https://sdq.kastel.kit.edu/index.php?title=Incremental_Real-Time_Personalization_in_Human_Activity_Recognition_Using_Domain_Adaptive_Batch_Normalization&feed=atom&action=historyIncremental Real-Time Personalization in Human Activity Recognition Using Domain Adaptive Batch Normalization - Versionsgeschichte2024-03-29T01:01:39ZVersionsgeschichte dieser Seite in SDQ-InstitutsseminarMediaWiki 1.39.6https://sdq.kastel.kit.edu/mediawiki-institutsseminar/index.php?title=Incremental_Real-Time_Personalization_in_Human_Activity_Recognition_Using_Domain_Adaptive_Batch_Normalization&diff=1390&oldid=prevNv3463 am 5. Juni 2020 um 08:47 Uhr2020-06-05T08:47:33Z<p></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="de">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Nächstältere Version</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Version vom 5. Juni 2020, 09:47 Uhr</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l4">Zeile 4:</td>
<td colspan="2" class="diff-lineno">Zeile 4:</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|vortragstyp=Masterarbeit</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|vortragstyp=Masterarbeit</div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|betreuer=Klemens Böhm</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|betreuer=Klemens Böhm</div></td></tr>
<tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>|termin=Institutsseminar/2020-06-<del style="font-weight: bold; text-decoration: none;">12</del></div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>|termin=Institutsseminar/2020-06-<ins style="font-weight: bold; text-decoration: none;">05</ins></div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|kurzfassung=Human Activity Recognition (HAR) from accelerometers is a fundamental problem in ubiquitous computing. Machine learning based recognition models often perform poorly when applied to new users that were not part of the training data. Previous work has addressed this challenge by personalizing general recognition models to the motion pattern of a new user in a static batch setting. The more challenging online setting has received less attention. No samples from the target user are available in advance, but they arrive sequentially. Additionally, the user's motion pattern may change over time. Thus, adapting to new and forgetting old information must be traded off. Finally, the target user should not have to do any work to use the recognition system by labeling activities. Our work addresses this challenges by proposing an unsupervised online domain adaptation algorithm. It works by aligning the feature distribution of all the subjects, sources and target, within deep neural network layers.</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|kurzfassung=Human Activity Recognition (HAR) from accelerometers is a fundamental problem in ubiquitous computing. Machine learning based recognition models often perform poorly when applied to new users that were not part of the training data. Previous work has addressed this challenge by personalizing general recognition models to the motion pattern of a new user in a static batch setting. The more challenging online setting has received less attention. No samples from the target user are available in advance, but they arrive sequentially. Additionally, the user's motion pattern may change over time. Thus, adapting to new and forgetting old information must be traded off. Finally, the target user should not have to do any work to use the recognition system by labeling activities. Our work addresses this challenges by proposing an unsupervised online domain adaptation algorithm. It works by aligning the feature distribution of all the subjects, sources and target, within deep neural network layers.</div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>}}</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>}}</div></td></tr>
</table>Nv3463https://sdq.kastel.kit.edu/mediawiki-institutsseminar/index.php?title=Incremental_Real-Time_Personalization_in_Human_Activity_Recognition_Using_Domain_Adaptive_Batch_Normalization&diff=1385&oldid=prevNv3463: Die Seite wurde neu angelegt: „{{Vortrag |vortragender=Alan Mazankiewicz |email=alan.mazankiewicz@student.kit.edu |vortragstyp=Masterarbeit |betreuer=Klemens Böhm |termin=Institutsseminar/2…“2020-06-02T12:06:45Z<p>Die Seite wurde neu angelegt: „{{Vortrag |vortragender=Alan Mazankiewicz |email=alan.mazankiewicz@student.kit.edu |vortragstyp=Masterarbeit |betreuer=Klemens Böhm |termin=Institutsseminar/2…“</p>
<p><b>Neue Seite</b></p><div>{{Vortrag<br />
|vortragender=Alan Mazankiewicz<br />
|email=alan.mazankiewicz@student.kit.edu<br />
|vortragstyp=Masterarbeit<br />
|betreuer=Klemens Böhm<br />
|termin=Institutsseminar/2020-06-12<br />
|kurzfassung=Human Activity Recognition (HAR) from accelerometers is a fundamental problem in ubiquitous computing. Machine learning based recognition models often perform poorly when applied to new users that were not part of the training data. Previous work has addressed this challenge by personalizing general recognition models to the motion pattern of a new user in a static batch setting. The more challenging online setting has received less attention. No samples from the target user are available in advance, but they arrive sequentially. Additionally, the user's motion pattern may change over time. Thus, adapting to new and forgetting old information must be traded off. Finally, the target user should not have to do any work to use the recognition system by labeling activities. Our work addresses this challenges by proposing an unsupervised online domain adaptation algorithm. It works by aligning the feature distribution of all the subjects, sources and target, within deep neural network layers.<br />
}}</div>Nv3463