https://sdq.kastel.kit.edu/index.php?title=Detecting_Outlying_Time-Series_with_Global_Alignment_Kernels&feed=atom&action=history
Detecting Outlying Time-Series with Global Alignment Kernels - Versionsgeschichte
2024-03-29T14:59:54Z
Versionsgeschichte dieser Seite in SDQ-Institutsseminar
MediaWiki 1.39.6
https://sdq.kastel.kit.edu/mediawiki-institutsseminar/index.php?title=Detecting_Outlying_Time-Series_with_Global_Alignment_Kernels&diff=1499&oldid=prev
Yr6540 am 3. Dezember 2020 um 12:45 Uhr
2020-12-03T12:45:20Z
<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 3. Dezember 2020, 13:45 Uhr</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l5">Zeile 5:</td>
<td colspan="2" class="diff-lineno">Zeile 5:</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=Florian Kalinke</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=Florian Kalinke</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>|termin=Institutsseminar/2020-12-11</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>|termin=Institutsseminar/2020-12-11</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>|kurzfassung=Using outlier detection algorithms e.g., SVDD, for detecting outlying <del style="font-weight: bold; text-decoration: none;">Time</del>-<del style="font-weight: bold; text-decoration: none;">Series </del>usually requires extracting domain-specific attributes. However, this indirect way <del style="font-weight: bold; text-decoration: none;">requires </del>expert knowledge, <del style="font-weight: bold; text-decoration: none;">which makes </del>SVDD <del style="font-weight: bold; text-decoration: none;">in </del>many use cases <del style="font-weight: bold; text-decoration: none;">impractical</del>. Incorporating "Global Alignment Kernels" directly into SVDD to compute the distance between time-series data bypasses the attribute-extraction step and makes the application of SVDD independent of the underlying domain. In this work, a new algorithm <del style="font-weight: bold; text-decoration: none;">based on </del>"Global Alignment Kernels" and SVDD <del style="font-weight: bold; text-decoration: none;">is developed</del>. Its outlier detection capabilities will be evaluated on synthetic data as well as on real-world data sets. Additionally, our approach's performance will be compared to state-of-the-art methods for outlier detection, especially <del style="font-weight: bold; text-decoration: none;">if our approach detects different </del>outliers.</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>|kurzfassung=Using outlier detection algorithms<ins style="font-weight: bold; text-decoration: none;">, </ins>e.g., <ins style="font-weight: bold; text-decoration: none;">Support Vector Data Description (</ins>SVDD<ins style="font-weight: bold; text-decoration: none;">)</ins>, for detecting outlying <ins style="font-weight: bold; text-decoration: none;">time</ins>-<ins style="font-weight: bold; text-decoration: none;">series </ins>usually requires extracting domain-specific attributes. However, this indirect way <ins style="font-weight: bold; text-decoration: none;">needs </ins>expert knowledge, <ins style="font-weight: bold; text-decoration: none;">making </ins>SVDD <ins style="font-weight: bold; text-decoration: none;">impractical for </ins>many <ins style="font-weight: bold; text-decoration: none;">real-world </ins>use cases. Incorporating "Global Alignment Kernels" directly into SVDD to compute the distance between time-series data bypasses the attribute-extraction step and makes the application of SVDD independent of the underlying domain.</div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></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> </div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></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>In this work, <ins style="font-weight: bold; text-decoration: none;">we propose </ins>a new <ins style="font-weight: bold; text-decoration: none;">time-series outlier detection </ins>algorithm<ins style="font-weight: bold; text-decoration: none;">, combining </ins>"Global Alignment Kernels" and SVDD. Its outlier detection capabilities will be evaluated on synthetic data as well as on real-world data sets. Additionally, our approach's performance will be compared to state-of-the-art methods for outlier detection, especially <ins style="font-weight: bold; text-decoration: none;">with regard to the types of detected </ins>outliers.</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>
