Estimation of feeling based on EEG by using NN and k-means algorithm for massage system

The authors had proposed the intelligent massage system for the massage chair based on masseur´s workmanship which means the DB of the relation between the human skin elasticity and the force of finger pressure massage. Here, DB is not necessarily applicable to an unknown user without updating DB. However, the estimation of user´s uncomfortable feeling by finger pressure massage is necessary to update DB. Then, this paper proposes the estimation method of uncomfortable feeling based on EEG using the data clustering and the neural network. And, updating method of DB based on the proposed estimation method is also discussed. The realizability of the proposed estimation method is verified by the experimental works.