INPROCEEDINGS{Yang2008,
|
|
842
|
+ author = {Sung-Ihk Yang and Sung-Bae Cho},
|
|
843
|
+ title = {Recognizing human activities from accelerometer and physiological
|
|
844
|
+ sensors},
|
|
845
|
+ booktitle = {Proc. IEEE International Conference on Multisensor Fusion and Integration
|
|
846
|
+ for Intelligent Systems MFI 2008},
|
|
847
|
+ year = {2008},
|
|
848
|
+ pages = {100--105},
|
|
849
|
+ month = {20--22 Aug. },
|
|
850
|
+ doi = {10.1109/MFI.2008.4648116},
|
|
851
|
+ owner = {chris},
|
|
852
|
+ timestamp = {2009.12.03}
|
|
853
|
+}
|
|
854
|
+
|
|
855
|
+@comment{jabref-meta: selector_publisher:}
|
|
856
|
+
|
|
857
|
+@comment{jabref-meta: selector_author:}
|
|
858
|
+
|
|
859
|
+@comment{jabref-meta: selector_journal:}
|
|
860
|
+
|
|
861
|
+@comment{jabref-meta: selector_keywords:}
|
|
862
|
+
|