Federated Learning and Interoperability Platform for Medical Imaging Applications (2021 - Present)
Federated Learning and Interoperability Platform for Medical Imaging Applications (2021 - Present)
At the AI Centre, we are developing technology that allows us to access large volumes of well-curated clinical data in a controlled environment, with the appropriate technical architecture, governance, and clinical expertise. Using the MONAI framework to access the latest AI and machine learning models, we are creating applications that will drive innovation in healthcare and allow for the fundamental redesign of clinical pathways to improve outcomes and reduce costs. We are developing two platforms, AIDE and FLIP, which will provide access to high-quality electronic health data for the purpose of development and deployment of AI Technology. They will enable NHS trusts to test and deploy AI in clinical practice and share data in a way that is safe and secure.
We developed drone robotic fish. This was a commercial water-borne self-maneuvering device used to collect water samples from flowing waters in streams and rivers. The data collection and onboard analysis will help in monitoring drinkable waters and safe-guard against water-borne diseases. In addition, we will be able to develop preventive strategies to combat viral diseases and bio-terrorism related activities.
The aim of this project was to enable decentralization, trust, and incentive mechanisms in NIST’s conceptual model for smart grid.
The project was part of a collaboration between researchers from centre for cyber physical systems of KU and MIT’s media lab.
We investigated the technical issues related to trust and its implications on cryptocurrency ecosystem.
We enabled and evaluated trustworthy cryptocurrency ecosystem for CPS.
The project was the collaboration between researchers from centre for cyber physical systems and American university of Beirut.
We built blockchain based decentralized AI framework to enable consensus based decision making in CPS.
We developed a three-tier intelligent computing architecture for mobile data stream mining applications in MECC systems.
We tested the proof-of-concept with real implementation of activity detection applications for smart cities and results were published in numerous high impact research venues.
We developed a test-bed to analyze the performance of frequent pattern mining applications on mobile devices. The results were published in IEEE/scopus-cited conference.
I served as co-supervisor of two PhD students (Uzair Iqbal and Qurat-ul-ain Mastoi) from Unversity of Malaya (UM). This project is part of collaboration between researchers from faculty of computer science and information technology and UM medical centre.
We developed a test-bed for adaptive scheduling of data stream mining tasks to gracefully and collaboratively execute in mobile (i.e. resource-constrained) and cloud (i.e. resourceful) systems.