Brain Signals Classification Based on Fuzzy Lattice Reasoning

Cyber-Physical System (CPS) applications including human-robot interaction call for automated reasoning rational decision-making. In the latter context, typically, audio-visual signals are employed. Τhis work considers brain emotion recognition towards an effective interaction. An ElectroEncephaloGraphy (EEG) signal here is represented by Intervals’ Number (IN). IN-based, optimizable parametric k Nearest Neighbor (kNN) classifier scheme decision-making fuzzy lattice (FLR) proposed, where conventional distance between two points replaced a order function (σ) reasoning-by-analogy. A main advantage of employment INs that no ad hoc feature extraction required since IN may represent all-order data statistics, features considered implicitly. Four different functions employed in this work. Experimental results demonstrate comparably good performance proposed techniques.