Thesis Raphaël LAMBERT

Handwriting deficits, also known as 'dysgraphia', affect 5 to 10% of school-age children. Currently, the diagnosis of dysgraphia is based on the BHK test which is relatively subjective. If they are not handled, these deificits rapidly impact the others scholar skills, eventually leading to scholar failure. It is thus crucial to diagnose and handle these deficits as early as possible.
While dysgraphia are pretty well described at the motor level in the literature(Danna et al, 2013; Smits-Engelsman & Galen, 1997; Hamstra-Bletz & Blöte, 1993), brain or oculomotor activities associated to handwriting deficits have been poorly investigated in children. Recently, a first algorithm for the automatic detection of dysgraphia has been developed (Asselborn et al, 2018), but technological improvements are required for its use in the dysgraphia diagnosis. In a previous project supported by the CEA Bottom-up program, an important database of handwriting has been collected in typical and dysgraphic children and handwriting parameters specific to dysgraphic children have been identified and used to develop our first algorithm. Performances achieved in terms of dysgraphia detection are around 85%.
The current PhD position aims at analyzing the handwriting in typical and dysgraphic children by using 3 simultaneous measurements: handwriting kinematic parameters, brain activity recorded by EEG and oculomotor activity recorded by eye tracking. From these data, contribution of EEG and oculomotor features in supervised machine learning models will be assessed. The final goal is to develop a new tool, automatic and reliable, for dysgraphia diagnosis.

Supervisors :
- Caroline JOLLY - caroline.jollyuniv-grenoble-alpes.fr (caroline[dot]jolly[at]univ-grenoble-alpes[dot]fr)
-  Jérôme BOUTET

Keywords : Dysgraphia,EEG,Handwriting,Eye tracking,Child development,Supervised machine learning models,