The STAGA-Dataset: Stop and Trip Annotated GPS and Accelerometer Data of Everyday Life
This is a modal window.
The media could not be loaded, either because the server or network failed or because the format is not supported.
Formal Metadata
Title |
| |
Title of Series | ||
Number of Parts | 351 | |
Author | ||
Contributors | ||
License | CC Attribution 3.0 Unported: You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor. | |
Identifiers | 10.5446/68907 (DOI) | |
Publisher | ||
Release Date | ||
Language | ||
Production Year | 2022 |
Content Metadata
Subject Area | ||
Genre | ||
Abstract |
| |
Keywords |
FOSS4G Firenze 2022335 / 351
1
7
13
22
25
31
33
36
39
41
43
44
46
52
53
55
58
59
60
76
80
93
98
104
108
127
128
133
135
141
142
143
150
151
168
173
176
178
190
196
200
201
202
204
211
219
225
226
236
242
251
258
263
270
284
285
292
00:00
UsabilityAlgorithmNegative numberFrequencyRaw image formatSampling (statistics)XMLUML
00:13
TrajectoryMultiplication signSampling (statistics)Group actionFrequencyIdentical particlesTrajectoryUsabilitySet (mathematics)Video gameSampling (statistics)Position operator
01:22
Video trackingTrailMobile appNegative numberSource codePhysicalismOpen source
01:47
SmartphoneVideo trackingIndependence (probability theory)TimestampMultiplication signMobile appRight angleData storage deviceNegative numberComputer animation
03:08
Row (database)Sampling (statistics)PlotterMultiplication signSet (mathematics)FrequencyIntegrated development environment
03:26
AverageSample (statistics)MedianInformationVideo gameOpen setSoftware frameworkMultiplication signQR codeSampling (statistics)Set (mathematics)Computer animation
Transcript: English(auto-generated)
00:00
Thank you very much. Tomorrow I'll tell you about how I ended up eventually developing an algorithm for detecting stop and trip periods in raw position data like GPS samples. Basically, I wanted to go from this to this. Therefore, I was looking for an annotated trajectory data set but with clear labels
00:21
indicating if one sample was recorded during a period of dwelling at a position stopping or during a time of transit between moving between two places from from one to another. We found, of course, plenty of openly available data sets but none of these contained any stop or trip labels to distinguish periods from
00:44
dwell or transit. Today I'll present to you our solution to this problem, a new publicly available data set of GPS samples including precise stop and trip annotations. My name is Robert Spang, researcher at the Quality and Usability Lab of Technical University of Berlin and our main goal here was to create a
01:02
new data set containing plain everyday life, containing all the relevant aspects from working, traveling, periods of vacation, everything that general basic people do all the time but with a precise labeled annotations for each and every sample if that was a trip or if that was a stop. To record this
01:23
data set we modified the micro logger open source app so it also recorded accelerometer data and put it into the pockets of our data donors. The app continuously recorded position data and physical motion of this tracking device and other than that participants were instructed to interact with the
01:42
phone as little as possible only charged overnight and bring it along the next day. To obtain annotations we developed a little companion app and while our participants recorded position data out of their pockets they manually labeled stops with the second app at the same time. This companion app is really
02:01
really simple it offers mostly only a single button to begin or end the logging of being at a place. Participants were instructed to press this button once as soon as they arrive at the place and press it again as soon as they leave it. For example imagine riding your bike to an ex-grocery store as soon as you get off the bike to lock it you would first
02:21
indicate that you are arrived have arrived at a place and then you lock your bike go inside do your shopping pack everything together and unlock your bike again and just before you're really getting off that place you would indicate leaving really that stop. This way annotations captured the
02:41
general larger concept of a place and an entity that you believe is a connected spot rather than distinguishing between the bicycle rack and the shop entrance because that's kind of out of scope for our purpose. Participants were instructed to record every stop that they believe would last longer than one minute. This should ensure that we not accidentally capture waiting at the
03:02
traffic lights but really capture all the places that are meaningful to them. All in all we captured 126 consecutive days of movement through mostly urban but also rural environments and this is an exemplary plot of the actual recorded GPS samples over their time period. The data
03:21
set contains over 120,000 GPS samples and over 7.8 million accelerometer samples. The movement diary captured at the same time includes 692 stops at the same time that's mostly around about 5.5 stops per day. You can use this QR code to scan it right now to get to the data
03:42
set and you'll also find a reference to the paper it's going more into detail about how, why and what we done in detail but the most important thing to remember is now there is a large stop and trip annotated data set so the next time you think that come in handy check out our StagR dataset. Thank you very much.