The overall goal of my research is to learn, reason and act based on data. My work to date accomplished this goal by developing data-driven approaches for addressing challenges associated with modelling, prediction and control in complex, real-world systems evolving over time, lying at the intersection of rigorous analysis with practical relevance. I have been particularly drawn to problems that involve modelling type 1 diabetes subjects data obtained from sensing platforms and health records, and large-scale networks of open channels from sensors and weather related information. Brief summaries of the projects I have participated in are provided below.
- Diabetes Care Type 1 diabetes (T1D) is a prime candidate for the development of a treatment strategy using biomedical control. In this disease, the destruction of pancreatic beta cells leaves the body incapable of producing insulin, a hormone that is required for the glucose homeostasis feedback loop. The current standard of treatment is for people with T1D to measure their blood glucose concentration several times per day and manually deliver corresponding doses of insulin based on rules-of-thumbs. My objective within this framework is to automate treatment by artificially recreating the glucose control feedback loop using a combination of medical devices. [more]
- Water management in large scale irrigation networks
In order to fully receive all the benefits that automation provides, also the large transport channels should be controlled automatically. However, due to the behaviour of these channels when there are strong winds blowing, it has so far been difficult to get acceptance for such a proposal. The work I carried out at the University of Melbourne provides a significant step towards the design and implementation of reliable controllers under strong wind conditions, such that the full benefit of automation can be achieved. [more]
A high-bandwith robot-workpiece interaction requires a stiff robot without resonances in the frequency range of operation. In this work, the compliance dynamics of the Gantry-Tau parallel kinematic robot were identified using subspace-based identification and physical modelling. Measurements were performed both with a camera vision system developed and with a laser tracker. Although promising simulation results for another Gantry-Tau prototype exist, both vision and laser tracker experiments identified multiple resonances around 14 Hz, which can reduce force control performance. [more]