Periodic Reporting for period 2 - CybSPEED (Cyber-Physical Systems for PEdagogical Rehabilitation in Special EDucation)
Reporting period: 2019-12-01 to 2022-07-31
In conclusion of the action, the project has contributed a significant advance in the state of the art of the field. The grounds for sound experimental research have been laid, with some experiments already under way with active participation of social stakeholders, namely in Greece and Bulgaria, led by IHU and IR-BAS, respectively. On the scientific production side, CybSPEED researchers have produced 39 gold open access publications in journals listed in the JCR or similar rankings, 39 green open access publications, 81 conference presentations, some of them published afterwards as green open access, 3 open data publications, and 7 open source software publications. Relations with third country partners have been strengthened and shown to be highly productive.
Secondly, the training, courses and conferences proposed in the project have been realized with minor o no delay. One of the keys to the success of these activities has been the willing participation of the researchers from all the beneficiaries and partners, that have adjusted their agendas in order to attend.
Thirdly, the scientific work was carried out smoothly along with the dissemination works. We have achieved a large number of open access publications, including open source software and open data, and conference presentations, some of them invited as keynote speakers. Moreover, despite the strong restrictions imposed by the pandemic, experimental work that will be providing new evidences and material for further publications and advances have already started in Greece and Bulgaria. These works will continue after project termination and the results will be reflected on the updated web site of the project.
Fourthly, we have also been active trying to reach out to the general public. We have achieved some moderate media impact that we expect will increase when the new experiments and results will be available. Reach out activities targeting specific audiences, such as parents, professional educators and researchers have had a moderate impact in the press and the general media.
- A theoretical framework for CPSs for pedagogical rehabilitation in special education;
- CPS model for pedagogical rehabilitation in special education based on Lattice Computing (LC) and other computational modelling approaches;
- Developed innovative LC models to fit cognitive biometrics signals recorded by advanced interfaces (brain-computer, eye-gaze tracking and virtual reality);
- A novel method for transformation of (numerical) signals such as images to (nonnumerical) symbols toward an effective data compression for communication of robots with one another (as well as with humans) being endowed by novel synthetic sensors;
-A model for representation of (nonnumerical) notions from psychology in computational models, including the notion “Gestalt”, with noticeable pedagogical effect;
Designs of optimal educational scenarios toward maximising the educational outcome estimated by cognitive biometrics data such as eye tracking and EEG data.
Work by IR-BAS has focused on the following aspects:
The societal implications in better understanding of the learning needs of children and provision of advanced technological support; better understanding of the professional needs of teachers and provision of advanced tools for individualised work with children; more entertaining learning environment for children, expert system support to the teaching process, reduced number of tests in class and the respective stress level on children in standard and special education.
Models for CPS have been developed with emphasis on logic/reasoning techniques building on novel computational (e.g. Fuzzy Lattice Reasoning) methodology. A platform for sensation restoring via virtual reality will be integrated as a novel type of human-robot interface in the overall system, based on extension of research on muscle computer interaction (muCI) and learning with limited sensor abilities. Research on life-long learning implementing deep learning techniques has been carried out with application to user preference modelling required by personalised human-robot interaction. The approach for validating educational situations (games) for children with special learning needs, describing the transition from one experiment in real-life conditions to another, not just from pilot to real-life testing, forwarded recently by IR-BAS, has been further developed.
Work by CVC, UPV/EHU, UH2C, and UCH was devoted to intelligent system design and data analysis to support the experimental results that will be provided by PRAXIS, UGA and IR-BAS researchers. Specifically aiming to the modeling of the behavioral and neural responses of children with special needs and the effect of CPS on their learning performance.