Despite the advances in Affective Computing, the application of affect models is still narrowly limited to answering questions like: "What is the mental state of patients while interacting with a robot?", "What emotions does an advertisement elicit in viewers?", "What is an actor's emotion in a scene?" or "What is the user's emotional state while playing a game?". From the above, it becomes apparent that affect models are context-dependent and cannot answer questions like "Why do these emotional states appear?" or "What are the elements of the context that cause the specific emotions?". The next generation of affect models should be context-invariant and able to identify and exploit cause-effect relations in humans’ emotional manifestation. ERICA is an ambitious project that aims to design affect models that use the ubiquitous cause-effect mechanisms in humans’ emotional expression.
This is a locally funded project in collaboration with ST Microelectronics. This is a work-in-progress project that aims to provide a high-level intelligent solution to enhance the processes and operations of ST Microelectronics 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 life cycle. 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 explore new areas, and ways of doing things, that can lead to smarter, more developed, and more efficient production processes and operations.
Researchers
This is a locally funded project in collaboration with ST Microelectronics. Deep Learning methodology is often a black box. In cases of Enterprise, management finds itself unable to trust results which only present accuracies as a performance metric. We are looking to improve Fairness, Accountability and Transparency in AI by developing an XAI decision support system for such companies. For these reasons, we proposed the MIRAI architecture. By using Transparent by Design methodologies, we want to not only deliver reasonable explanations for our AI’s performance, but also have performant results as we move forward to newer and better algorithms.
Researchers
Prof. Alexiei Dingli
Dr Vanessa Camilleri
Ms Natalia Mallia is conducting research for her M.Sc. degree in AI
Research being conducted through the collaboration with Parliament and MITA is entitled, apps4Parliament. This project seeks to create a number of apps intended to reach out to citizens and inform them about Parliamentary work and procedures by making collections of Parliamentary data more open, searchable and accessible.
The first app created as part of this project is called PQViz. This app exploits the Maltese PQ data by leveraging on the interaction between Members of Parliament (MPs) from the different parties and presents an interesting, interactive visualisation through which users can more intuitively understand questions like: who asked whom about what, who asked the most and who answered the most PQs. The aim of this app is to increase awareness into the operation of Parliament, and also provide transparency into its operations.
Research into this app involves the processing of the PQs Open Data to extract the ‘useful’ relevant information, and visualise this information by utilising the most suitable format.
Researchers
Dr Charlie Abela
Dr Joel Azzopardi
Additional links
The collaboration with the Ministry for Gozo involved the development of online services that rendered governmental services offered by the ministry more accessible to the citizens. The developed services were linked to government central registers where possible in order to adhere to principle of single data entry promoted by the government. The back-end services provided data aggregations and visualisations to assist with the management of the submitted data.
Researchers
Dr Charlie Abela
Dr Joel Azzopardi
This research is being conducted in collaboration with the Office of the Notary to Government and Notarial Archives. 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 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 information from deeds, written in medieval Latin, and to represent this information as a 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.
Researchers
Dr Charlie Abela
Dr Joel Azzopardi
Additional links
NotaryPedia, an exciting project run by the Maltese notariat, Notaries of Europe, February 2019
Charlene Ellul, Charlie Abela, Joel Azzopardi, 2018, 'Extracting Information from Medieval Notarial Deeds' in Proceedings of the EKAW 2018 Posters and Demonstrations Session co-located with 21st International Conference on Knowledge Engineering and Knowledge Management (EKAW 2018), Nancy, France, pp.25-28
