Interested in Collaborating with the UH-DAIS Research lab?

In general, the UH-DAIS research group has a strong background in data mining, machine learning, data analysis, and in solving challenging optimization problems; in particular, our areas of expertise include spatial data mining, clustering, association analysis, and prediction. In the past, we collaborated with hydrologists, optometrists, planetary scientists, air pollution experts, and building designers helping them in their scientific research and in making sense of their data.

Moreover, our research group developed several unique data mining tools, including:

  • Prototype-based, agglomerative, and grid-based clustering algorithms that allow for plug-in fitness functions; this enables domain experts to instruct clustering algorithms to find groupings based on their "own" notion of interestingness.
  • Region discovery algorithms that find "interesting places" in spatial datasets.
  • Density-based clustering algorithms that operate on non-parametric density functions.
  • Regional co-location mining algorithms that find types of events that are located in close proximity to each other in spatial datasets.
  • Data mining algorithms that analyze several related datasets, including discrepancy mining algorithms that identify differences/change between two datasets and correspondence mining algorithms that identify "interesting relationships" between related datasets.
  • Trajectory and polygon mining algorithms.
  • A java-based data mining platform called Cougar^2.

  • In general, we seek collaboration with well respected scientists that work on challenging research problems that have a strong impact on the future of our society. Feel free to contact us:

    Contact person: Christoph F. Eick