Research overview

Our group is dedicated to both basic and application-oriented research in the expansive field of AI and ML. We focus on adaptive learning methods, showcased in projects like Hephaestus, which explores industrial data streams from drilling machines in a production pipeline. KISWIND concentrates on detecting outliers in multiple sensor data from wind turbines, while OSCAR focuses on textual data streams, including those generated by social media. In addition, we are committed to responsible AI, demonstrated through projects such as MAMMoth, which addresses multidimensional discrimination in complex data, and projects NoBIAS and BIAS that focus on understanding bias sources and designing mitigation strategies in AI systems. Moreover, our research extends to exploring the creative potential of generative AI to enhance data quality, as seen in projects like STELAR, and to innovatively design new data and solutions, exemplified by projects such as SFB1463. We apply our methods across various industries, including education, social networks, banking, agriculture, manufacturing, and engineering. Our research receives support from EU and national funding, including the DFG and the Volkswagen Foundation.

Ongoing research projects

• DFG Scientific Network on Digital Bioethics
The scientific network Digital Bioethics supported by DFG and led by Prof. Sabine Salloch from the Hannover Medical School (MHH) aims at covering the wide domain of bioethics and the role of technology, esp AI, in the domain as the new technologies offer new methodological opportunities but there are also ethical implications arising from algorithmic decision-making in healthcare and biomedical research including technology's own risks and limitations.

• MAMMOTH (Multi-Attribute, Multimodal Bias Mitigation in AI Systems)
Funding: EU under the call HORIZON-CL4-2021-HUMAN-01 (A HUMAN-CENTRED AND ETHICAL DEVELOPMENT OF DIGITAL AND INDUSTRIAL TECHNOLOGIES 2021).
The MAMMOth project focuses on multi-discrimination mitigation for tabular, network and multimodal data. Through its computer science and AI experts, MAMMOth aims at addressing the associated scientific challenges by developing an innovative fairness-aware AI-data driven foundation that provides the necessary tools and techniques for the discovery and mitigation of (multi-)discrimination and ensures the accountability of AI-systems with respect to multiple protected attributes and for traditional tabular data and more complex network and visual data. The project aims to demonstrate through pilots the developed solutions into three relevant sectors of interest: a) finance/loan applications, b) identity verification systems, and c) academic evaluation.

• STELAR (Spatio-TEmporal Linked data tools for the AgRi-food data space)
Funding: EU under the call HORIZON-CL4-2021-DATA-01-03 - Technologies for data management (IA).
STELAR will design, develop, evaluate, and showcase an innovative Knowledge Lake Management System (KLMS) to support and facilitate a holistic approach for FAIR (Findable, Accessible, Interoperable, Reusable) and AI-ready (high-quality, reliably labeled) data that will be pilot tested in diverse, real-world use cases in the agrifood data space, one of the nine data spaces of strategic societal and economic importance identified in the European Strategy for Data.

• CRC 1463: Integrated Design and Operation Methodology for Offshore Megastructures
Funding: DFG.
With the help of the real-time capable simulation model of a digital twin, the SFB researches the design and operating conditions of offshore megastructures, whereby all life phases of a structure can be represented. This enables a reactive and automated adaptation of the structure and its operation to current and future conditions. We participate in project B01 "Integrated design process for offshore structures" with the aim to develop a prognosis model to predict the design quality over the complete life cycle of offshore structures, combining the experience and intuition of the engineer and expert through appropriate ML methods.

• Hephaestus - Machine learning methods for adaptive process planning of 5-axis milling
Funding: DFG.
Rising customer demands and a trend towards smaller batch sizes have led to an increased complexity in product design and subsequent process planning, e.g. of 5-axes milling operations. Thus, process simulations are commonly used in industry to support process planning. Especially, the dimensional accuracy is crucial for most machined parts, since it affects directly the functionality. Consequently, finishing operations have especially high requirements with respect to the surface tolerances. Despite the aforementioned simulation tools, manual adjustments, which rely on the expert knowledge of workers and process planners, are still necessary in order to cope with process- or machine-specific deviations such as tool stiffness or machine dynamics.

• ITN NoBIAS - Artificial Intelligence without Bias
Funding: EU.
The core objective of NoBIAS is to research and develop novel methods for AI-based decision making without bias. NoBIAS will deliver a cohort of 15 researchers trained to identify biased and discriminating AI-decision making and able to provide solutions that reconcile and fully exploit AI while ensuring compliance with legal and social norms.

