Methodology

 
Initiated by the pioneer work of [1] on fuzzy logic (FL), almost fifty years later, FL-based inference systems (FL-ISs) have become one of the most famous fields of FL. The main reason of the latter is the ability of FL to incorporate human’s expert knowledge with its nuances, as well as to express the behavior of the system in an interpretable way for humans.
In this way, innovative modelling/analysis techniques are used in the A/B/C-TEACH modelling module (see Menu Item Arquitecture) by incorporating hybrid and innovative processing techniques from the fields of fuzzy set theory, neuro-fuzzy modelling, intuitionistic fuzzy systems, dynamic nonlinear analysis, and affective computing. More specifically:
 

 (i) The FuzzyQoI model [2], which incorporates LMS Moodle metrics
to estimate the users’ Quality of Interaction (QoI) using fuzzy logic.

 

(ii) The Collaboration/Metacognition-Adaptive Fuzzy Model (C/M-AFM) [3], which supports the advancement of online collaborative skills, employing a neurofuzzy structure to model the individual collaborative strategy across sessions of peers’ collaboration, i.e., at the micro-level. Using this knowledge, the C/M-AFM estimates the value of a feedback indicator concerning the quality of the individual collaborative activity (quality of collaboration–QoC) in a forthcoming session of collaboration.

 

(iii) The Intuitionistic Fuzzy Inference System (IFIS) [4], where the expert’s hesitancy is incorporated within the construction of the fuzzy rule base, producing more reliable estimation of peers’ QoC, when considering the peers’ turn-taking (TT), action types (AT), entity types (ET), balance (B), productivity (P) and cognitive rate (CR).

 (iv) The codding for the dynamic nonlinear analysis
of the collaborative TT [5] per contribution type [6] among peers’ interaction.
 

and (v) Block-diagram of an emotion recognition process using EMOTIV EPOC Headset
and EEG analysis [7].