SAFE AI ENGINEERING
AI engineering ensures safety of AI components for autonomous, connected driving
SIQAS
Thanks to the measurement of social interaction, psychological stress caused by loneliness can be detected at an earlier stage
Start: 03.2024
End: 08.2025
Social isolation and its effects on mental health are a growing social problem. By measuring social interaction, the SIQAS project is opening up new avenues for early detection and individualized therapeutic approaches in this field.
Social interactions are difficult to measure; current methods often rely on subjective self-reports. The SIQAS project aims to develop an app-based solution that can objectively measure social interactions in everyday life while complying with data protection regulations and avoiding distortion. For example, it measures how intensively a person participates in a conversation, whether they only talk to certain people, and whether their behavior differs between professional and private contexts. To achieve this, audio files are analyzed using AI. SIQAS closes a research gap by combining the collection of objective data, real-time processing and AI models for analyzing social interactions.
This opens up new research areas in psychology, medicine and computer science. For providers of digital health solutions, SIQAS opens up new product possibilities in mobile diagnostics and therapy. Additionally, a new market is emerging for intelligent, data protection-compliant audio processing in healthcare.
Planned AI-based methods, such as SVM, CNN-BiLSTM and transformer models, use audio data to recognize social interactions and emotions. Both real and synthetically generated training data will be used.
This project is intended for researchers, particularly those specializing in healthcare.
Role of the FZI
The FZI is responsible for the following aspects of the SIQAS project:
- Selection and preparation of training data
- Design, selection, and training of AI models
- Performance optimization of algorithms for applicability on mobile devices
- Integration and evaluation of models in an internal test environment
Contact
Dominik Beyer
Research Scientist
Research Division: Embedded Systems and Sensors Engineering
- +49 721 9654-752
- beyer@fzi.de
- Headquarters Karlsruhe
Research Focus
Applied Artificial Intelligence
In this research focus, the FZI concentrates on practical research into the key technology of Artificial Intelligence (AI). Innovative AI solutions are developed and transferred to application areas such as mobility, robotics, healthcare technology, logistics, production, and supply and disposal on behalf of our partners and customers.
Funding information:
The SIQAS project is funded by the Federal Ministry for Economic Affairs and Energy.
Project partner:
More projects
SouveMed
Data trustee model protects use of individual health data in research
OKTI
AI-based software detects and corrects motion artifacts in OCT images.
SIQAS
Thanks to the measurement of social interaction, psychological stress caused by loneliness can be detected at an earlier stage
BeACTIVE
More exercise in everyday life: Self-learning real-time system recognizes behavior patterns and recommends customized activities
RISE
AI assistant serves as first point of contact for legal questions
MAD Urban
AI engineering empowering security reasoning throughout the entire lifecycle of an AI function
SDI4ECom
Secure and self-determined digital identities in e-commerce
CaMinoBW
Co-design for application-specific microelectronics with innovative chiplets in Baden-Württemberg
regioKArgoTramTrain
Jointly moving people and goods