• BIAS – Bias and Discrimination in Big Data and Algorithmic Processing. Philosophical Assessments, Legal Dimensions, and Technical Solutions.
Funding: Volkswagen Stiftung.
AI techniques based on big data and algorithmic processing are increasingly used to guide decisions in important societal spheres, including hiring decisions, university admissions, loan granting, and crime prediction. However, there are growing concerns with regard to the epistemic and normative quality of AI evaluations and predictions. Our shared research question is: How can standards of unbiased attitudes and non-discriminatory practices be met in big data analysis and algorithm-based decision-making? In approaching this question, we will provide philosophical analyses of the relevant concepts and principles in the context of AI (bias, discrimination, fairness), investigate their adequate reception in pertinent legal frameworks (data protection, consumer, competition, anti-discrimination law), and develop concrete technical solutions (debiasing strategies, discrimination detection procedures etc.).

• KISWIND
Funding: Bundesministerium für Wirtschaft und Energie (BMWi), Role: PI (Eirini Ntoutsi).
The overall objective of the research project is the development of methods for efficient and automated continuous monitoring of the support structure of wind turbines for the detection of damage events and anomalies using acoustic emission analysis and innovative evaluation methods from the field of artificial intelligence (AI).

• LernMINT - Dealing with bias and discrimination in learning analytics models
Funding: Ministry of Science and Culture of Lower Saxony, Role: PI (Eirini Ntoutsi)
The goal of the PhD training network LernMINT is to provide interdisciplinary training for the doctoral candidates to qualify them as experts in a sub-area of digital education namely data-assisted learning and teaching in STEM (in German: MINT) subjects. In LernMINT, there are five subject areas: (1) Learning analytics methods for STEM teaching, (2) Data-based support of learning potential, (3) Informal learning in schools and universities, (4) Transition from school to university, (5) Data protection and fairness of learning analytics methods.

• ENKIS - Etablierung nachhaltiger KI-bezogener Studienangebote für eine Verantwortungsvolle Künstliche Intelligenz an der FUB, Role: PI (Eirini Ntoutsi).
Funding: BMBF.
Promoting AI in higher education (FUB, particularly).
Updated status: No further involvement.

• Responsible AI
Funding: Ministry of Science and Culture of Lower Saxony, Role: PI (Eirini Ntoutsi).
Artificial intelligence (AI) technologies are the driving force behind digitization. Due to their enormous social relevance, a responsible use of AI is of particular importance. The research and application of responsible AI is a very young discipline and requires the bundling of research activities from different disciplines in order to design and apply AI systems in a reliable, transparent, secure and legally acceptable way.
Updated status: No further involvement.

Finished research projects

• OSCAR - Opinion Stream Classification with Ensembles and Active leaRners.
Funding: DFG, Role: PI (Eirini Ntoutsi).
Many data accumulating in the Web reflect opinions on diverse subjects - products, institutions, events (e.g., elections) or topics (e.g., earth warming). Opinionated documents constitute a continuous stream; polarity learning on them delivers insights on the attitude of people towards each subject. Polarity learning algorithms must cope with classic Big Data characteristics: high volume and velocity of the arriving data, and volatility of the learned concepts, since subjects and attitudes of people toward certain subjects change over time. In OSCAR, we will develop classifiers that operate on an evolving feature space, adapt to changes in both vocabulary and data and operate with limited class labels.

• Transalpine mobility and knowledge transfer
Funding: DFG FOR 1670, Role: Postdoctoral researcher (Eirini Ntoutsi).
The project aims at the establishment of an isotopic fingerprint for bioarchaeological finds, especially cremations, and its application to archaeological and cultural-historical problems of the Late Bronze Age until Roman Times. From a computer science persective, our focus is on the development of innovative methods that allow complete scientific analysis of project related data despite their complexity. We focus on data management and automated data analysis (similarity search, cluster analysis, outlier recognition) for the establishment of small-scaled isotopic fingerprints.

• GeoPKDD (Geographic Privacy-aware Knowledge Discovery and Delivery)
FP6/IST project, 2005-2009, Role: Ph.D. researcher (Eirini Ntoutsi).
GeoPKDD aims at developing theory, techniques and systems for knowledge discovery and delivery, based on new automated privacy-preserving methods for extracting user-consumable forms of knowledge from large amounts of raw data referenced in both space and time dimensions.

• Knowledge Discovery and Pattern Management - the PBMS approach
Funding: EPEAEK II / Heracletos Programme, 2003-2005, Role: Ph.D. researcher (Eirini Ntoutsi).
The goal of this project is the efficient management of data mining patterns extracted from large databases, with emphasis on the pattern similarity assesment problem.

• PANDA (Patterns for Next Generation Database Systems)
Funding: IST project 2001-2004, Role: Ph.D. researcher (Eirini Ntoutsi).
PANDA working group studies current state-of-the-art in pattern management and explores novel theoretical and practical aspects of a Pattern Base Management System (so-called, PBMS). PANDA's goal is the efficient and effective management of patterns; just as raw data are managed by traditional DBMS.