• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2023 Fiscal Year Final Research Report

Estimation of dream content by machine learning using magnetoencephalographic data.

Research Project

  • PDF
Project/Area Number 19K16244
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 45060:Applied anthropology-related
Research InstitutionKyushu University

Principal Investigator

Motomura Yuki  九州大学, 芸術工学研究院, 助教 (50645273)

Project Period (FY) 2019-04-01 – 2023-03-31
Keywords夢 / 機械学習 / レム睡眠 / 脳波
Outline of Final Research Achievements

In this study, we attempted to construct a machine-learning algorithm to determine the affective value (negative or positive) of dreams using physiological indicators such as EEG, eye movements and heart rate. Using physiological data obtained simultaneously with dream reports during REM sleep acquired at Hiroshima University, we constructed a machine learning algorithm for feature selection using random forests and BORUTA. As a result, we were able to discriminate the emotional valence of dreams with nearly 70% accuracy.

Free Research Field

精神生理学

Academic Significance and Societal Importance of the Research Achievements

悪夢はうつ病や自殺の予測因子であることがわかっていることから、本成果で構築した夢の情動価判別アルゴリズムは悪夢の検知によるうつや自殺の予防法開発等に役立つ可能性があります。さらにエンターテインメント分野においても、夢の内容にアクセスする新たなインターフェースの開発にも貢献すると考えられます。また本研究の特色として、大型の機器を使用せず、脳波や生理反応など比較的簡便に測定できる手法を用いていることから、応用可能性が高いこともあげられます。

URL: 

Published: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi