Contact
Currently at Aarhus University
For master theses in the field of analyzing MD data, please write to beer@cs.au.dk
Research Interests:
- Methods for analyzing molecular dynamics data
- Clustering, Subspace Clustering, Correlation Clustering, Spectral Clustering
- High-Dimensional Data
- Outlier Detection
- Graphs and Networks
Teaching:
- Bachelor Seminar "Privacy Preserving Data Mining" (WiSe 2021/22)
- Knowledge Discovery in Databases 2 (SoSe2021)
- Master Seminar "On Spectral Clustering" (WiSe 2020/21)
- Knowledge Discovery in Databases 2 (SoSe2020)
- Big Data Management and Analytics (WiSe 2019/20)
- Bachelor Seminar "Aktuelle Themen im Bereich Data Science" (SoSe2019)
- Bachelor Seminar "Einführung ins wissenschaftliche Arbeiten- Clustering" (WiSe 2018/19)
- Algorithmen und Datenstrukturen (SoSe 2018)
- Knowledge Discovery in Databases (WiSe 2017/18)
- Managing Massive Multiplayer Online Games (SoSe 2017)
Supervised Theses:
- Multi-View Spectral Clustering on Single-View Data – Grouping High-Dimensional Representations of 3D Objects
- Accelerating Robust Spectral Clustering using the Nyström Method
- On Optimizing Parameter Settings for Clustering Algorithms
- Linear Unsupervised Correlation Clustering transferring Knowledge from Cluster Algorithms
- Statistic-based Internal Quality measures for Clustering
- A Multilabel Clustering Approach based on Attribute-Dependent Density
- Clustering using Inverse Heat Kernels
- Variants of Spectral Clustering
- kNN in High-Dimensional Data
- Interactive Spectral Clustering
- Comparison of Different Grid Construction Methods in Clustering
- Angle-Based Clustering
- A kNN-based Clustering Approach
- Anytime Outlier Detection based on Distributions and k-Means
- Subspace Clustering with kNN
- Gamification of Subspace Clustering via Visual Analytics
- Linear Correlation Clustering auf Basis der nächsten Nachbarn
- Chaindetection for DBSCAN
- Using a Semi-Pseudometric for Clustering High Dimensional Data
- Clustering Multidimensional Data using Fitted Grid Size
- Clustern von Punktmengen basierend auf dynamischer Dichte
Publications and Accepted Papers:
- Hohma*, E., Frey*, C., Beer*, A. & Seidl, T. (2022). SCAR - Spectral Clustering Accelerated and Robustified. Accepted for publication at VLDB 2022.
- Ullmann, T., Beer, A., Hünemörder, M., Seidl, T., & Boulesteix, A. L. (2022). Over-optimistic evaluation and reporting of novel cluster algorithms: an illustrative study. Advances in Data Analysis and Classification, 1-28.
- Beer, A., Stephan, L., & Seidl, T. (2021, December). LUCKe—Connecting Clustering and Correlation Clustering. In 2021 International Conference on Data Mining Workshops (ICDMW) (pp. 431-440). IEEE.
- Beer, A. (2021). On the edges of clustering (Doctoral dissertation, LMU Munich).
- Kazempour, D., Beer, A., Oelker, M., Kröger, P., & Seidl, T. (2021, September). Compound segmentation via clustering on Mol2Vec-based embeddings. In 2021 IEEE 17th International Conference on eScience (eScience) (pp. 60-69). IEEE.
- Sandra Obermeier, Anna Beer, Florian Wahl, Thomas Seidl (2021, September). Cluster Flow — an Advanced Concept for Ensemble-Enabling, Interactive Clustering. BTW 2021.
- Beer, A., Allerborn, E., Hartmann, V., & Seidl, T. (2021, March). KISS – A fast kNN-based Importance Score for Subspaces. EDBT 2021.
- Lohrer, A., Beer, A., Hünemörder, M., Lauterbach, J., Seidl, T., & Kröger, P. (2021). AnyCORE-An Anytime Algorithm for Cluster Outlier REmoval.
- D. Kazempour, A. Beer, P. Kröger, and T. Seidl. “I fold you so! An internal evaluation measure for arbitrary oriented subspace clustering through piecewise-linear approximations of manifolds". In Proceedings of the 8th Workshop on High Dimensional Data Mining (HDM 2020) at the 20th IEEE International Conference on Data Mining (ICDM 2020). Virtual, Nov. 17–20, 2020.
- Beer, A., Seeholzer, D., Schüler, N. S., & Seidl, T. (2020, September). Angle-Based Clustering. SISAP 2020 (pp. 312-320).
- Beer, A., Kazempour, D., Busch, J., Tekles, A., Seidl, T. (2020, September). Grace - Limiting the Number of Grid Cells for Clustering High-Dimensional Data. LWDA 2020.
- Beer, A., Hartmann, V., & Seidl, T. (2020, July). Orderings of Data-More Than a Tripping Hazard: Visionary. SSDBM 2020.
- Beer, A., Schüler, N. S., & Seidl, T. (2019). A Generator for Subspace Clusters. LWDA 2019.
- Kazempour, D., Beer, A., Schrüfer, O., & Seidl, T. (2019). Clustering Trend Data Time-Series through Segmentation of FFT-decomposed Signal Constituents. LWDA 2019.
- Hünemörder, M. A. X., Kazempour, D., Beer, A., & Seidl, T. (2019). CODEC-Detecting Linear Correlations in Dense Clusters using coMAD-based PCA. LWDA 2019.
- Beer, A., Lauterbach, J. & Seidl, T. (2019, October). MORe++: k-Means based Outlier Removal on High-Dimensional Data. SISAP 2019.
- Held, J., Beer, A., & Seidl, T. Chain-detection Between Clusters. Datenbank-Spektrum, 1-12.
- Beer, A. & Seidl, T. (2019, July). Graph Ordering and Clustering - A Circular Approach. SSDBM 2019.
- Beer, A., Kazempour, D., Stephan, L., & Seidl, T. (2019, July). LUCK- Linear Correlation Clustering Using Cluster Algorithms and a kNN based Distance Function. SSDBM 2019.
- Beer, A., Kazempour, D., Baur, M., & Seidl, T. (2019, July). Human Learning in Data Science. In International Conference on Human-Computer Interaction (pp. 170-176). Springer, Cham.
- Kazempour, D., Beer, A., & Seidl, T. (2019, July). Data on RAILs: On Interactive Generation of Artificial Linear Correlated Data. In International Conference on Human-Computer Interaction (pp. 184-189). Springer, Cham.
- Beer, A., Kazempour, D., & Seidl, T. (2019, March). Rock- Let the points roam to their clusters themselves. EDBT 2019 (pp. 630-633).
- Held, J., Beer, A., & Seidl, T. (2019, March). Chain-detection for DBSCAN. Datenbanksysteme für Business, Technologie und Web (BTW2019) (pp 173- 182).
- Kazempour, D., Beer, A., Herzog, F., Kaltenthaler, D., Lohrer, J. Y., & Seidl, T. (2018, October). FATBIRD: A Tool for Flight and Trajectories Analyses of Birds. In 2018 IEEE 14th International Conference on e-Science (e-Science) (pp. 75-82). IEEE.
- Kazempour, D., Beer, A., Lohrer, J. Y., Kaltenthaler, D., & Seidl, T. (2018, July). PARADISO: an interactive approach of parameter selection for the mean shift algorithm. In Proceedings of the 30th International Conference on Scientific and Statistical Database Management (p. 26). ACM.