Yr6540
https://sdq.kastel.kit.edu/mediawiki-institutsseminar/index.php?title=Detecting_Outlying_Time-Series_with_Global_Alignment_Kernels&diff=1497&oldid=prev
Uxrdr am 2. Dezember 2020 um 14:16 Uhr
2020-12-02T14:16:36Z
<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 2. Dezember 2020, 15:16 Uhr</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l5">Zeile 5:</td>
<td colspan="2" class="diff-lineno">Zeile 5:</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=Florian Kalinke</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=Florian Kalinke</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>|termin=Institutsseminar/2020-12-11</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>|termin=Institutsseminar/2020-12-11</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>|kurzfassung=Using outlier detection algorithms<del style="font-weight: bold; text-decoration: none;">, </del>e.g., <del style="font-weight: bold; text-decoration: none;">Support Vector Data Description (</del>SVDD<del style="font-weight: bold; text-decoration: none;">)</del>, for detecting outlying <del style="font-weight: bold; text-decoration: none;">time</del>-<del style="font-weight: bold; text-decoration: none;">series </del>usually requires extracting domain-specific attributes. However, this indirect way <del style="font-weight: bold; text-decoration: none;">needs </del>expert knowledge, <del style="font-weight: bold; text-decoration: none;">making </del>SVDD <del style="font-weight: bold; text-decoration: none;">impractical for </del>many <del style="font-weight: bold; text-decoration: none;">real-world </del>use cases. Incorporating <del style="font-weight: bold; text-decoration: none;">“Global </del>Alignment <del style="font-weight: bold; text-decoration: none;">Kernels” </del>directly into SVDD to compute the distance between time-series data bypasses the attribute-extraction step and makes the application of SVDD independent of the underlying domain.</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>|kurzfassung=Using outlier detection algorithms e.g., SVDD, for detecting outlying <ins style="font-weight: bold; text-decoration: none;">Time</ins>-<ins style="font-weight: bold; text-decoration: none;">Series </ins>usually requires extracting domain-specific attributes. However, this indirect way <ins style="font-weight: bold; text-decoration: none;">requires </ins>expert knowledge, <ins style="font-weight: bold; text-decoration: none;">which makes </ins>SVDD <ins style="font-weight: bold; text-decoration: none;">in </ins>many use cases <ins style="font-weight: bold; text-decoration: none;">impractical</ins>. Incorporating <ins style="font-weight: bold; text-decoration: none;">"Global </ins>Alignment <ins style="font-weight: bold; text-decoration: none;">Kernels" </ins>directly into SVDD to compute the distance between time-series data bypasses the attribute-extraction step and makes the application of SVDD independent of the underlying domain<ins style="font-weight: bold; text-decoration: none;">. In this work, a new algorithm based on "Global Alignment Kernels" and SVDD is developed. Its outlier detection capabilities will be evaluated on synthetic data as well as on real-world data sets. Additionally, our approach's performance will be compared to state-of-the-art methods for outlier detection, especially if our approach detects different outliers</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>}}</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>
Uxrdr
https://sdq.kastel.kit.edu/mediawiki-institutsseminar/index.php?title=Detecting_Outlying_Time-Series_with_Global_Alignment_Kernels&diff=1496&oldid=prev
Yr6540 am 2. Dezember 2020 um 12:17 Uhr
2020-12-02T12:17:34Z
<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 2. Dezember 2020, 13:17 Uhr</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l5">Zeile 5:</td>
