###M-IoT: Straightening the IoT medical ecosystem
Project ID: 2228bd1204 (You will need this ID for your application)
Research Theme: Digital Security and Resilience
UCL Lead department: Electronic and Electrical Engineering (EEE)
Lead Supervisor: Anna Maria Mandalari
Project Summary:
Internet of Things (IoT) devices are increasingly being used in the health and medical domain, providing monitoring and home care solutions for a range of conditions including elderly care and monitoring. These devices often come with a range of sensors and actuators, require access to a number of personal data sources and continuous internet connectivity, and are equipped with a variety of embedded pre-trained Machine Learning (ML) models. The data from these devices is often available through the cloud-based solutions provided by the manufacturers, with varying resolution and aggregation strategies, increasing the risk of security and privacy threats.
In this project, I propose to translate the lab-based platform into a home gateway setting, ready for real-world trials. I will adopt lightweight ML models from our advanced IoT labs, integrate the crowdsourced component, and enable privacy-preserving device behaviour analytics gathering through Federated Learning (FL). Our approach enables translation of lab-based experiments into a proof-of-concept prototype on a home gateway, and to be evaluated with real patients taking part in large-scale trials. Working directly with the NHS and the UK Dementia Research Institute as a partner, I aim to use the findings from our existing research and the wealth of knowledge gained from the past projects to provide a simple and intuitive interface for the patients, while providing a privacy-preserving data collection mechanism via the gateway. The project has the following three main objectives:
(i) Port and evaluate latest security threat analysis, and privacy features, on a real industrial gateway; (ii) Implementation and evaluation of feasibility of crowdsourcing IoT behavioural insights using FL; (iii) Conduct a demonstrator use cases with NHS Patients and UK Dementia Research Institute volunteers.