Projects

A central focus of the AI Innovation Center is direct cooperation with industrial companies: Feasibility studies (Quick Checks) and projects to develop initial prototypes (Exploring Projects) of AI applications. In addition, consortium projects and innovation networks are aimed at cross-company exchange.

Extraction and utilization of facts from medical publications

An AI-supported system for extracting, summarizing and translating medical publications is being developed to make specialist knowledge more efficiently accessible and to cope with the flood of information.

High speed picking

The analysis of the patient journey at Klinikum Stuttgart identifies AI applications to optimize care, increase employee satisfaction and improve economic and ecological criteria.

Information extraction from medical publications

It was evaluated how the preparation of marketing authorization dossiers (core dossiers) can be supported by the extraction of information from medical studies.

Instant calculation of CNC components

Algorithms learn from existing production data and CAD geometries, estimate component complexity in real time, improve cost transparency, automate costing and relieve teams of manual assessments and time-consuming customer communication on a day-to-day basis.

Intuitive label editor for AI applications

The AI Innovation Center's intuitive label editor optimizes the labeling process through structured workflows and automation features, increasing efficiency and ease of use.

AI-supported sales forecast

An AI-supported sales forecast analyzes historical sales data and external factors to predict future sales figures more accurately and enable data-based decisions.

AI anomaly detection with limited data sets

Research on AI anomaly detection with limited data sets aims to develop and test efficient methods for identifying anomalies in various industries despite data scarcity.

Jewelry image AI-based image recognition

AI-based valuation of returns when renting out valuables

In the sharing economy, efficient returns pose a major challenge. This can be largely automated through the use of AI.

AI-based print image control for effervescent tablet tubes at Jaco

The project developed an AI-based solution for print image control. This uses anomaly detection to distinguish real print defects from pseudo defects and reduces false alarms by an average of 85.7%. The technology enables reliable, fully automated quality control without excessive reject rates in the production of effervescent tablet tubes.

AI-based appointment optimization by predicting appointment bookings, no-shows and cancellations

An AI prototype uses traffic light logic to suggest the preferred time slots for scheduling appointment requests in order to achieve the most efficient capacity utilization possible. This is based on past appointment data and takes into account no-shows and appointment cancellations.