<td colspan="2" class="diff-lineno">Zeile 5:</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=Florian Kalinke</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=Florian Kalinke</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>|termin=Institutsseminar/2020-12-11</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>|termin=Institutsseminar/2020-12-11</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>|kurzfassung=Using outlier detection algorithms e.g., SVDD, for detecting outlying <del style="font-weight: bold; text-decoration: none;">Time</del>-<del style="font-weight: bold; text-decoration: none;">Series </del>usually requires extracting domain-specific attributes. However, this indirect way <del style="font-weight: bold; text-decoration: none;">requires </del>expert knowledge, <del style="font-weight: bold; text-decoration: none;">which makes </del>SVDD <del style="font-weight: bold; text-decoration: none;">in </del>many use cases <del style="font-weight: bold; text-decoration: none;">impractical</del>. Incorporating “Global Alignment Kernels” directly into SVDD to compute the distance between time-series data bypasses the attribute-extraction step and makes the application of SVDD independent of the underlying domain.</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>|kurzfassung=Using outlier detection algorithms<ins style="font-weight: bold; text-decoration: none;">, </ins>e.g., <ins style="font-weight: bold; text-decoration: none;">Support Vector Data Description (</ins>SVDD<ins style="font-weight: bold; text-decoration: none;">)</ins>, for detecting outlying <ins style="font-weight: bold; text-decoration: none;">time</ins>-<ins style="font-weight: bold; text-decoration: none;">series </ins>usually requires extracting domain-specific attributes. However, this indirect way <ins style="font-weight: bold; text-decoration: none;">needs </ins>expert knowledge, <ins style="font-weight: bold; text-decoration: none;">making </ins>SVDD <ins style="font-weight: bold; text-decoration: none;">impractical for </ins>many <ins style="font-weight: bold; text-decoration: none;">real-world </ins>use cases. Incorporating “Global Alignment Kernels” directly into SVDD to compute the distance between time-series data bypasses the attribute-extraction step and makes the application of SVDD independent of the underlying domain.</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>
Yr6540
https://sdq.kastel.kit.edu/mediawiki-institutsseminar/index.php?title=Detecting_Outlying_Time-Series_with_Global_Alignment_Kernels&diff=1494&oldid=prev
Uxrdr am 2. Dezember 2020 um 08:31 Uhr
2020-12-02T08:31:52Z
<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 2. Dezember 2020, 09:31 Uhr</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l5">Zeile 5:</td>
<td colspan="2" class="diff-lineno">Zeile 5:</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=Florian Kalinke</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=Florian Kalinke</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>|termin=Institutsseminar/2020-12-11</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>|termin=Institutsseminar/2020-12-11</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>|kurzfassung=<del style="font-weight: bold; text-decoration: none;">Kurzfassung</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>|kurzfassung=<ins style="font-weight: bold; text-decoration: none;">Using outlier detection algorithms e.g., SVDD, for detecting outlying Time-Series usually requires extracting domain-specific attributes. However, this indirect way requires expert knowledge, which makes SVDD in many use cases impractical. Incorporating “Global Alignment Kernels” directly into SVDD to compute the distance between time-series data bypasses the attribute-extraction step and makes the application of SVDD independent of the underlying domain.</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>}}</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>
Uxrdr
https://sdq.kastel.kit.edu/mediawiki-institutsseminar/index.php?title=Detecting_Outlying_Time-Series_with_Global_Alignment_Kernels&diff=1486&oldid=prev
Yr6540: Die Seite wurde neu angelegt: „{{Vortrag |vortragender=Haiko Thiessen |email=haiko.thiessen@student.kit.edu |vortragstyp=Proposal |betreuer=Florian Kalinke |termin=Institutsseminar/2020-12-1…“
2020-11-25T10:08:48Z
<p>Die Seite wurde neu angelegt: „{{Vortrag |vortragender=Haiko Thiessen |email=haiko.thiessen@student.kit.edu |vortragstyp=Proposal |betreuer=Florian Kalinke |termin=Institutsseminar/2020-12-1…“</p>
<p><b>Neue Seite</b></p><div>{{Vortrag<br />
|vortragender=Haiko Thiessen<br />
|email=haiko.thiessen@student.kit.edu<br />
|vortragstyp=Proposal<br />
|betreuer=Florian Kalinke<br />
|termin=Institutsseminar/2020-12-11<br />
|kurzfassung=Kurzfassung<br />
}}</div>
Yr6540