Intelligent Information Systems
We Derive Value from Data and Information
- How to leverage information?
- How to find new topics and trends?
- How to derive insight from heterogeneous/unstructured data and information?
- How to allow a «natural» access to data?
- How can software link data automatically?
These are but a few of the questions that the Intelligent Information Systems (IIS) group of the InIT is working to answer. While the “data and information flood” is often discussed negatively, we see a great opportunity to leverage data and information using the right approaches – both at search-time, as well as during analysis.
The research group transfers insights derived from research and development into teaching for students of the computer science curricula. It offers modules such as “Information Engineering 1 (Information Retrieval)”, “Information Engineering 2 (Data Warehousing & Big Data)” and "Databases". The group is active in both national and international research projects of the EU framework programs.
Research Topics
The Intelligent Information Systems group develops solutions for a changing, data-driven world. It performs research at the intersection of databases (DB), information retrieval (IR), data engineering (DE), natural language processing (NLP) and machine learning (ML)
The group covers two main research lines:
Big Data and Nano Data
We solve challenging problems when working with a range of datasets from very small (nano data) to very large (big data), where the nature of the problems change drastically as we work on different scales:
Current research:
- Information retrieval for small document collections
- Machine learning for query optimization
- Artificial intelligence for data integration and cleaning
- Quantum databases and quantum machine learning
Data Understanding
As we strive for "intelligent" solutions to data-driven problems, classical information systems need to process data at a different level, interpreting it to gain important information. Both structured and unstructured data must be processed not on a mechanical, but on a semantic level - e.g. by using natural language processing and understanding. Data is ultimately connected through graph structures or made accessible via semantic search.
Current research:
- Natural language interfaces for databases
- Semantic search on entities
- Knowledge graph construction
- Question answering over knowledge graphs
- Stream analytics and event detection
- Information retrieval evaluation
-
GraphQueryML – Using Machine Learning to Optimize Queries in Graph Databases (SNSF/DFG)
Optimizing the brain of databases with machine learning:Query optimization is one of the hardest problems of database systems research. A query optimizer can be considered as the “brain” of the system that makes sure that queries are executed efficiently. Even after several decades of research, many sub-problems of ...
-
DOSSMA – Detection of Suspicious Social Media Activities
The DOSSMA project will investigate suspicious and malicious behaviour on social media platforms. In a first phase, we will compile an extensive survey report on the areas that are currently being researched, including the respective state-of-the-art, existing solutions and initiatives. This report will serve as a ...
-
Accessible Scientific PDFs for All
PDF is the most popular document format to provide and distribute information on the internet. It was developed by Adobe 1996 but has been an open format since 2008. It was estimated in 2015 that more than 2.5 trillion PDF documents exist on the internet, covering all aspects of life and research, and their number ...
-
Smith, Ellery; Paloots, Rahel; Giagkos, Dimitris; Baudis, Michael; Stockinger, Kurt,
2024.
Data-driven information extraction and enrichment of molecular profiling data for cancer cell lines.
Bioinformatics Advances.
Available from: https://doi.org/10.1093/bioadv/vbae045
-
Frehner, Robin; Wu, Kesheng; Sim, Alexander; Kim, Jinoh; Stockinger, Kurt,
2024.
Detecting anomalies in time series using kernel density approaches.
IEEE Access.
12, pp. 33420-33439.
Available from: https://doi.org/10.1109/ACCESS.2024.3371891
-
Lehmann, Claude; Sulimov, Pavel; Stockinger, Kurt,
2024.
Is your learned query optimizer behaving as you expect? : a machine learning perspective.
Proceedings of the VLDB Endowment.
17(7), pp. 1565-1577.
Available from: https://doi.org/10.21256/zhaw-30586
-
Zhang, Yi; Deriu, Jan Milan; Katsogiannis-Meimarakis, George; Kosten, Catherine; Koutrika, Georgia; Stockinger, Kurt,
2024.
ScienceBenchmark : a complex real-world benchmark for evaluating natural language to SQL systems.
Proceedings of the VLDB Endowment.
17(4), pp. 685-698.
Available from: https://doi.org/10.14778/3636218.3636225
-
Kosten, Catherine; Cudré-Mauroux, Philippe; Stockinger, Kurt,
2024.
Spider4SPARQL : a complex benchmark for evaluating knowledge graph question answering systems [paper].
In:
2023 IEEE International Conference on Big Data (BigData).
IEEE International Conference on Big Data, Sorrento, Italy, 15-18 December 2023.
IEEE.
Available from: https://doi.org/10.1109/BigData59044.2023.10386182