BSc MSc PhD FHEA
Position: Senior Analyst/Developer (Imardis)
Office: Room 403, Dean Street
As a practical person my interests are on the applied side of engineering – how can we use technology to solve the problems that society faces. I am a passionate advocate for all forms of renewable energy. As a data analyst / computer programmer I am interested in the use of modern data analysis and visualisation techniques when applied to large datasets, especially those coming from the ever growing number of IoT sensors. My practical research interests are in the fields of applied photovoltaics, embedded microelectronics and wireless sensor networks, and I am particularly interested in the use of organic photovoltaics for solar energy harvesting.
Offshore Renewable Energy
I currently work on the Imardis project and our aim is to bring together diverse ocean science datasets and make them available to various research and commercial partners within the offshore renewable and ocean sciences community through our map-based portal (https://portal.imardis.org/). Our intention is to add value to this data by combining datasets together with model outputs and applying modern data analysis and visualisation techniques (e.g. AI, ML, augmented reality, digital twins etc).
Internet of Things (IoT)
Having spent several years designing and building low power wireless sensors for various partners across the spectrum, from agri-tech to social housing, I have a lot of experience in this area, especially in the field of LoRaWAN communications technology. My interest now is in developing solutions for managing this large volume of data, so that it can be used effectively. We are also looking at developing machine learning techniques to make use of the large amounts of data that IoT devices generate. I am always looking for new sources of data that we can manage and analyse and would welcome approaches by any interested parties.
We are working on various data science applications, especially in the area of data forecasting; using past data to predict future performance. As the amount of data created by IoT devices increases it becomes harder to make full use of it and this is where data forecasting using artificial neural networks comes into its own. We are always looking for more opportunities to utilise these techniques.