Tiny ML and Edge AI

• My research interest lies in the development of energy-efficient and low-latency machine learning models deployable on resource-constrained edge devices. TinyML and Edge AI represent a transformative shift towards intelligent, real-time decision-making at the edge, enabling applications in healthcare, IoT, agriculture, and smart cities. I am particularly focused on model optimization techniques such as quantization, pruning, and neural architecture search, as well as secure and privacy-preserving edge inference.

IoT – HCI and education

• I am also interested in the integration of IoT with Augmented Reality (AR) and Virtual Reality (VR) to create immersive, interactive, and data-driven educational environments. By leveraging real-time data from IoT sensors and combining it with AR/VR interfaces, I aim to design adaptive learning systems that respond dynamically to learners’ behaviour, environments, and needs. This includes applications such as smart classrooms, virtual labs, and remote learning setups where physical-digital interactions enhance engagement, contextual understanding, and experiential learning.