The aim of this work is to analyze complex data from a Brain Computer Interfaces (BCI) study using
multivariate statistical methods (PCAmix approach and clustering of variables) to better understand and interpret their
relationships. This article presents clustering of variables which aim is to lump together strongly related variables. The
proposed approach works on a mixed data set, i.e. on a data set which contains numerical variables and categorical
variables. Two algorithms of clustering of variables are described : a hierarchical clustering and a k-means type clustering.
A brief description of PCAmix method (that is a principal component analysis for mixed data) is provided, since the calculus
of the synthetic variables summarizing the obtained clusters of variables is based on this multivariate method. Finally, the
PCAmix and ClustOfVar approaches (implemented in the R packages ClustOfVar and PCAmixdata) are illustrated on a
real dataset from a BCI (brain computer interface) study. Recommendations, based not only on performance, efficiency,
but also on satisfaction criteria, could be made concerning the choice of interface in the use of virtual keyboards, especially
for people with motor disorder such as Charcot’s disease.
With the migration of responsibility from drivers to automation systems in vehicles, there are potential risks to be studied due to “out-of-the loop” issue induced by the automated driving. To investigate these potential risks, two complementary experiments were implemented on a driving simulator. The 1st experiment investigates vehicle automation in highway traffic jam conditions. Main findings indicate that increased automation of Level 4 (compared to L3) was assessed as more useful by the participants, reducing the task difficulty and annoyance. The 2nd experiment focused on critical driving conditions and automation’s effect on participants’ Situational Awareness (SA), their criticality assessment, their ability to resume manual control when necessary, or their confidence in an automated system managing the risk for them. Main findings of this 2nd experiment found several effects of vehicle automation on drivers’ SA and risk assessment, or on their visual scanning behaviours, however this was dependent of the participant’s level of driving experience. Finally, eye tracking data collected during the second experiment were used in a cognitive model (named COSMODRIVE) to simulate some effects of vehicle automation of drivers’ visual scanning. This modeling work is presented in the last section of the article.
After mentioning the six paradigms of the learning process, one of Edelman contribution to the theory is explained. Its application to the learning process of reading shows how important it is to link it with writing.
Converging technologies, or NBIC neotechnologies, are the subject of all the hopes, fears and resistances that support the moral positions developed and promoted by citizens facing the exponential development of these technologies. These positions can be schematically distinguished into four main trends, which are themselves modified by the ethical value that individuals place on issues of application of technologies.