Keywords: AES, traces of interaction, modeling of knowledge and reasoning, disabilities.
In accordance with the third thematic of the SILEX team “Systèmes adaptatifs pour la
Co-construction d'activités interactives”( Adaptive Systems for the co-construction of interactive activities), the subject of the PHD focuses on the Adaptive Educational Systems (AES) dedicated to persons with disabilities. These systems will be capable to propose learning scenarios adapted to the needs of each user taking into account his profile and his behavior.
In this case, we distinguish generally between the adaptation of pedagogical content and adaptation of interface. Where, the former is done according to the domain knowledge and pedagogical objectives, while the latter is done according to the user’s preferences. The limitations of majority of the existing approaches rest principally in the absence of taking into account the cognitive and physical capacities of the user. In fact, the latter have a huge influence on the aptitude of the user in effectively carrying out his tasks on the one hand and, on the other hand, it permits to determine the way with which the user can interact with the system or perceive its state. This information proved to be critical in decision making regarding the persons with “disabilities” and more generally, can potentially be helpful for everyone (for example: old persons, a person in a situation where his hands, his eyes are occupied, etc.).
The first objective of this PhD is to propose a formal model of adaptive learning scenarios according to the expert’s knowledge, user profile (in particular his cognitive and physical capacities) and pedagogical goals of the session. Thus, the model will allow the AES to adapt itself to each user, in particular, generate the most suitable set of activities and problems according to the user’s capacities. In this sense, the model must therefore keep in account the interaction modalities as objects of interaction. That is, to compare the properties of each modality with the user’s cognitive and physical capacities in order to detect the eventual discrepancies and to determine, as a result, the privileged interaction modalities. For example, it can be the presence of a disability engine of the user, which leads to an incapacity of the user to use the computer device with a gestural mode of communication or an important visual discrepancy, which makes it necessary to present the content differently.
The second objective of this study is to propose the methods which permit to evaluate the domain knowledge and user’s profile while analyzing the user’s traces of interaction. These traces of interaction represents the user’s actions (in the formalism of M-Traces[1], developed by SILEX) during his interaction with learning scenarios. We assume that the transformation of traces can provide the expert tools for updating of the user’s profile and domain knowledge.
Finally, the third objective of this study is to develop and test our future approaches (according to the two above mentioned objectives) in the project CLES (Cognitive and Linguistic Element Stimulation). CLES is a project FUI (Fonds Unique Interministériel) conducted in partnership with the laboratories EMC1, LUTIN2 and the society GERIP3. The objective of this project is to create an environment of “Serious Games” for therapeutic purposes. That is to propose the tools (based on serious games) for the reeducation and cognitive simulation for children, adults and seniors. This study will cover all the themes of speech (spoken language and written language), memory, calculation disorders, attention disorders, cognitive impairments, assessment of the cognitive skills and memory, voice disorders and audio and visual perception disorders.
For each pathology, this project aims to develop a software component that is focused on specific deficiencies while maximizing, through techniques employed in video games, their cognitive ergonomics. Based on these components, the aim of this PhD study, in this project, consists in developing a module capable of generating personalized courses according to the challenges faced and progress of each patient. This module should therefore keep in account
From what the practitioner has prescribed his patients
From the knowledge base of the treatments available for the pathology
Results of the previous exercises of the user
This module will also be able to help the practitioner in monitoring the progress of his patients in each learning session. The latter, once designed, will be subject to a validation process including clinical tests that will be conducted with project partners.