RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication
Artículo científico (JournalArticle)
An ACO-based personalized learning technique in support of people with acquired brain injury
The ever-increasing cases of acquired brain injury (ABI), especially among young people, have prompted a
rapid progress in research involving neurological disorders. One important path is the concept of relearning,
which attempts to help people regain basic motor and cognitive skills lost due to illness or accident.
The goals of relearning are twofold. First, there must exist a way to properly assess the necessities of an
affected person, leading to a diagnosis, followed by a recommendation regarding the exercises, tests
and tasks to perform; and second, there must be a way to confirm the results obtained from these
recommendations in order to fine-tune and personalize the relearning process.
This presents a challenge, as there is a deeply-rooted duality between the personalized and the generalized
approach. In this work we propose a personalization algorithm based on the ant colony optimization
(ACO), which is a bio-inspired meta-heuristic. As we show, the stochastic nature of ants has certain
similarities to the human learning process.
We combine the adaptive and exploratory capabilities of ACO systems to respond to rapidly changing
environments and the ubiquitous human factor. Finally, we test the proposed solution extensively in
various scenarios, achieving high quality results.
© 2016 Elsevier B.V. All rights reserved, This research has been funded by the Spanish Ministry of Economy and Competitiveness and by the FEDER funds of the EU under the project SUPEREMOS (TIN2014-60077-R) and insPIre (TIN2012-34003). Kamil Krynicki is supported by the FPI fellowship from Universitat Politecnica de Valencia.