Title: Real-time Adaptive Virtual Reality for Pain Reduction
Virtual Reality has been proven to be an effective tool in helping patients cope with pain through distraction. Past studies have shown that patients who made use of Virtual Reality reported drops in pain scores of as much as 50%. However, what has already been implemented often assumes a one size fits all approach which introduces a risk in that the technology might not be suitable for all patients or that the method of therapy using VR might not be as effective across different patient groups. This research therefore looks at tackling these risks. Through the use of Virtual Reality and Artificial Intelligence we will provide patients with a game that is able to adapt to the patient’s affective state in real time. We are combining three concepts synonymous with Artificial Intelligence; Affective Computing, Serious Games and Virtual Reality. The aim is to provide patients with an adaptive game that is able to react to human emotions, to keep the patient constantly engaged with what is happening in the game thus making it less likely that attention will shift to the pain symptoms one would normally feel.
Researchers: Prof. Alexiei Dingli, Luca Bondin
Further notes: The project also has the backing of the Sir Anthony Mamo Oncology Hospital (SAMOC), and has also received backing from the Stanford Virtual Human Interaction Lab.
Title: Intelligent Digital Twin project.
This project aims to provide a high-level intelligent solution to enhance the processes and operations of STMicroelectronics manufacturing facilities and factories. In these days, manufacturers are in a desperate need to rethink about the current statistics maturity, the productivity levels, and the product lifecycles. More than any time before, the researchers at the University of Malta, Department of Artificial Intelligence, strongly believe that it is a high time to experience.
Company: Transport Malta (TM), Institute of Climate Change, Destinations Project (CIVITAS)
Brief description: The area of Intelligent Transport Systems has been an important area in traffic management and intelligent systems for the past decades. Developing and designing an Intelligent Transport System that is able to model real live traffic data using information mined from the internet is beneficial given how inexpensive such a system is. The development of Intelligent Transport Systems for traffic orchestration is divided into three separate sections. Initially, the information is sensed using a variety of IoT sensors such as inductive loops, magnetic loops, infrared, acoustic detectors and IP cameras. The information gathered by these sensors is then converted to a digital representation representing traffic before a final orchestration agent digests this information to manage traffic control structures. Currently, we have successfully managed to develop a system that uses low quality (360p, 480p) IP Camera feeds to extract information such as vehicle counting, traffic flow, car speeds and lane detection with an accuracy of over 90% during the day. Ongoing research will focus on the development of orchestration agents using techniques such as Deep Reinforcement Learning trained upon the real world data gathered by our system in order to manage traffic lights, message boards and tidal lanes and autonomously adapt policies depending on the traffic situation. The modality of the system also allows for the potential development of models that detect dangerous driving and accident detection. This project is in collaboration with the Institute of Climate Change and Sustainable Development and Transport Malta through the CIVITAS 2020 Destinations Project.
Who's involved in the collaboration:
Mark Bugeja - Ph.D. Researcher
Prof. Alexiei Dingli - Supervisor
Prof. Maria Attard - Supervisor
Dylan Seychell - Supervisor
NotaryPedia: a Knowledge Graph of Historical Notarial Manuscripts
The Notarial Archives in Valletta are a treasure trove for Malta’s history and house an invaluable collection of around twenty thousand notarial deeds dating back to the 15th century. NotaryPedia project bridges the research areas of Humanities and Artificial Intelligence and makes the Notarial Archives more accessible to historians and the general public.
Machine learning techniques are used to automatically extract entities, key phrases and relations from deeds, written in Medieval Latin, to populate the Notarypedia Knowledge Graph. This knowledge structure represents facts about people, places and things, and how these entities are all connected, thus allowing for better data integration, knowledge discovery and in-depth analysis of the historical notarial domain. An ontological representation for notarial deeds has also been defined. Furthermore, a Knowledge Graph is not complete upon construction and refinement techniques need to be used to introduce, delete and modify knowledge. In Notarypedia, Knowledge Graph completion is achieved through link-prediction techniques based on TensorFlow and inference techniques. Evaluation included the use of different translational distance models to predict relations amongst literals by promoting them to entities and to infer new knowledge from existing entities.
Dr Charlie Abela
Dr Joel Azzopardi
Ms Charlene Ellul (Research Support Officer I)