Sort by
Refine Your Search
-
LEO, MEO, and GEO constellations), and complementary on-board sensors. Research will investigate algorithms for robust multi-sensor fusion and positioning assurance. A strong emphasis will be placed
-
research group, which leads pioneering work in multi-sensor navigation, signal processing, and system integrity for aerospace, defence, and autonomous systems. The research will deliver a comprehensive
-
prototype/demonstrator of a low-cost smart sensor. To develop an efficient algorithm to process the vibration signals locally and to develop the firmware to be embedded within the sensor node. To validate
-
capable of leveraging signals from terrestrial base stations, non-terrestrial networks such as LEO satellite, and complementary on-board sensors. Specifically, it will: To design reconfigurable airborne
-
sensors, firmware-controlled automation, wireless connectivity, and maintenance algorithms. Students will design, build, and test smart sanitation solutions that can monitor system performance, optimize
-
—remains a critical challenge. This project will focus on designing AI-driven cognitive navigation solutions that can adaptively fuse multiple sensor sources under uncertainty, enabling safe and efficient
-
sustainability. The research will delve into power-aware computing strategies, thermal management, and the development of algorithms that balance performance with energy consumption. Students will aim to create
-
, predictive maintenance algorithms, and digital twin technologies tailored specifically for healthcare, aviation, and sanitation industries. You will identify critical operational pain points within
-
AI techniques for damage analysis in advanced composite materials due to high velocity impacts - PhD
Thermography. This raw dataset is needed to be processed and annotated to train supervised and unsupervised AI models. The research will aim to develop deep learning algorithms for damage classification
-
for Pollinator Monitoring: Train and optimise deep learning models for pollinator detection and classification using annotated image datasets. Post-processing object tracking algorithms will be incorporated