Comparison of Data Reduction Methods for the Analysis of Iyashi Expressions using Brain Signals

  • ROMERO Julian
    InterLocus, Inc. Meiji Institute for Advanced Study of Mathematical Sciences, Meiji University
  • DIAGO Luis
    InterLocus, Inc. Meiji Institute for Advanced Study of Mathematical Sciences, Meiji University
  • SHINODA Junichi
    InterLocus, Inc. Meiji Institute for Advanced Study of Mathematical Sciences, Meiji University
  • HAGIWARA Ichiro
    Meiji Institute for Advanced Study of Mathematical Sciences, Meiji University

抄録

Recent advances in simulation in science and engineering are focusing on automatic measuring of human-feelings about a product design by using Kansei Engineering words. Iyashi is a Japanese word used to describe a peculiar phenomenon that is mentally soothing, but is yet to be clearly defined. This paper explores the analysis of Electro Encephalogram (EEG) brain signals (Alpha, Beta) as a method to determine when a stimulus (face images) generates Iyashi in a person and produces good feelings. NeuroSky B3 Headband is used as a device to obtain the EEG signals and Holographic Neural Networks (HNN) are evaluated to predict the level of Iyashi. Nine data dimensionality reduction algorithms for brain signals are explored to improve the level of prediction of the HNN. The experimental results show that the percent of prediction with HNN can be increased in more than 10% if data reduction methods are applied to Beta brain waves.

収録刊行物

被引用文献 (1)*注記

もっと見る

参考文献 (7)*注記

もっと見る

関連プロジェクト

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