PhD in Human-Computer Interaction (Hci)

The e-Media Research Lab is a research section of Dynamical Systems, Signal Processing, and Data Analytics (STADIUS) in the Department of Electrical Engineering (ESAT) at KU Leuven. The e-Media Lab's research includes topics related to signal processing, data analysis, machine learning, and Human-Computer Interaction (HCI). E-Media made significant contributions to critical applications in the domains of healthcare, Industry 5.0, biomedical sensing, and education. In particular, e-Media is exploring novel tinyML technologies to enhance the intelligence and energy efficiency of resource-constrained devices./nAs climate change intensifies, clear-air turbulence in aviation becomes more severe, and natural disasters occur more frequently. Even with the current typical 10-day weather forecast in the troposphere (less than 20 km), the exact spatiotemporal mechanisms through which the Earth’s low altitudes (ELA) (less than or equal to 50 km) impact weather patterns remain insufficiently understood. In-situ sensing in ELA offers an opportunity to extend weather forecasts far beyond the current 10-day range, improve ozone observation, and enhance cosmic radiation monitoring. The rapid advancements in rotary-wing and fixed-wing unmanned aerial vehicle (UAV) technology make them a promising solution to densify ELA monitoring. However, expanding the density of meteorological sensors in the ELA to bridge the spatiotemporal meteorological gaps presents major fundamental challenges. First, the vast volume and heterogeneity of data generated by airborne UAV and Weather Balloon (WB) sensors strain efficient raw data transfer and require significant computational resources for centralized processing. Second, the existing centralized, terrestrial-based control infrastructure cannot scale with the increasing number of airborne sensors due to bandwidth and coverage constraints. These challenges are further exacerbated due to the limited energy budget and computational resources of the meteorological aerial sensor./nIn the first phase, this PhD project focuses on developing ultra-reliable spatiotemporal (4D) predictions using trustworthy, distributed AI-driven intelligence deployed across heterogeneous aerial nodes. To achieve this, an aerial platform featuring distributed computing within a mobile network of resource-constrained devices will be designed. Incorporating uncertainty-aware AI models will enhance trustworthiness and maximize resource efficiency. In the second phase, seamless integration of sensing, computation, and communication functionalities for context-aware self-organized aerial networks will be investigated./nLocation: Leuven, Belgium