Deployed 654f6f3c
to dev with MkDocs 1.2.1 and mike 1.0.1
parent
8ced61dcca
commit
c3df19cd8b
|
@ -2029,9 +2029,9 @@
|
|||
<tr>
|
||||
<td>Phone Activity Recognition</td>
|
||||
<td>RAPIDS</td>
|
||||
<td>N</td>
|
||||
<td>N</td>
|
||||
<td>N</td>
|
||||
<td>Y</td>
|
||||
<td>Y</td>
|
||||
<td>Y</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Phone Applications Foreground</td>
|
||||
|
@ -2640,31 +2640,81 @@ When generating test data, all traces for iOS device need to be unique otherwise
|
|||
(i.e. for iPhone) are empty data files.</li>
|
||||
</ul>
|
||||
<h2 id="activity-recognition">Activity Recognition<a class="headerlink" href="#activity-recognition" title="Permanent link">¶</a></h2>
|
||||
<p>Description</p>
|
||||
<ul>
|
||||
<li>The raw Activity Recognition data file contains data for 1 day.</li>
|
||||
<li>The raw Activity Recognition data each <code>epoch</code> period contains
|
||||
rows that records 2 - 5 different <code>activity_types</code>. The is such
|
||||
that durations of activities can be tested. Additionally, there
|
||||
are records that mimic the duration of an activity over the time
|
||||
boundary of neighboring epochs. (For example, there a set of
|
||||
records that mimic the participant <code>in_vehicle</code> from <code>afternoon</code>
|
||||
into <code>evening</code>)</li>
|
||||
<li>There is one file each with raw Activity Recognition data for
|
||||
testing both iOS and Android data formats.
|
||||
(plugin_google_activity_recognition_raw.csv for android and
|
||||
plugin_ios_activity_recognition_raw.csv for iOS)</li>
|
||||
<li>There is also an additional empty data file for both android and
|
||||
iOS for testing empty data files.</li>
|
||||
<li>The 4-day raw conversation data is contained in <code>plugin_google_activity_recognition_raw.csv</code> and <code>plugin_ios_activity_recognition_raw.csv</code>.</li>
|
||||
<li>Two episodes locate in the same 30-min segment (<code>Fri 04:01:54</code> and <code>Fri 04:13:52</code>)</li>
|
||||
<li>One episode for each daily segment (<code>night</code>, <code>morning</code>, <code>afternoon</code> and <code>evening</code>)</li>
|
||||
<li>Two episodes locate in the same daily segment (<code>Fri 05:03:09</code> and <code>Fri 05:50:36</code>)</li>
|
||||
<li>Two episodes with the time difference less than <code>5 mins</code> threshold (<code>Fri 07:14:21</code> and <code>Fri 07:18:50</code>)</li>
|
||||
<li>One episode before the time switch (<code>Sun 00:46:00</code>) and one episode after the time switch (<code>Sun 03:42:00</code>)</li>
|
||||
</ul>
|
||||
<p>Checklist</p>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>time segment</th>
|
||||
<th>single tz</th>
|
||||
<th>multi tz</th>
|
||||
<th>platform</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td>30min</td>
|
||||
<td>OK</td>
|
||||
<td>OK</td>
|
||||
<td>android, iOS</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>morning</td>
|
||||
<td>OK</td>
|
||||
<td>OK</td>
|
||||
<td>android, iOS</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>daily</td>
|
||||
<td>OK</td>
|
||||
<td>OK</td>
|
||||
<td>android, iOS</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>threeday</td>
|
||||
<td>OK</td>
|
||||
<td>OK</td>
|
||||
<td>android, iOS</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>weekend</td>
|
||||
<td>OK</td>
|
||||
<td>OK</td>
|
||||
<td>android, iOS</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>beforeMarchEvent</td>
|
||||
<td>OK</td>
|
||||
<td>OK</td>
|
||||
<td>android, iOS</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>beforeNovemberEvent</td>
|
||||
<td>OK</td>
|
||||
<td>OK</td>
|
||||
<td>android, iOS</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<h2 id="conversation">Conversation<a class="headerlink" href="#conversation" title="Permanent link">¶</a></h2>
|
||||
<p>The 4-day raw conversation data is contained in <code>phone_conversation_raw.csv</code>. The different <code>inference</code> records are
|
||||
randomly distributed throughout the <code>epoch</code>. </p>
|
||||
<p>Description
|
||||
- One episode for each daily segment (<code>night</code>, <code>morning</code>, <code>afternoon</code> and <code>evening</code>) on each day
|
||||
- Two episodes near the transition of the daily segment, one starts at the end of the afternoon, <code>Fri 17:10:00</code> and another one starts at the beginning of the evening, <code>Fri 18:01:00</code>
|
||||
- One episode across two segments, <code>daily</code> and <code>30-mins</code>, (from <code>Fri 05:55:00</code> to <code>Fri 06:00:41</code>)
|
||||
- Two episodes locate in the same daily segment (<code>Sat 12:45:36</code> and <code>Sat 16:48:22</code>)
|
||||
- One episode before the time switch, <code>Sun 00:15:06</code>, and one episode after the time switch, <code>Sun 06:01:00</code></p>
|
||||
<p>Description</p>
|
||||
<ul>
|
||||
<li>One episode for each daily segment (<code>night</code>, <code>morning</code>, <code>afternoon</code> and <code>evening</code>) on each day</li>
|
||||
<li>Two episodes near the transition of the daily segment, one starts at the end of the afternoon, <code>Fri 17:10:00</code> and another one starts at the beginning of the evening, <code>Fri 18:01:00</code></li>
|
||||
<li>One episode across two segments, <code>daily</code> and <code>30-mins</code>, (from <code>Fri 05:55:00</code> to <code>Fri 06:00:41</code>)</li>
|
||||
<li>Two episodes locate in the same daily segment (<code>Sat 12:45:36</code> and <code>Sat 16:48:22</code>)</li>
|
||||
<li>One episode before the time switch, <code>Sun 00:15:06</code>, and one episode after the time switch, <code>Sun 06:01:00</code></li>
|
||||
</ul>
|
||||
<p>Data format</p>
|
||||
<table>
|
||||
<thead>
|
||||
|
|
|
@ -1892,7 +1892,7 @@
|
|||
<tr>
|
||||
<td>durationstationary</td>
|
||||
<td>minutes</td>
|
||||
<td>The total duration of <code>[ACTIVITY_CLASSES][STATIONARY]</code> episodes</td>
|
||||
<td>The total duration of <code>[ACTIVITY_CLASSES][STATIONARY]</code> episodes of still and tilting activities</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>durationmobile</td>
|
||||
|
|
File diff suppressed because one or more lines are too long
Binary file not shown.
Loading…
Reference in New Issue