Projects
SHERO : Self-HEaling soft RObotics Vrije Universiteit Brussel
While artificial intelligence, robotics and computing power advance at a stunning pace, the physical interactions between such systems remain as an unsolved question. Replacement aftermarket parts for robotics account for $400 billion a year. This figure, comparable to the entire GDP of Belgium, could be reduced if smart materials were combined with robotics and AI to heal robotic parts or prevent damage. The natural healing ...
Encouraging Lifelong Learning for an Inclusive and Vibrant Europe KU Leuven
The ENLIVEN research models how policy interventions in adult education markets can become more effective. Integrating state-of-the-art methodologies and theorisations (e.g. Case-Based Reasoning methodology in artificial intelligence, bounded agency in adult learning), it implements and evaluates an innovative Intelligent Decision Support System to provide a new and more scientific underpinning for policy debate and decision-making on adult ...
Towards Context-aware Implicit Multimodal Human-Computer Interaction Vrije Universiteit Brussel
Over the last decade, we have seen a clear trend towards smart environments and living spaces where information processing is embedded into everyday objects. This introduces some challenges in terms of human-computer interaction: How should we design any implicit interaction for these sensor-based systems? The intelligent interpretation and adaptation of human-machine interaction is addressed by the rapidly emerging ...
MIRAD-An Integrated Methodology to bring Intelligent Robotic Assistive devices to the user "MIRAD" Vrije Universiteit Brussel
Intelligent decision and prediction methods using fuzzy sets in warning systems Ghent University
This project has two objectives: (1) To develop a general framawork of integrated warning system (WS). This framework will contain both technical and organisational elements and their relationships, which will particulary look at both an early warning generation from information fusion and decision making from warnings. (2) To develop a new fusion methodology to manage uncertain information (using fuzzy sets and fuzzy case-based reasoning) in ...
A thorough study of spatial reasoning for intelligent information retrieval Ghent University
The main goal of this project is to develop reasoning techniques and algorithms to cope with spatial information in the context of, predominantly geographical, information retrieval systems. The vagueness, unreliability and diversity of the available information will play a central issue in this.
ARCHIMEDES: Accelerometry and Reservoir Computing for Home-compatible Intelligent Multimodal Early Detection of Epileptic Seizures Ghent University
This project tackles fundamental resesarch on the technology needed for an automatic epileptic seizure detection system. It uses flexible and stretchable substrates with various sensors, it processes EEG signals and other measurement data and it uses the reservoir computing neural network technique. This leads to a fast detection system, tailored to individual patients and fit for a home detection system.
Probing the neural correlates of perception and cognition using population decoding KU Leuven
From the moment we open our eyes, we receive an overwhelming amount of information about the world in front of us. While incredibly complex, our brain makes sense of this information effortlessly through the coordinated action of a large number of cortical areas and processes. Developing artificial systems that can perceive the visual world as efficiently as humans do has always been one of the central quests of artificial intelligence. In ...
Efficient scheduling and compilation of embedded multi-core AI platforms KU Leuven
The future of artificial intelligence strives for powerful machine inference in resource-scarce distributed devices. To allow intelligent applications at ultra-low energy and low latency, it becomes increasingly clear that every intelligent edge device will need to be equipped with a diverse set of many heterogeneous co-processors, which allow to run every workload at the most compatible (combination of) accelerators. Moreover, using multiple ...