[ Overview | Projects | Achievements | Cooperations ]

Research Group Seidl

In modern information systems, the sheer amount as well as the complexity of the stored data are increasing at a high rate. This trend is known as Big Data in industry or Data-intensive (Analysis-driven) Science in academia, or simply Data Science. The management and analysis of Big Data is the key challenge arising in almost all sectors of our modern society (in academia, this trend is also know as the 4th paradigm in science). To cope with this challenge we will need powerful methods for Big Data Management and Big Data Intelligence.

Our group has a long standing expertise in both fields and, thus builds the bridge between handling and modeling huge amounts of data as well as analyzing these data by means of scalable data mining algorithms. In terms of Big data Management, our group is well-known for the development of various algorithms and access structures for indexing and querying high-dimensional complex data like the R*-tree, X-Tree or the IQ-Tree. In the area of Big Data Intelligence, the members of our group contributed various algorithms and methods for scalable data mining such as DBSCAN, OPTICS or LOF which are among the state-of-the-art solutions for clustering and outlier detection. In addition, we developed several specialized concepts for analyzing data from different applications in industry and academia like spatial-/temporal data, sensor networks, multimedia, bio-medical data, etc. Some of our current research projects are:

• Clustering and Outlier Detection in high-dimensional data
• Managing Uncertain Data
• Query Processing in Uncertain Databases
• Efficient Similarity Search and Data Mining in Medical Image Data
• Database and Search Technologies in Automotive Environments