Institutsseminar/2021-05-21

Aus SDQ-Institutsseminar
Version vom 17. Mai 2021, 13:02 Uhr von Emre Taspolatoglu (Diskussion | Beiträge) (Änderung 1666 von Ew8352 (Diskussion) rückgängig gemacht.)
Termin (Alle Termine)
Datum Freitag, 21. Mai 2021
Uhrzeit 11:30 – 12:45 Uhr (Dauer: 75 min)
Ort https://conf.dfn.de/webapp/conference/979160755
Webkonferenz
Vorheriger Termin Fr 14. Mai 2021
Nächster Termin Fr 21. Mai 2021

Termin in Kalender importieren: iCal (Download)

Vorträge

Vortragende(r) Haiko Thiessen
Titel Detecting Outlying Time-Series with Global Alignment Kernels (Defense)
Vortragstyp Masterarbeit
Betreuer(in) Florian Kalinke
Vortragsmodus
Kurzfassung Detecting outlying time-series poses two challenges: First, labeled training data is rare, as it is costly and error-prone to obtain. Second, algorithms usually rely on distance metrics, which are not readily applicable to time-series data. To address the first challenge, one usually employs unsupervised algorithms. To address the second challenge, existing algorithms employ a feature-extraction step and apply the distance metrics to the extracted features instead. However, feature extraction requires expert knowledge, rendering this approach also costly and time-consuming.

In this thesis, we propose GAK-SVDD. We combine the well-known SVDD algorithm to detect outliers in an unsupervised fashion with Global Alignment Kernels (GAK), bypassing the feature-extraction step. We evaluate GAK-SVDD's performance on 28 standard benchmark data sets and show that it is on par with its closest competitors. Comparing GAK with a DTW-based kernel, GAK improves the median Balanced Accuracy by 4%. Additionally, we extend our method to the active learning setting and examine the combination of GAK and domain-independent attributes.

Vortragende(r) Kuan Yang
Titel Efficient Verification of Data-Value-Aware Process Models
Vortragstyp Bachelorarbeit
Betreuer(in) Elaheh Ordoni
Vortragsmodus
Kurzfassung Verification methods detect unexpected behavior of business process models before their execution. In many process models, verification depends on data values. A data value is a value in the domain of a data object, e.g., $1000 as the price of a product. However, verification of process models with data values often leads to state-space explosion. This problem is more serious when the domain of data objects is large. The existing works to tackle this problem often abstract the domain of data objects. However, the abstraction may lead to a wrong diagnosis when process elements modify the value of data objects.

In this thesis, we provide a novel approach to enable verification of process models with data values, so-called data-value-aware process models. A distinctive of our approach is to support modification of data values while preserving the verification results. We show the functionality of our approach by conducting the verification of a real-world application: the German 4G spectrum auction model.

Neuen Vortrag erstellen

Hinweise